github/openclaw
1
0
Fork 0
mirror of https://github.com/openclaw/openclaw.git synced 2026-04-18 19:57:27 +00:00
Code Issues Packages Projects Releases Wiki Activity

refactor: rename to openclaw

Browse Source
This commit is contained in:
Peter Steinberger
2026-01-30 03:15:10 +01:00
parent 4583f88626
commit 9a7160786a
2357 changed files with 16688 additions and 16788 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
docs/CNAME
View File

@@ -1 +1 @@
docs.molt.bot
docs.openclaw.ai

6
docs/_config.yml
View File

@@ -1,4 +1,4 @@
title: "Moltbot Docs"
title: "OpenClaw Docs"
description: "A TypeScript/Node gateway + macOS/iOS/Android companions for WhatsApp (web) and Telegram (bot)."
markdown: kramdown
highlighter: rouge
@@ -22,8 +22,8 @@ defaults:
nav:
- title: "Home"
url: "/"
- title: "Moltbot Assistant"
url: "/start/clawd/"
- title: "OpenClaw Assistant"
url: "/start/openclaw/"
- title: "Gateway"
url: "/gateway/"
- title: "Remote"

18
docs/_layouts/default.html
View File

@@ -17,7 +17,7 @@
<script>
(() => {
try {
const stored = localStorage.getItem("moltbot:theme");
const stored = localStorage.getItem("openclaw:theme");
if (stored === "light" || stored === "dark") document.documentElement.dataset.theme = stored;
} catch {
// ignore
@@ -35,7 +35,7 @@
<header class="shell">
<div class="shell__frame" role="banner">
<div class="shell__titlebar">
<div class="brand" aria-label="Moltbot docs terminal">
<div class="brand" aria-label="OpenClaw docs terminal">
<img
class="brand__logo"
src="{{ "/assets/pixel-lobster.svg" | relative_url }}"
@@ -45,17 +45,17 @@
decoding="async"
/>
<div class="brand__text">
<div class="brand__name">Moltbot</div>
<div class="brand__name">OpenClaw</div>
<div class="brand__hint">docs // lobster terminal</div>
</div>
</div>
<div class="titlebar__actions">
<a class="titlebar__cta" href="https://github.com/moltbot/moltbot">
<a class="titlebar__cta" href="https://github.com/openclaw/openclaw">
<span class="titlebar__cta-label">GitHub</span>
<span class="titlebar__cta-meta">repo</span>
</a>
<a class="titlebar__cta titlebar__cta--accent" href="https://github.com/moltbot/moltbot/releases/latest">
<a class="titlebar__cta titlebar__cta--accent" href="https://github.com/openclaw/openclaw/releases/latest">
<span class="titlebar__cta-label">Download</span>
<span class="titlebar__cta-meta">latest</span>
</a>
@@ -90,7 +90,7 @@
<main id="content" class="content" role="main">
<div class="terminal">
<div class="terminal__prompt" aria-hidden="true">
<span class="prompt__user">clawd</span>@<span class="prompt__host">moltbot</span>:<span class="prompt__path">~/docs</span>$<span class="prompt__cmd">
<span class="prompt__user">openclaw</span>@<span class="prompt__host">openclaw</span>:<span class="prompt__path">~/docs</span>$<span class="prompt__cmd">
{% if page.url == "/" %}cat index.md{% else %}less {{ page.path }}{% endif %}
</span>
</div>
@@ -116,11 +116,11 @@
<footer class="terminal__footer" role="contentinfo">
<div class="footer__line">
<span class="footer__sig">moltbot.ai</span>
<span class="footer__sig">openclaw.ai</span>
<span class="footer__sep">·</span>
<a href="https://github.com/moltbot/moltbot">source</a>
<a href="https://github.com/openclaw/openclaw">source</a>
<span class="footer__sep">·</span>
<a href="https://github.com/moltbot/moltbot/releases">releases</a>
<a href="https://github.com/openclaw/openclaw/releases">releases</a>
</div>
<div class="footer__hint" aria-hidden="true">
tip: press <kbd>F2</kbd> (Mac: <kbd>fn</kbd>+<kbd>F2</kbd>) to flip

BIN
docs/assets/openclaw-logo-text.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 90 KiB

2
docs/assets/theme.js
View File

@@ -1,4 +1,4 @@
const THEME_STORAGE_KEY = "moltbot:theme";
const THEME_STORAGE_KEY = "openclaw:theme";
function safeGet(key) {
try {

14
docs/automation/auth-monitoring.md
View File

@@ -6,13 +6,13 @@ read_when:
---
# Auth monitoring
Moltbot exposes OAuth expiry health via `moltbot models status`. Use that for
OpenClaw exposes OAuth expiry health via `openclaw models status`. Use that for
automation and alerting; scripts are optional extras for phone workflows.
## Preferred: CLI check (portable)
```bash
moltbot models status --check
openclaw models status --check
```
Exit codes:
@@ -27,15 +27,15 @@ This works in cron/systemd and requires no extra scripts.
These live under `scripts/` and are **optional**. They assume SSH access to the
gateway host and are tuned for systemd + Termux.
- `scripts/claude-auth-status.sh` now uses `moltbot models status --json` as the
- `scripts/claude-auth-status.sh` now uses `openclaw models status --json` as the
source of truth (falling back to direct file reads if the CLI is unavailable),
so keep `moltbot` on `PATH` for timers.
so keep `openclaw` on `PATH` for timers.
- `scripts/auth-monitor.sh`: cron/systemd timer target; sends alerts (ntfy or phone).
- `scripts/systemd/moltbot-auth-monitor.{service,timer}`: systemd user timer.
- `scripts/claude-auth-status.sh`: Claude Code + Moltbot auth checker (full/json/simple).
- `scripts/systemd/openclaw-auth-monitor.{service,timer}`: systemd user timer.
- `scripts/claude-auth-status.sh`: Claude Code + OpenClaw auth checker (full/json/simple).
- `scripts/mobile-reauth.sh`: guided re‑auth flow over SSH.
- `scripts/termux-quick-auth.sh`: one‑tap widget status + open auth URL.
- `scripts/termux-auth-widget.sh`: full guided widget flow.
- `scripts/termux-sync-widget.sh`: sync Claude Code creds → Moltbot.
- `scripts/termux-sync-widget.sh`: sync Claude Code creds → OpenClaw.
If you don’t need phone automation or systemd timers, skip these scripts.

38
docs/automation/cron-jobs.md
View File

@@ -17,7 +17,7 @@ cron is the mechanism.
## TL;DR
- Cron runs **inside the Gateway** (not inside the model).
- Jobs persist under `~/.clawdbot/cron/` so restarts don’t lose schedules.
- Jobs persist under `~/.openclaw/cron/` so restarts don’t lose schedules.
- Two execution styles:
- **Main session**: enqueue a system event, then run on the next heartbeat.
- **Isolated**: run a dedicated agent turn in `cron:<jobId>`, optionally deliver output.
@@ -151,8 +151,8 @@ Prefixed targets like `telegram:...` / `telegram:group:...` are also accepted:
- `telegram:group:-1001234567890:topic:123`
## Storage & history
- Job store: `~/.clawdbot/cron/jobs.json` (Gateway-managed JSON).
- Run history: `~/.clawdbot/cron/runs/<jobId>.jsonl` (JSONL, auto-pruned).
- Job store: `~/.openclaw/cron/jobs.json` (Gateway-managed JSON).
- Run history: `~/.openclaw/cron/runs/<jobId>.jsonl` (JSONL, auto-pruned).
- Override store path: `cron.store` in config.
## Configuration
@@ -161,7 +161,7 @@ Prefixed targets like `telegram:...` / `telegram:group:...` are also accepted:
{
cron: {
enabled: true, // default true
store: "~/.clawdbot/cron/jobs.json",
store: "~/.openclaw/cron/jobs.json",
maxConcurrentRuns: 1 // default 1
}
}
@@ -169,13 +169,13 @@ Prefixed targets like `telegram:...` / `telegram:group:...` are also accepted:
Disable cron entirely:
- `cron.enabled: false` (config)
- `CLAWDBOT_SKIP_CRON=1` (env)
- `OPENCLAW_SKIP_CRON=1` (env)
## CLI quickstart
One-shot reminder (UTC ISO, auto-delete after success):
```bash
moltbot cron add \
openclaw cron add \
--name "Send reminder" \
--at "2026-01-12T18:00:00Z" \
--session main \
@@ -186,7 +186,7 @@ moltbot cron add \
One-shot reminder (main session, wake immediately):
```bash
moltbot cron add \
openclaw cron add \
--name "Calendar check" \
--at "20m" \
--session main \
@@ -196,7 +196,7 @@ moltbot cron add \
Recurring isolated job (deliver to WhatsApp):
```bash
moltbot cron add \
openclaw cron add \
--name "Morning status" \
--cron "0 7 * * *" \
--tz "America/Los_Angeles" \
@@ -209,7 +209,7 @@ moltbot cron add \
Recurring isolated job (deliver to a Telegram topic):
```bash
moltbot cron add \
openclaw cron add \
--name "Nightly summary (topic)" \
--cron "0 22 * * *" \
--tz "America/Los_Angeles" \
@@ -222,7 +222,7 @@ moltbot cron add \
Isolated job with model and thinking override:
```bash
moltbot cron add \
openclaw cron add \
--name "Deep analysis" \
--cron "0 6 * * 1" \
--tz "America/Los_Angeles" \
@@ -237,22 +237,22 @@ moltbot cron add \
Agent selection (multi-agent setups):
```bash
# Pin a job to agent "ops" (falls back to default if that agent is missing)
moltbot cron add --name "Ops sweep" --cron "0 6 * * *" --session isolated --message "Check ops queue" --agent ops
openclaw cron add --name "Ops sweep" --cron "0 6 * * *" --session isolated --message "Check ops queue" --agent ops
# Switch or clear the agent on an existing job
moltbot cron edit <jobId> --agent ops
moltbot cron edit <jobId> --clear-agent
openclaw cron edit <jobId> --agent ops
openclaw cron edit <jobId> --clear-agent
```
```
Manual run (debug):
```bash
moltbot cron run <jobId> --force
openclaw cron run <jobId> --force
```
Edit an existing job (patch fields):
```bash
moltbot cron edit <jobId> \
openclaw cron edit <jobId> \
--message "Updated prompt" \
--model "opus" \
--thinking low
@@ -260,23 +260,23 @@ moltbot cron edit <jobId> \
Run history:
```bash
moltbot cron runs --id <jobId> --limit 50
openclaw cron runs --id <jobId> --limit 50
```
Immediate system event without creating a job:
```bash
moltbot system event --mode now --text "Next heartbeat: check battery."
openclaw system event --mode now --text "Next heartbeat: check battery."
```
## Gateway API surface
- `cron.list`, `cron.status`, `cron.add`, `cron.update`, `cron.remove`
- `cron.run` (force or due), `cron.runs`
For immediate system events without a job, use [`moltbot system event`](/cli/system).
For immediate system events without a job, use [`openclaw system event`](/cli/system).
## Troubleshooting
### “Nothing runs”
- Check cron is enabled: `cron.enabled` and `CLAWDBOT_SKIP_CRON`.
- Check cron is enabled: `cron.enabled` and `OPENCLAW_SKIP_CRON`.
- Check the Gateway is running continuously (cron runs inside the Gateway process).
- For `cron` schedules: confirm timezone (`--tz`) vs the host timezone.

14
docs/automation/cron-vs-heartbeat.md
View File

@@ -95,7 +95,7 @@ Cron jobs run at **exact times** and can run in isolated sessions without affect
### Cron example: Daily morning briefing
```bash
moltbot cron add \
openclaw cron add \
--name "Morning briefing" \
--cron "0 7 * * *" \
--tz "America/New_York" \
@@ -112,7 +112,7 @@ This runs at exactly 7:00 AM New York time, uses Opus for quality, and delivers
### Cron example: One-shot reminder
```bash
moltbot cron add \
openclaw cron add \
--name "Meeting reminder" \
--at "20m" \
--session main \
@@ -168,13 +168,13 @@ The most efficient setup uses **both**:
**Cron jobs** (precise timing):
```bash
# Daily morning briefing at 7am
moltbot cron add --name "Morning brief" --cron "0 7 * * *" --session isolated --message "..." --deliver
openclaw cron add --name "Morning brief" --cron "0 7 * * *" --session isolated --message "..." --deliver
# Weekly project review on Mondays at 9am
moltbot cron add --name "Weekly review" --cron "0 9 * * 1" --session isolated --message "..." --model opus
openclaw cron add --name "Weekly review" --cron "0 9 * * 1" --session isolated --message "..." --model opus
# One-shot reminder
moltbot cron add --name "Call back" --at "2h" --session main --system-event "Call back the client" --wake now
openclaw cron add --name "Call back" --at "2h" --session main --system-event "Call back the client" --wake now
```
@@ -226,7 +226,7 @@ Use `--session main` with `--system-event` when you want:
- No separate isolated run
```bash
moltbot cron add \
openclaw cron add \
--name "Check project" \
--every "4h" \
--session main \
@@ -243,7 +243,7 @@ Use `--session isolated` when you want:
- History that doesn't clutter main session
```bash
moltbot cron add \
openclaw cron add \
--name "Deep analysis" \
--cron "0 6 * * 0" \
--session isolated \

50
docs/automation/gmail-pubsub.md
View File

@@ -1,19 +1,19 @@
---
summary: "Gmail Pub/Sub push wired into Moltbot webhooks via gogcli"
summary: "Gmail Pub/Sub push wired into OpenClaw webhooks via gogcli"
read_when:
- Wiring Gmail inbox triggers to Moltbot
- Wiring Gmail inbox triggers to OpenClaw
- Setting up Pub/Sub push for agent wake
---
# Gmail Pub/Sub -> Moltbot
# Gmail Pub/Sub -> OpenClaw
Goal: Gmail watch -> Pub/Sub push -> `gog gmail watch serve` -> Moltbot webhook.
Goal: Gmail watch -> Pub/Sub push -> `gog gmail watch serve` -> OpenClaw webhook.
## Prereqs
- `gcloud` installed and logged in ([install guide](https://docs.cloud.google.com/sdk/docs/install-sdk)).
- `gog` (gogcli) installed and authorized for the Gmail account ([gogcli.sh](https://gogcli.sh/)).
- Moltbot hooks enabled (see [Webhooks](/automation/webhook)).
- OpenClaw hooks enabled (see [Webhooks](/automation/webhook)).
- `tailscale` logged in ([tailscale.com](https://tailscale.com/)). Supported setup uses Tailscale Funnel for the public HTTPS endpoint.
Other tunnel services can work, but are DIY/unsupported and require manual wiring.
Right now, Tailscale is what we support.
@@ -24,7 +24,7 @@ Example hook config (enable Gmail preset mapping):
{
hooks: {
enabled: true,
token: "CLAWDBOT_HOOK_TOKEN",
token: "OPENCLAW_HOOK_TOKEN",
path: "/hooks",
presets: ["gmail"]
}
@@ -38,7 +38,7 @@ that sets `deliver` + optional `channel`/`to`:
{
hooks: {
enabled: true,
token: "CLAWDBOT_HOOK_TOKEN",
token: "OPENCLAW_HOOK_TOKEN",
presets: ["gmail"],
mappings: [
{
@@ -91,19 +91,19 @@ under `hooks.transformsDir` (see [Webhooks](/automation/webhook)).
## Wizard (recommended)
Use the Moltbot helper to wire everything together (installs deps on macOS via brew):
Use the OpenClaw helper to wire everything together (installs deps on macOS via brew):
```bash
moltbot webhooks gmail setup \
--account moltbot@gmail.com
openclaw webhooks gmail setup \
--account openclaw@gmail.com
```
Defaults:
- Uses Tailscale Funnel for the public push endpoint.
- Writes `hooks.gmail` config for `moltbot webhooks gmail run`.
- Writes `hooks.gmail` config for `openclaw webhooks gmail run`.
- Enables the Gmail hook preset (`hooks.presets: ["gmail"]`).
Path note: when `tailscale.mode` is enabled, Moltbot automatically sets
Path note: when `tailscale.mode` is enabled, OpenClaw automatically sets
`hooks.gmail.serve.path` to `/` and keeps the public path at
`hooks.gmail.tailscale.path` (default `/gmail-pubsub`) because Tailscale
strips the set-path prefix before proxying.
@@ -119,14 +119,14 @@ via Homebrew; on Linux install them manually first.
Gateway auto-start (recommended):
- When `hooks.enabled=true` and `hooks.gmail.account` is set, the Gateway starts
`gog gmail watch serve` on boot and auto-renews the watch.
- Set `CLAWDBOT_SKIP_GMAIL_WATCHER=1` to opt out (useful if you run the daemon yourself).
- Set `OPENCLAW_SKIP_GMAIL_WATCHER=1` to opt out (useful if you run the daemon yourself).
- Do not run the manual daemon at the same time, or you will hit
`listen tcp 127.0.0.1:8788: bind: address already in use`.
Manual daemon (starts `gog gmail watch serve` + auto-renew):
```bash
moltbot webhooks gmail run
openclaw webhooks gmail run
```
## One-time setup
@@ -164,7 +164,7 @@ gcloud pubsub topics add-iam-policy-binding gog-gmail-watch \
```bash
gog gmail watch start \
--account moltbot@gmail.com \
--account openclaw@gmail.com \
--label INBOX \
--topic projects/<project-id>/topics/gog-gmail-watch
```
@@ -177,23 +177,23 @@ Local example (shared token auth):
```bash
gog gmail watch serve \
--account moltbot@gmail.com \
--account openclaw@gmail.com \
--bind 127.0.0.1 \
--port 8788 \
--path /gmail-pubsub \
--token <shared> \
--hook-url http://127.0.0.1:18789/hooks/gmail \
--hook-token CLAWDBOT_HOOK_TOKEN \
--hook-token OPENCLAW_HOOK_TOKEN \
--include-body \
--max-bytes 20000
```
Notes:
- `--token` protects the push endpoint (`x-gog-token` or `?token=`).
- `--hook-url` points to Moltbot `/hooks/gmail` (mapped; isolated run + summary to main).
- `--include-body` and `--max-bytes` control the body snippet sent to Moltbot.
- `--hook-url` points to OpenClaw `/hooks/gmail` (mapped; isolated run + summary to main).
- `--include-body` and `--max-bytes` control the body snippet sent to OpenClaw.
Recommended: `moltbot webhooks gmail run` wraps the same flow and auto-renews the watch.
Recommended: `openclaw webhooks gmail run` wraps the same flow and auto-renews the watch.
## Expose the handler (advanced, unsupported)
@@ -224,8 +224,8 @@ Send a message to the watched inbox:
```bash
gog gmail send \
--account moltbot@gmail.com \
--to moltbot@gmail.com \
--account openclaw@gmail.com \
--to openclaw@gmail.com \
--subject "watch test" \
--body "ping"
```
@@ -233,8 +233,8 @@ gog gmail send \
Check watch state and history:
```bash
gog gmail watch status --account moltbot@gmail.com
gog gmail history --account moltbot@gmail.com --since <historyId>
gog gmail watch status --account openclaw@gmail.com
gog gmail history --account openclaw@gmail.com --since <historyId>
```
## Troubleshooting
@@ -246,7 +246,7 @@ gog gmail history --account moltbot@gmail.com --since <historyId>
## Cleanup
```bash
gog gmail watch stop --account moltbot@gmail.com
gog gmail watch stop --account openclaw@gmail.com
gcloud pubsub subscriptions delete gog-gmail-watch-push
gcloud pubsub topics delete gog-gmail-watch
```

14
docs/automation/poll.md
View File

@@ -16,19 +16,19 @@ read_when:
```bash
# WhatsApp
moltbot message poll --target +15555550123 \
openclaw message poll --target +15555550123 \
--poll-question "Lunch today?" --poll-option "Yes" --poll-option "No" --poll-option "Maybe"
moltbot message poll --target 123456789@g.us \
openclaw message poll --target 123456789@g.us \
--poll-question "Meeting time?" --poll-option "10am" --poll-option "2pm" --poll-option "4pm" --poll-multi
# Discord
moltbot message poll --channel discord --target channel:123456789 \
openclaw message poll --channel discord --target channel:123456789 \
--poll-question "Snack?" --poll-option "Pizza" --poll-option "Sushi"
moltbot message poll --channel discord --target channel:123456789 \
openclaw message poll --channel discord --target channel:123456789 \
--poll-question "Plan?" --poll-option "A" --poll-option "B" --poll-duration-hours 48
# MS Teams
moltbot message poll --channel msteams --target conversation:19:abc@thread.tacv2 \
openclaw message poll --channel msteams --target conversation:19:abc@thread.tacv2 \
--poll-question "Lunch?" --poll-option "Pizza" --poll-option "Sushi"
```
@@ -53,11 +53,11 @@ Params:
## Channel differences
- WhatsApp: 2-12 options, `maxSelections` must be within option count, ignores `durationHours`.
- Discord: 2-10 options, `durationHours` clamped to 1-768 hours (default 24). `maxSelections > 1` enables multi-select; Discord does not support a strict selection count.
- MS Teams: Adaptive Card polls (Moltbot-managed). No native poll API; `durationHours` is ignored.
- MS Teams: Adaptive Card polls (OpenClaw-managed). No native poll API; `durationHours` is ignored.
## Agent tool (Message)
Use the `message` tool with `poll` action (`to`, `pollQuestion`, `pollOption`, optional `pollMulti`, `pollDurationHours`, `channel`).
Note: Discord has no “pick exactly N” mode; `pollMulti` maps to multi-select.
Teams polls are rendered as Adaptive Cards and require the gateway to stay online
to record votes in `~/.clawdbot/msteams-polls.json`.
to record votes in `~/.openclaw/msteams-polls.json`.

10
docs/automation/webhook.md
View File

@@ -2,7 +2,7 @@
summary: "Webhook ingress for wake and isolated agent runs"
read_when:
- Adding or changing webhook endpoints
- Wiring external systems into Moltbot
- Wiring external systems into OpenClaw
---
# Webhooks
@@ -29,7 +29,7 @@ Notes:
Every request must include the hook token. Prefer headers:
- `Authorization: Bearer <token>` (recommended)
- `x-moltbot-token: <token>`
- `x-openclaw-token: <token>`
- `?token=<token>` (deprecated; logs a warning and will be removed in a future major release)
## Endpoints
@@ -98,7 +98,7 @@ Mapping options (summary):
(`channel` defaults to `last` and falls back to WhatsApp).
- `allowUnsafeExternalContent: true` disables the external content safety wrapper for that hook
(dangerous; only for trusted internal sources).
- `moltbot webhooks gmail setup` writes `hooks.gmail` config for `moltbot webhooks gmail run`.
- `openclaw webhooks gmail setup` writes `hooks.gmail` config for `openclaw webhooks gmail run`.
See [Gmail Pub/Sub](/automation/gmail-pubsub) for the full Gmail watch flow.
## Responses
@@ -120,7 +120,7 @@ curl -X POST http://127.0.0.1:18789/hooks/wake \
```bash
curl -X POST http://127.0.0.1:18789/hooks/agent \
-H 'x-moltbot-token: SECRET' \
-H 'x-openclaw-token: SECRET' \
-H 'Content-Type: application/json' \
-d '{"message":"Summarize inbox","name":"Email","wakeMode":"next-heartbeat"}'
```
@@ -131,7 +131,7 @@ Add `model` to the agent payload (or mapping) to override the model for that run
```bash
curl -X POST http://127.0.0.1:18789/hooks/agent \
-H 'x-moltbot-token: SECRET' \
-H 'x-openclaw-token: SECRET' \
-H 'Content-Type: application/json' \
-d '{"message":"Summarize inbox","name":"Email","model":"openai/gpt-5.2-mini"}'
```

20
docs/bedrock.md
View File

@@ -1,12 +1,12 @@
---
summary: "Use Amazon Bedrock (Converse API) models with Moltbot"
summary: "Use Amazon Bedrock (Converse API) models with OpenClaw"
read_when:
- You want to use Amazon Bedrock models with Moltbot
- You want to use Amazon Bedrock models with OpenClaw
- You need AWS credential/region setup for model calls
---
# Amazon Bedrock
Moltbot can use **Amazon Bedrock** models via pi‑ai’s **Bedrock Converse**
OpenClaw can use **Amazon Bedrock** models via pi‑ai’s **Bedrock Converse**
streaming provider. Bedrock auth uses the **AWS SDK default credential chain**,
not an API key.
@@ -19,7 +19,7 @@ not an API key.
## Automatic model discovery
If AWS credentials are detected, Moltbot can automatically discover Bedrock
If AWS credentials are detected, OpenClaw can automatically discover Bedrock
models that support **streaming** and **text output**. Discovery uses
`bedrock:ListFoundationModels` and is cached (default: 1 hour).
@@ -97,9 +97,9 @@ export AWS_BEARER_TOKEN_BEDROCK="..."
## EC2 Instance Roles
When running Moltbot on an EC2 instance with an IAM role attached, the AWS SDK
When running OpenClaw on an EC2 instance with an IAM role attached, the AWS SDK
will automatically use the instance metadata service (IMDS) for authentication.
However, Moltbot's credential detection currently only checks for environment
However, OpenClaw's credential detection currently only checks for environment
variables, not IMDS credentials.
**Workaround:** Set `AWS_PROFILE=default` to signal that AWS credentials are
@@ -146,8 +146,8 @@ aws ec2 associate-iam-instance-profile \
--iam-instance-profile Name=EC2-Bedrock-Access
# 3. On the EC2 instance, enable discovery
moltbot config set models.bedrockDiscovery.enabled true
moltbot config set models.bedrockDiscovery.region us-east-1
openclaw config set models.bedrockDiscovery.enabled true
openclaw config set models.bedrockDiscovery.region us-east-1
# 4. Set the workaround env vars
echo 'export AWS_PROFILE=default' >> ~/.bashrc
@@ -155,7 +155,7 @@ echo 'export AWS_REGION=us-east-1' >> ~/.bashrc
source ~/.bashrc
# 5. Verify models are discovered
moltbot models list
openclaw models list
```
## Notes
@@ -163,7 +163,7 @@ moltbot models list
- Bedrock requires **model access** enabled in your AWS account/region.
- Automatic discovery needs the `bedrock:ListFoundationModels` permission.
- If you use profiles, set `AWS_PROFILE` on the gateway host.
- Moltbot surfaces the credential source in this order: `AWS_BEARER_TOKEN_BEDROCK`,
- OpenClaw surfaces the credential source in this order: `AWS_BEARER_TOKEN_BEDROCK`,
then `AWS_ACCESS_KEY_ID` + `AWS_SECRET_ACCESS_KEY`, then `AWS_PROFILE`, then the
default AWS SDK chain.
- Reasoning support depends on the model; check the Bedrock model card for

2
docs/brave-search.md
View File

@@ -7,7 +7,7 @@ read_when:
# Brave Search API
Moltbot uses Brave Search as the default provider for `web_search`.
OpenClaw uses Brave Search as the default provider for `web_search`.
## Get an API key

12
docs/broadcast-groups.md
View File

@@ -17,7 +17,7 @@ Broadcast Groups enable multiple agents to process and respond to the same messa
Current scope: **WhatsApp only** (web channel).
Broadcast groups are evaluated after channel allowlists and group activation rules. In WhatsApp groups, this means broadcasts happen when Moltbot would normally reply (for example: on mention, depending on your group settings).
Broadcast groups are evaluated after channel allowlists and group activation rules. In WhatsApp groups, this means broadcasts happen when OpenClaw would normally reply (for example: on mention, depending on your group settings).
## Use Cases
@@ -76,7 +76,7 @@ Add a top-level `broadcast` section (next to `bindings`). Keys are WhatsApp peer
}
```
**Result:** When Moltbot would reply in this chat, it will run all three agents.
**Result:** When OpenClaw would reply in this chat, it will run all three agents.
### Processing Strategy
@@ -179,7 +179,7 @@ In group `120363403215116621@g.us` with agents `["alfred", "baerbel"]`:
```
Session: agent:alfred:whatsapp:group:120363403215116621@g.us
History: [user message, alfred's previous responses]
Workspace: /Users/pascal/clawd-alfred/
Workspace: /Users/pascal/openclaw-alfred/
Tools: read, write, exec
```
@@ -187,7 +187,7 @@ Tools: read, write, exec
```
Session: agent:baerbel:whatsapp:group:120363403215116621@g.us
History: [user message, baerbel's previous responses]
Workspace: /Users/pascal/clawd-baerbel/
Workspace: /Users/pascal/openclaw-baerbel/
Tools: read only
```
@@ -296,7 +296,7 @@ Broadcast groups work alongside existing routing:
**Debug:**
```bash
tail -f ~/.clawdbot/logs/gateway.log | grep broadcast
tail -f ~/.openclaw/logs/gateway.log | grep broadcast
```
### Only One Agent Responding
@@ -368,7 +368,7 @@ tail -f ~/.clawdbot/logs/gateway.log | grep broadcast
### Config Schema
```typescript
interface MoltbotConfig {
interface OpenClawConfig {
broadcast?: {
strategy?: "parallel" | "sequential";
[peerId: string]: string[];

24
docs/channels/bluebubbles.md
View File

@@ -12,7 +12,7 @@ Status: bundled plugin that talks to the BlueBubbles macOS server over HTTP. **R
## Overview
- Runs on macOS via the BlueBubbles helper app ([bluebubbles.app](https://bluebubbles.app)).
- Recommended/tested: macOS Sequoia (15). macOS Tahoe (26) works; edit is currently broken on Tahoe, and group icon updates may report success but not sync.
- Moltbot talks to it through its REST API (`GET /api/v1/ping`, `POST /message/text`, `POST /chat/:id/*`).
- OpenClaw talks to it through its REST API (`GET /api/v1/ping`, `POST /message/text`, `POST /chat/:id/*`).
- Incoming messages arrive via webhooks; outgoing replies, typing indicators, read receipts, and tapbacks are REST calls.
- Attachments and stickers are ingested as inbound media (and surfaced to the agent when possible).
- Pairing/allowlist works the same way as other channels (`/start/pairing` etc) with `channels.bluebubbles.allowFrom` + pairing codes.
@@ -22,7 +22,7 @@ Status: bundled plugin that talks to the BlueBubbles macOS server over HTTP. **R
## Quick start
1. Install the BlueBubbles server on your Mac (follow the instructions at [bluebubbles.app/install](https://bluebubbles.app/install)).
2. In the BlueBubbles config, enable the web API and set a password.
3. Run `moltbot onboard` and select BlueBubbles, or configure manually:
3. Run `openclaw onboard` and select BlueBubbles, or configure manually:
```json5
{
channels: {
@@ -41,7 +41,7 @@ Status: bundled plugin that talks to the BlueBubbles macOS server over HTTP. **R
## Onboarding
BlueBubbles is available in the interactive setup wizard:
```
moltbot onboard
openclaw onboard
```
The wizard prompts for:
@@ -53,7 +53,7 @@ The wizard prompts for:
You can also add BlueBubbles via CLI:
```
moltbot channels add bluebubbles --http-url http://192.168.1.100:1234 --password <password>
openclaw channels add bluebubbles --http-url http://192.168.1.100:1234 --password <password>
```
## Access control (DMs + groups)
@@ -61,8 +61,8 @@ DMs:
- Default: `channels.bluebubbles.dmPolicy = "pairing"`.
- Unknown senders receive a pairing code; messages are ignored until approved (codes expire after 1 hour).
- Approve via:
- `moltbot pairing list bluebubbles`
- `moltbot pairing approve bluebubbles <CODE>`
- `openclaw pairing list bluebubbles`
- `openclaw pairing approve bluebubbles <CODE>`
- Pairing is the default token exchange. Details: [Pairing](/start/pairing)
Groups:
@@ -99,7 +99,7 @@ Per-group configuration:
## Typing + read receipts
- **Typing indicators**: Sent automatically before and during response generation.
- **Read receipts**: Controlled by `channels.bluebubbles.sendReadReceipts` (default: `true`).
- **Typing indicators**: Moltbot sends typing start events; BlueBubbles clears typing automatically on send or timeout (manual stop via DELETE is unreliable).
- **Typing indicators**: OpenClaw sends typing start events; BlueBubbles clears typing automatically on send or timeout (manual stop via DELETE is unreliable).
```json5
{
@@ -151,7 +151,7 @@ Available actions:
- Voice memos: set `asVoice: true` with **MP3** or **CAF** audio to send as an iMessage voice message. BlueBubbles converts MP3 → CAF when sending voice memos.
### Message IDs (short vs full)
Moltbot may surface *short* message IDs (e.g., `1`, `2`) to save tokens.
OpenClaw may surface *short* message IDs (e.g., `1`, `2`) to save tokens.
- `MessageSid` / `ReplyToId` can be short IDs.
- `MessageSidFull` / `ReplyToIdFull` contain the provider full IDs.
- Short IDs are in-memory; they can expire on restart or cache eviction.
@@ -213,7 +213,7 @@ Prefer `chat_guid` for stable routing:
- `chat_id:123`
- `chat_identifier:...`
- Direct handles: `+15555550123`, `user@example.com`
- If a direct handle does not have an existing DM chat, Moltbot will create one via `POST /api/v1/chat/new`. This requires the BlueBubbles Private API to be enabled.
- If a direct handle does not have an existing DM chat, OpenClaw will create one via `POST /api/v1/chat/new`. This requires the BlueBubbles Private API to be enabled.
## Security
- Webhook requests are authenticated by comparing `guid`/`password` query params or headers against `channels.bluebubbles.password`. Requests from `localhost` are also accepted.
@@ -223,11 +223,11 @@ Prefer `chat_guid` for stable routing:
## Troubleshooting
- If typing/read events stop working, check the BlueBubbles webhook logs and verify the gateway path matches `channels.bluebubbles.webhookPath`.
- Pairing codes expire after one hour; use `moltbot pairing list bluebubbles` and `moltbot pairing approve bluebubbles <code>`.
- Pairing codes expire after one hour; use `openclaw pairing list bluebubbles` and `openclaw pairing approve bluebubbles <code>`.
- Reactions require the BlueBubbles private API (`POST /api/v1/message/react`); ensure the server version exposes it.
- Edit/unsend require macOS 13+ and a compatible BlueBubbles server version. On macOS 26 (Tahoe), edit is currently broken due to private API changes.
- Group icon updates can be flaky on macOS 26 (Tahoe): the API may return success but the new icon does not sync.
- Moltbot auto-hides known-broken actions based on the BlueBubbles server's macOS version. If edit still appears on macOS 26 (Tahoe), disable it manually with `channels.bluebubbles.actions.edit=false`.
- For status/health info: `moltbot status --all` or `moltbot status --deep`.
- OpenClaw auto-hides known-broken actions based on the BlueBubbles server's macOS version. If edit still appears on macOS 26 (Tahoe), disable it manually with `channels.bluebubbles.actions.edit=false`.
- For status/health info: `openclaw status --all` or `openclaw status --deep`.
For general channel workflow reference, see [Channels](/channels) and the [Plugins](/plugins) guide.

30
docs/channels/discord.md
View File

@@ -11,7 +11,7 @@ Status: ready for DM and guild text channels via the official Discord bot gatewa
## Quick setup (beginner)
1) Create a Discord bot and copy the bot token.
2) In the Discord app settings, enable **Message Content Intent** (and **Server Members Intent** if you plan to use allowlists or name lookups).
3) Set the token for Moltbot:
3) Set the token for OpenClaw:
- Env: `DISCORD_BOT_TOKEN=...`
- Or config: `channels.discord.token: "..."`.
- If both are set, config takes precedence (env fallback is default-account only).
@@ -32,7 +32,7 @@ Minimal config:
```
## Goals
- Talk to Moltbot via Discord DMs or guild channels.
- Talk to OpenClaw via Discord DMs or guild channels.
- Direct chats collapse into the agent's main session (default `agent:main:main`); guild channels stay isolated as `agent:<agentId>:discord:channel:<channelId>` (display names use `discord:<guildSlug>#<channelSlug>`).
- Group DMs are ignored by default; enable via `channels.discord.dm.groupEnabled` and optionally restrict by `channels.discord.dm.groupChannels`.
- Keep routing deterministic: replies always go back to the channel they arrived on.
@@ -40,12 +40,12 @@ Minimal config:
## How it works
1. Create a Discord application → Bot, enable the intents you need (DMs + guild messages + message content), and grab the bot token.
2. Invite the bot to your server with the permissions required to read/send messages where you want to use it.
3. Configure Moltbot with `channels.discord.token` (or `DISCORD_BOT_TOKEN` as a fallback).
3. Configure OpenClaw with `channels.discord.token` (or `DISCORD_BOT_TOKEN` as a fallback).
4. Run the gateway; it auto-starts the Discord channel when a token is available (config first, env fallback) and `channels.discord.enabled` is not `false`.
- If you prefer env vars, set `DISCORD_BOT_TOKEN` (a config block is optional).
5. Direct chats: use `user:<id>` (or a `<@id>` mention) when delivering; all turns land in the shared `main` session. Bare numeric IDs are ambiguous and rejected.
6. Guild channels: use `channel:<channelId>` for delivery. Mentions are required by default and can be set per guild or per channel.
7. Direct chats: secure by default via `channels.discord.dm.policy` (default: `"pairing"`). Unknown senders get a pairing code (expires after 1 hour); approve via `moltbot pairing approve discord <code>`.
7. Direct chats: secure by default via `channels.discord.dm.policy` (default: `"pairing"`). Unknown senders get a pairing code (expires after 1 hour); approve via `openclaw pairing approve discord <code>`.
- To keep old “open to anyone” behavior: set `channels.discord.dm.policy="open"` and `channels.discord.dm.allowFrom=["*"]`.
- To hard-allowlist: set `channels.discord.dm.policy="allowlist"` and list senders in `channels.discord.dm.allowFrom`.
- To ignore all DMs: set `channels.discord.dm.enabled=false` or `channels.discord.dm.policy="disabled"`.
@@ -75,7 +75,7 @@ Disable with:
## How to create your own bot
This is the “Discord Developer Portal” setup for running Moltbot in a server (guild) channel like `#help`.
This is the “Discord Developer Portal” setup for running OpenClaw in a server (guild) channel like `#help`.
### 1) Create the Discord app + bot user
1. Discord Developer Portal → **Applications** → **New Application**
@@ -83,7 +83,7 @@ This is the “Discord Developer Portal” setup for running Moltbot in a server
- **Bot** → **Add Bot**
- Copy the **Bot Token** (this is what you put in `DISCORD_BOT_TOKEN`)
### 2) Enable the gateway intents Moltbot needs
### 2) Enable the gateway intents OpenClaw needs
Discord blocks “privileged intents” unless you explicitly enable them.
In **Bot** → **Privileged Gateway Intents**, enable:
@@ -113,7 +113,7 @@ Avoid **Administrator** unless you’re debugging and fully trust the bot.
Copy the generated URL, open it, pick your server, and install the bot.
### 4) Get the ids (guild/user/channel)
Discord uses numeric ids everywhere; Moltbot config prefers ids.
Discord uses numeric ids everywhere; OpenClaw config prefers ids.
1. Discord (desktop/web) → **User Settings** → **Advanced** → enable **Developer Mode**
2. Right-click:
@@ -121,7 +121,7 @@ Discord uses numeric ids everywhere; Moltbot config prefers ids.
- Channel (e.g. `#help`) → **Copy Channel ID**
- Your user → **Copy User ID**
### 5) Configure Moltbot
### 5) Configure OpenClaw
#### Token
Set the bot token via env var (recommended on servers):
@@ -187,7 +187,7 @@ Notes:
3. If nothing happens: check **Troubleshooting** below.
### Troubleshooting
- First: run `moltbot doctor` and `moltbot channels status --probe` (actionable warnings + quick audits).
- First: run `openclaw doctor` and `openclaw channels status --probe` (actionable warnings + quick audits).
- **“Used disallowed intents”**: enable **Message Content Intent** (and likely **Server Members Intent**) in the Developer Portal, then restart the gateway.
- **Bot connects but never replies in a guild channel**:
- Missing **Message Content Intent**, or
@@ -258,12 +258,12 @@ Outbound Discord API calls retry on rate limits (429) using Discord `retry_after
policy: "pairing", // pairing | allowlist | open | disabled
allowFrom: ["123456789012345678", "steipete"],
groupEnabled: false,
groupChannels: ["clawd-dm"]
groupChannels: ["openclaw-dm"]
},
guilds: {
"*": { requireMention: true },
"123456789012345678": {
slug: "friends-of-clawd",
slug: "friends-of-openclaw",
requireMention: false,
reactionNotifications: "own",
users: ["987654321098765432", "steipete"],
@@ -375,13 +375,13 @@ Allowlist matching notes:
- When `guilds.<id>.channels` is omitted, all channels in the allowlisted guild are allowed.
- To allow **no channels**, set `channels.discord.groupPolicy: "disabled"` (or keep an empty allowlist).
- The configure wizard accepts `Guild/Channel` names (public + private) and resolves them to IDs when possible.
- On startup, Moltbot resolves channel/user names in allowlists to IDs (when the bot can search members)
- On startup, OpenClaw resolves channel/user names in allowlists to IDs (when the bot can search members)
and logs the mapping; unresolved entries are kept as typed.
Native command notes:
- The registered commands mirror Moltbot’s chat commands.
- The registered commands mirror OpenClaw’s chat commands.
- Native commands honor the same allowlists as DMs/guild messages (`channels.discord.dm.allowFrom`, `channels.discord.guilds`, per-channel rules).
- Slash commands may still be visible in Discord UI to users who aren’t allowlisted; Moltbot enforces allowlists on execution and replies “not authorized”.
- Slash commands may still be visible in Discord UI to users who aren’t allowlisted; OpenClaw enforces allowlists on execution and replies “not authorized”.
## Tool actions
The agent can call `discord` with actions like:
@@ -401,4 +401,4 @@ Emoji can be unicode (e.g., `✅`) or custom emoji syntax like `<:party_blob:123
## Safety & ops
- Treat the bot token like a password; prefer the `DISCORD_BOT_TOKEN` env var on supervised hosts or lock down the config file permissions.
- Only grant the bot permissions it needs (typically Read/Send Messages).
- If the bot is stuck or rate limited, restart the gateway (`moltbot gateway --force`) after confirming no other processes own the Discord session.
- If the bot is stuck or rate limited, restart the gateway (`openclaw gateway --force`) after confirming no other processes own the Discord session.

32
docs/channels/googlechat.md
View File

@@ -13,7 +13,7 @@ Status: ready for DMs + spaces via Google Chat API webhooks (HTTP only).
- Enable the API if it is not already enabled.
2) Create a **Service Account**:
- Press **Create Credentials** > **Service Account**.
- Name it whatever you want (e.g., `moltbot-chat`).
- Name it whatever you want (e.g., `openclaw-chat`).
- Leave permissions blank (press **Continue**).
- Leave principals with access blank (press **Done**).
3) Create and download the **JSON Key**:
@@ -21,17 +21,17 @@ Status: ready for DMs + spaces via Google Chat API webhooks (HTTP only).
- Go to the **Keys** tab.
- Click **Add Key** > **Create new key**.
- Select **JSON** and press **Create**.
4) Store the downloaded JSON file on your gateway host (e.g., `~/.clawdbot/googlechat-service-account.json`).
4) Store the downloaded JSON file on your gateway host (e.g., `~/.openclaw/googlechat-service-account.json`).
5) Create a Google Chat app in the [Google Cloud Console Chat Configuration](https://console.cloud.google.com/apis/api/chat.googleapis.com/hangouts-chat):
- Fill in the **Application info**:
- **App name**: (e.g. `Moltbot`)
- **Avatar URL**: (e.g. `https://molt.bot/logo.png`)
- **App name**: (e.g. `OpenClaw`)
- **Avatar URL**: (e.g. `https://openclaw.ai/logo.png`)
- **Description**: (e.g. `Personal AI Assistant`)
- Enable **Interactive features**.
- Under **Functionality**, check **Join spaces and group conversations**.
- Under **Connection settings**, select **HTTP endpoint URL**.
- Under **Triggers**, select **Use a common HTTP endpoint URL for all triggers** and set it to your gateway's public URL followed by `/googlechat`.
- *Tip: Run `moltbot status` to find your gateway's public URL.*
- *Tip: Run `openclaw status` to find your gateway's public URL.*
- Under **Visibility**, check **Make this Chat app available to specific people and groups in &lt;Your Domain&gt;**.
- Enter your email address (e.g. `user@example.com`) in the text box.
- Click **Save** at the bottom.
@@ -40,7 +40,7 @@ Status: ready for DMs + spaces via Google Chat API webhooks (HTTP only).
- Look for the **App status** section (usually near the top or bottom after saving).
- Change the status to **Live - available to users**.
- Click **Save** again.
7) Configure Moltbot with the service account path + webhook audience:
7) Configure OpenClaw with the service account path + webhook audience:
- Env: `GOOGLE_CHAT_SERVICE_ACCOUNT_FILE=/path/to/service-account.json`
- Or config: `channels.googlechat.serviceAccountFile: "/path/to/service-account.json"`.
8) Set the webhook audience type + value (matches your Chat app config).
@@ -57,7 +57,7 @@ Once the gateway is running and your email is added to the visibility list:
6) Send "Hello" to trigger the assistant!
## Public URL (Webhook-only)
Google Chat webhooks require a public HTTPS endpoint. For security, **only expose the `/googlechat` path** to the internet. Keep the Moltbot dashboard and other sensitive endpoints on your private network.
Google Chat webhooks require a public HTTPS endpoint. For security, **only expose the `/googlechat` path** to the internet. Keep the OpenClaw dashboard and other sensitive endpoints on your private network.
### Option A: Tailscale Funnel (Recommended)
Use Tailscale Serve for the private dashboard and Funnel for the public webhook path. This keeps `/` private while exposing only `/googlechat`.
@@ -112,7 +112,7 @@ your-domain.com {
reverse_proxy /googlechat* localhost:18789
}
```
With this config, any request to `your-domain.com/` will be ignored or returned as 404, while `your-domain.com/googlechat` is safely routed to Moltbot.
With this config, any request to `your-domain.com/` will be ignored or returned as 404, while `your-domain.com/googlechat` is safely routed to OpenClaw.
### Option C: Cloudflare Tunnel
Configure your tunnel's ingress rules to only route the webhook path:
@@ -122,14 +122,14 @@ Configure your tunnel's ingress rules to only route the webhook path:
## How it works
1. Google Chat sends webhook POSTs to the gateway. Each request includes an `Authorization: Bearer <token>` header.
2. Moltbot verifies the token against the configured `audienceType` + `audience`:
2. OpenClaw verifies the token against the configured `audienceType` + `audience`:
- `audienceType: "app-url"` → audience is your HTTPS webhook URL.
- `audienceType: "project-number"` → audience is the Cloud project number.
3. Messages are routed by space:
- DMs use session key `agent:<agentId>:googlechat:dm:<spaceId>`.
- Spaces use session key `agent:<agentId>:googlechat:group:<spaceId>`.
4. DM access is pairing by default. Unknown senders receive a pairing code; approve with:
- `moltbot pairing approve googlechat <code>`
- `openclaw pairing approve googlechat <code>`
5. Group spaces require @-mention by default. Use `botUser` if mention detection needs the app’s user name.
## Targets
@@ -187,32 +187,32 @@ status code: 405, reason phrase: HTTP error response: HTTP/1.1 405 Method Not Al
This means the webhook handler isn't registered. Common causes:
1. **Channel not configured**: The `channels.googlechat` section is missing from your config. Verify with:
```bash
moltbot config get channels.googlechat
openclaw config get channels.googlechat
```
If it returns "Config path not found", add the configuration (see [Config highlights](#config-highlights)).
2. **Plugin not enabled**: Check plugin status:
```bash
moltbot plugins list | grep googlechat
openclaw plugins list | grep googlechat
```
If it shows "disabled", add `plugins.entries.googlechat.enabled: true` to your config.
3. **Gateway not restarted**: After adding config, restart the gateway:
```bash
moltbot gateway restart
openclaw gateway restart
```
Verify the channel is running:
```bash
moltbot channels status
openclaw channels status
# Should show: Google Chat default: enabled, configured, ...
```
### Other issues
- Check `moltbot channels status --probe` for auth errors or missing audience config.
- Check `openclaw channels status --probe` for auth errors or missing audience config.
- If no messages arrive, confirm the Chat app's webhook URL + event subscriptions.
- If mention gating blocks replies, set `botUser` to the app's user resource name and verify `requireMention`.
- Use `moltbot logs --follow` while sending a test message to see if requests reach the gateway.
- Use `openclaw logs --follow` while sending a test message to see if requests reach the gateway.
Related docs:
- [Gateway configuration](/gateway/configuration)

26
docs/channels/imessage.md
View File

@@ -13,7 +13,7 @@ Status: external CLI integration. Gateway spawns `imsg rpc` (JSON-RPC over stdio
1) Ensure Messages is signed in on this Mac.
2) Install `imsg`:
- `brew install steipete/tap/imsg`
3) Configure Moltbot with `channels.imessage.cliPath` and `channels.imessage.dbPath`.
3) Configure OpenClaw with `channels.imessage.cliPath` and `channels.imessage.dbPath`.
4) Start the gateway and approve any macOS prompts (Automation + Full Disk Access).
Minimal config:
@@ -47,7 +47,7 @@ Disable with:
## Requirements
- macOS with Messages signed in.
- Full Disk Access for Moltbot + `imsg` (Messages DB access).
- Full Disk Access for OpenClaw + `imsg` (Messages DB access).
- Automation permission when sending.
- `channels.imessage.cliPath` can point to any command that proxies stdin/stdout (for example, a wrapper script that SSHes to another Mac and runs `imsg rpc`).
@@ -60,7 +60,7 @@ If you want the bot to send from a **separate iMessage identity** (and keep your
1) Create a dedicated Apple ID (example: `my-cool-bot@icloud.com`).
- Apple may require a phone number for verification / 2FA.
2) Create a macOS user (example: `clawdshome`) and sign into it.
2) Create a macOS user (example: `openclawhome`) and sign into it.
3) Open Messages in that macOS user and sign into iMessage using the bot Apple ID.
4) Enable Remote Login (System Settings → General → Sharing → Remote Login).
5) Install `imsg`:
@@ -103,7 +103,7 @@ Example config:
For single-account setups, use flat options (`channels.imessage.cliPath`, `channels.imessage.dbPath`) instead of the `accounts` map.
### Remote/SSH variant (optional)
If you want iMessage on another Mac, set `channels.imessage.cliPath` to a wrapper that runs `imsg` on the remote macOS host over SSH. Moltbot only needs stdio.
If you want iMessage on another Mac, set `channels.imessage.cliPath` to a wrapper that runs `imsg` on the remote macOS host over SSH. OpenClaw only needs stdio.
Example wrapper:
```bash
@@ -111,7 +111,7 @@ Example wrapper:
exec ssh -T gateway-host imsg "$@"
```
**Remote attachments:** When `cliPath` points to a remote host via SSH, attachment paths in the Messages database reference files on the remote machine. Moltbot can automatically fetch these over SCP by setting `channels.imessage.remoteHost`:
**Remote attachments:** When `cliPath` points to a remote host via SSH, attachment paths in the Messages database reference files on the remote machine. OpenClaw can automatically fetch these over SCP by setting `channels.imessage.remoteHost`:
```json5
{
@@ -125,7 +125,7 @@ exec ssh -T gateway-host imsg "$@"
}
```
If `remoteHost` is not set, Moltbot attempts to auto-detect it by parsing the SSH command in your wrapper script. Explicit configuration is recommended for reliability.
If `remoteHost` is not set, OpenClaw attempts to auto-detect it by parsing the SSH command in your wrapper script. Explicit configuration is recommended for reliability.
#### Remote Mac via Tailscale (example)
If the Gateway runs on a Linux host/VM but iMessage must run on a Mac, Tailscale is the simplest bridge: the Gateway talks to the Mac over the tailnet, runs `imsg` via SSH, and SCPs attachments back.
@@ -134,7 +134,7 @@ Architecture:
```
┌──────────────────────────────┐ SSH (imsg rpc) ┌──────────────────────────┐
│ Gateway host (Linux/VM) │──────────────────────────────────▶│ Mac with Messages + imsg │
│ - moltbot gateway │ SCP (attachments) │ - Messages signed in │
│ - openclaw gateway │ SCP (attachments) │ - Messages signed in │
│ - channels.imessage.cliPath │◀──────────────────────────────────│ - Remote Login enabled │
└──────────────────────────────┘ └──────────────────────────┘
▲
@@ -149,7 +149,7 @@ Concrete config example (Tailscale hostname):
channels: {
imessage: {
enabled: true,
cliPath: "~/.clawdbot/scripts/imsg-ssh",
cliPath: "~/.openclaw/scripts/imsg-ssh",
remoteHost: "bot@mac-mini.tailnet-1234.ts.net",
includeAttachments: true,
dbPath: "/Users/bot/Library/Messages/chat.db"
@@ -158,7 +158,7 @@ Concrete config example (Tailscale hostname):
}
```
Example wrapper (`~/.clawdbot/scripts/imsg-ssh`):
Example wrapper (`~/.openclaw/scripts/imsg-ssh`):
```bash
#!/usr/bin/env bash
exec ssh -T bot@mac-mini.tailnet-1234.ts.net imsg "$@"
@@ -169,15 +169,15 @@ Notes:
- Use SSH keys so `ssh bot@mac-mini.tailnet-1234.ts.net` works without prompts.
- `remoteHost` should match the SSH target so SCP can fetch attachments.
Multi-account support: use `channels.imessage.accounts` with per-account config and optional `name`. See [`gateway/configuration`](/gateway/configuration#telegramaccounts--discordaccounts--slackaccounts--signalaccounts--imessageaccounts) for the shared pattern. Don't commit `~/.clawdbot/moltbot.json` (it often contains tokens).
Multi-account support: use `channels.imessage.accounts` with per-account config and optional `name`. See [`gateway/configuration`](/gateway/configuration#telegramaccounts--discordaccounts--slackaccounts--signalaccounts--imessageaccounts) for the shared pattern. Don't commit `~/.openclaw/openclaw.json` (it often contains tokens).
## Access control (DMs + groups)
DMs:
- Default: `channels.imessage.dmPolicy = "pairing"`.
- Unknown senders receive a pairing code; messages are ignored until approved (codes expire after 1 hour).
- Approve via:
- `moltbot pairing list imessage`
- `moltbot pairing approve imessage <CODE>`
- `openclaw pairing list imessage`
- `openclaw pairing approve imessage <CODE>`
- Pairing is the default token exchange for iMessage DMs. Details: [Pairing](/start/pairing)
Groups:
@@ -193,7 +193,7 @@ Groups:
## Group-ish threads (`is_group=false`)
Some iMessage threads can have multiple participants but still arrive with `is_group=false` depending on how Messages stores the chat identifier.
If you explicitly configure a `chat_id` under `channels.imessage.groups`, Moltbot treats that thread as a “group” for:
If you explicitly configure a `chat_id` under `channels.imessage.groups`, OpenClaw treats that thread as a “group” for:
- session isolation (separate `agent:<agentId>:imessage:group:<chat_id>` session key)
- group allowlisting / mention gating behavior

8
docs/channels/index.md
View File

@@ -1,12 +1,12 @@
---
summary: "Messaging platforms Moltbot can connect to"
summary: "Messaging platforms OpenClaw can connect to"
read_when:
- You want to choose a chat channel for Moltbot
- You want to choose a chat channel for OpenClaw
- You need a quick overview of supported messaging platforms
---
# Chat Channels
Moltbot can talk to you on any chat app you already use. Each channel connects via the Gateway.
OpenClaw can talk to you on any chat app you already use. Each channel connects via the Gateway.
Text is supported everywhere; media and reactions vary by channel.
## Supported channels
@@ -33,7 +33,7 @@ Text is supported everywhere; media and reactions vary by channel.
## Notes
- Channels can run simultaneously; configure multiple and Moltbot will route per chat.
- Channels can run simultaneously; configure multiple and OpenClaw will route per chat.
- Fastest setup is usually **Telegram** (simple bot token). WhatsApp requires QR pairing and
stores more state on disk.
- Group behavior varies by channel; see [Groups](/concepts/groups).

12
docs/channels/line.md
View File

@@ -1,14 +1,14 @@
---
summary: "LINE Messaging API plugin setup, config, and usage"
read_when:
- You want to connect Moltbot to LINE
- You want to connect OpenClaw to LINE
- You need LINE webhook + credential setup
- You want LINE-specific message options
---
# LINE (plugin)
LINE connects to Moltbot via the LINE Messaging API. The plugin runs as a webhook
LINE connects to OpenClaw via the LINE Messaging API. The plugin runs as a webhook
receiver on the gateway and uses your channel access token + channel secret for
authentication.
@@ -21,13 +21,13 @@ are not supported.
Install the LINE plugin:
```bash
moltbot plugins install @moltbot/line
openclaw plugins install @openclaw/line
```
Local checkout (when running from a git repo):
```bash
moltbot plugins install ./extensions/line
openclaw plugins install ./extensions/line
```
## Setup
@@ -106,8 +106,8 @@ Direct messages default to pairing. Unknown senders get a pairing code and their
messages are ignored until approved.
```bash
moltbot pairing list line
moltbot pairing approve line <CODE>
openclaw pairing list line
openclaw pairing approve line <CODE>
```
Allowlists and policies:

2
docs/channels/location.md
View File

@@ -7,7 +7,7 @@ read_when:
# Channel location parsing
Moltbot normalizes shared locations from chat channels into:
OpenClaw normalizes shared locations from chat channels into:
- human-readable text appended to the inbound body, and
- structured fields in the auto-reply context payload.

28
docs/channels/matrix.md
View File

@@ -5,7 +5,7 @@ read_when:
---
# Matrix (plugin)
Matrix is an open, decentralized messaging protocol. Moltbot connects as a Matrix **user**
Matrix is an open, decentralized messaging protocol. OpenClaw connects as a Matrix **user**
on any homeserver, so you need a Matrix account for the bot. Once it is logged in, you can DM
the bot directly or invite it to rooms (Matrix "groups"). Beeper is a valid client option too,
but it requires E2EE to be enabled.
@@ -20,25 +20,25 @@ Matrix ships as a plugin and is not bundled with the core install.
Install via CLI (npm registry):
```bash
moltbot plugins install @moltbot/matrix
openclaw plugins install @openclaw/matrix
```
Local checkout (when running from a git repo):
```bash
moltbot plugins install ./extensions/matrix
openclaw plugins install ./extensions/matrix
```
If you choose Matrix during configure/onboarding and a git checkout is detected,
Moltbot will offer the local install path automatically.
OpenClaw will offer the local install path automatically.
Details: [Plugins](/plugin)
## Setup
1) Install the Matrix plugin:
- From npm: `moltbot plugins install @moltbot/matrix`
- From a local checkout: `moltbot plugins install ./extensions/matrix`
- From npm: `openclaw plugins install @openclaw/matrix`
- From a local checkout: `openclaw plugins install ./extensions/matrix`
2) Create a Matrix account on a homeserver:
- Browse hosting options at [https://matrix.org/ecosystem/hosting/](https://matrix.org/ecosystem/hosting/)
- Or host it yourself.
@@ -60,8 +60,8 @@ Details: [Plugins](/plugin)
```
- Replace `matrix.example.org` with your homeserver URL.
- Or set `channels.matrix.userId` + `channels.matrix.password`: Moltbot calls the same
login endpoint, stores the access token in `~/.clawdbot/credentials/matrix/credentials.json`,
- Or set `channels.matrix.userId` + `channels.matrix.password`: OpenClaw calls the same
login endpoint, stores the access token in `~/.openclaw/credentials/matrix/credentials.json`,
and reuses it on next start.
4) Configure credentials:
- Env: `MATRIX_HOMESERVER`, `MATRIX_ACCESS_TOKEN` (or `MATRIX_USER_ID` + `MATRIX_PASSWORD`)
@@ -113,17 +113,17 @@ Enable with `channels.matrix.encryption: true`:
- If the crypto module loads, encrypted rooms are decrypted automatically.
- Outbound media is encrypted when sending to encrypted rooms.
- On first connection, Moltbot requests device verification from your other sessions.
- On first connection, OpenClaw requests device verification from your other sessions.
- Verify the device in another Matrix client (Element, etc.) to enable key sharing.
- If the crypto module cannot be loaded, E2EE is disabled and encrypted rooms will not decrypt;
Moltbot logs a warning.
OpenClaw logs a warning.
- If you see missing crypto module errors (for example, `@matrix-org/matrix-sdk-crypto-nodejs-*`),
allow build scripts for `@matrix-org/matrix-sdk-crypto-nodejs` and run
`pnpm rebuild @matrix-org/matrix-sdk-crypto-nodejs` or fetch the binary with
`node node_modules/@matrix-org/matrix-sdk-crypto-nodejs/download-lib.js`.
Crypto state is stored per account + access token in
`~/.clawdbot/matrix/accounts/<account>/<homeserver>__<user>/<token-hash>/crypto/`
`~/.openclaw/matrix/accounts/<account>/<homeserver>__<user>/<token-hash>/crypto/`
(SQLite database). Sync state lives alongside it in `bot-storage.json`.
If the access token (device) changes, a new store is created and the bot must be
re-verified for encrypted rooms.
@@ -142,8 +142,8 @@ Once verified, the bot can decrypt messages in encrypted rooms.
- Default: `channels.matrix.dm.policy = "pairing"`. Unknown senders get a pairing code.
- Approve via:
- `moltbot pairing list matrix`
- `moltbot pairing approve matrix <CODE>`
- `openclaw pairing list matrix`
- `openclaw pairing approve matrix <CODE>`
- Public DMs: `channels.matrix.dm.policy="open"` plus `channels.matrix.dm.allowFrom=["*"]`.
- `channels.matrix.dm.allowFrom` accepts user IDs or display names. The wizard resolves display names to user IDs when directory search is available.
@@ -172,7 +172,7 @@ Once verified, the bot can decrypt messages in encrypted rooms.
- `groupAllowFrom` restricts which senders can trigger the bot in rooms (optional).
- Per-room `users` allowlists can further restrict senders inside a specific room.
- The configure wizard prompts for room allowlists (room IDs, aliases, or names) and resolves names when possible.
- On startup, Moltbot resolves room/user names in allowlists to IDs and logs the mapping; unresolved entries are kept as typed.
- On startup, OpenClaw resolves room/user names in allowlists to IDs and logs the mapping; unresolved entries are kept as typed.
- Invites are auto-joined by default; control with `channels.matrix.autoJoin` and `channels.matrix.autoJoinAllowlist`.
- To allow **no rooms**, set `channels.matrix.groupPolicy: "disabled"` (or keep an empty allowlist).
- Legacy key: `channels.matrix.rooms` (same shape as `groups`).

16
docs/channels/mattermost.md
View File

@@ -1,5 +1,5 @@
---
summary: "Mattermost bot setup and Moltbot config"
summary: "Mattermost bot setup and OpenClaw config"
read_when:
- Setting up Mattermost
- Debugging Mattermost routing
@@ -16,16 +16,16 @@ Mattermost ships as a plugin and is not bundled with the core install.
Install via CLI (npm registry):
```bash
moltbot plugins install @moltbot/mattermost
openclaw plugins install @openclaw/mattermost
```
Local checkout (when running from a git repo):
```bash
moltbot plugins install ./extensions/mattermost
openclaw plugins install ./extensions/mattermost
```
If you choose Mattermost during configure/onboarding and a git checkout is detected,
Moltbot will offer the local install path automatically.
OpenClaw will offer the local install path automatically.
Details: [Plugins](/plugin)
@@ -33,7 +33,7 @@ Details: [Plugins](/plugin)
1) Install the Mattermost plugin.
2) Create a Mattermost bot account and copy the **bot token**.
3) Copy the Mattermost **base URL** (e.g., `https://chat.example.com`).
4) Configure Moltbot and start the gateway.
4) Configure OpenClaw and start the gateway.
Minimal config:
```json5
@@ -83,8 +83,8 @@ Notes:
## Access control (DMs)
- Default: `channels.mattermost.dmPolicy = "pairing"` (unknown senders get a pairing code).
- Approve via:
- `moltbot pairing list mattermost`
- `moltbot pairing approve mattermost <CODE>`
- `openclaw pairing list mattermost`
- `openclaw pairing approve mattermost <CODE>`
- Public DMs: `channels.mattermost.dmPolicy="open"` plus `channels.mattermost.allowFrom=["*"]`.
## Channels (groups)
@@ -93,7 +93,7 @@ Notes:
- Open channels: `channels.mattermost.groupPolicy="open"` (mention-gated).
## Targets for outbound delivery
Use these target formats with `moltbot message send` or cron/webhooks:
Use these target formats with `openclaw message send` or cron/webhooks:
- `channel:<id>` for a channel
- `user:<id>` for a DM

52
docs/channels/msteams.md
View File

@@ -21,23 +21,23 @@ Explainable: keeps core installs lighter and lets MS Teams dependencies update i
Install via CLI (npm registry):
```bash
moltbot plugins install @moltbot/msteams
openclaw plugins install @openclaw/msteams
```
Local checkout (when running from a git repo):
```bash
moltbot plugins install ./extensions/msteams
openclaw plugins install ./extensions/msteams
```
If you choose Teams during configure/onboarding and a git checkout is detected,
Moltbot will offer the local install path automatically.
OpenClaw will offer the local install path automatically.
Details: [Plugins](/plugin)
## Quick setup (beginner)
1) Install the Microsoft Teams plugin.
2) Create an **Azure Bot** (App ID + client secret + tenant ID).
3) Configure Moltbot with those credentials.
3) Configure OpenClaw with those credentials.
4) Expose `/api/messages` (port 3978 by default) via a public URL or tunnel.
5) Install the Teams app package and start the gateway.
@@ -58,7 +58,7 @@ Minimal config:
Note: group chats are blocked by default (`channels.msteams.groupPolicy: "allowlist"`). To allow group replies, set `channels.msteams.groupAllowFrom` (or use `groupPolicy: "open"` to allow any member, mention-gated).
## Goals
- Talk to Moltbot via Teams DMs, group chats, or channels.
- Talk to OpenClaw via Teams DMs, group chats, or channels.
- Keep routing deterministic: replies always go back to the channel they arrived on.
- Default to safe channel behavior (mentions required unless configured otherwise).
@@ -101,7 +101,7 @@ Example:
- Keys can be team IDs or names; channel keys can be conversation IDs or names.
- When `groupPolicy="allowlist"` and a teams allowlist is present, only listed teams/channels are accepted (mention‑gated).
- The configure wizard accepts `Team/Channel` entries and stores them for you.
- On startup, Moltbot resolves team/channel and user allowlist names to IDs (when Graph permissions allow)
- On startup, OpenClaw resolves team/channel and user allowlist names to IDs (when Graph permissions allow)
and logs the mapping; unresolved entries are kept as typed.
Example:
@@ -127,12 +127,12 @@ Example:
2. Create an **Azure Bot** (App ID + secret + tenant ID).
3. Build a **Teams app package** that references the bot and includes the RSC permissions below.
4. Upload/install the Teams app into a team (or personal scope for DMs).
5. Configure `msteams` in `~/.clawdbot/moltbot.json` (or env vars) and start the gateway.
5. Configure `msteams` in `~/.openclaw/openclaw.json` (or env vars) and start the gateway.
6. The gateway listens for Bot Framework webhook traffic on `/api/messages` by default.
## Azure Bot Setup (Prerequisites)
Before configuring Moltbot, you need to create an Azure Bot resource.
Before configuring OpenClaw, you need to create an Azure Bot resource.
### Step 1: Create Azure Bot
@@ -141,7 +141,7 @@ Before configuring Moltbot, you need to create an Azure Bot resource.
| Field | Value |
|-------|-------|
| **Bot handle** | Your bot name, e.g., `moltbot-msteams` (must be unique) |
| **Bot handle** | Your bot name, e.g., `openclaw-msteams` (must be unique) |
| **Subscription** | Select your Azure subscription |
| **Resource group** | Create new or use existing |
| **Pricing tier** | **Free** for dev/testing |
@@ -218,8 +218,8 @@ This is often easier than hand-editing JSON manifests.
## Setup (minimal text-only)
1. **Install the Microsoft Teams plugin**
- From npm: `moltbot plugins install @moltbot/msteams`
- From a local checkout: `moltbot plugins install ./extensions/msteams`
- From npm: `openclaw plugins install @openclaw/msteams`
- From a local checkout: `openclaw plugins install ./extensions/msteams`
2. **Bot registration**
- Create an Azure Bot (see above) and note:
@@ -235,7 +235,7 @@ This is often easier than hand-editing JSON manifests.
- Create icons: `outline.png` (32x32) and `color.png` (192x192).
- Zip all three files together: `manifest.json`, `outline.png`, `color.png`.
4. **Configure Moltbot**
4. **Configure OpenClaw**
```json
{
"msteams": {
@@ -289,14 +289,14 @@ Minimal, valid example with the required fields. Replace IDs and URLs.
"manifestVersion": "1.23",
"version": "1.0.0",
"id": "00000000-0000-0000-0000-000000000000",
"name": { "short": "Moltbot" },
"name": { "short": "OpenClaw" },
"developer": {
"name": "Your Org",
"websiteUrl": "https://example.com",
"privacyUrl": "https://example.com/privacy",
"termsOfUseUrl": "https://example.com/terms"
},
"description": { "short": "Moltbot in Teams", "full": "Moltbot in Teams" },
"description": { "short": "OpenClaw in Teams", "full": "OpenClaw in Teams" },
"icons": { "outline": "outline.png", "color": "color.png" },
"accentColor": "#5B6DEF",
"bots": [
@@ -397,7 +397,7 @@ Teams delivers messages via HTTP webhook. If processing takes too long (e.g., sl
- Teams retrying the message (causing duplicates)
- Dropped replies
Moltbot handles this by returning quickly and sending replies proactively, but very slow responses may still cause issues.
OpenClaw handles this by returning quickly and sending replies proactively, but very slow responses may still cause issues.
### Formatting
Teams markdown is more limited than Slack or Discord:
@@ -475,7 +475,7 @@ Teams recently introduced two channel UI styles over the same underlying data mo
- **Channels/groups:** Attachments live in M365 storage (SharePoint/OneDrive). The webhook payload only includes an HTML stub, not the actual file bytes. **Graph API permissions are required** to download channel attachments.
Without Graph permissions, channel messages with images will be received as text-only (the image content is not accessible to the bot).
By default, Moltbot only downloads media from Microsoft/Teams hostnames. Override with `channels.msteams.mediaAllowHosts` (use `["*"]` to allow any host).
By default, OpenClaw only downloads media from Microsoft/Teams hostnames. Override with `channels.msteams.mediaAllowHosts` (use `["*"]` to allow any host).
## Sending files in group chats
@@ -512,7 +512,7 @@ Bots don't have a personal OneDrive drive (the `/me/drive` Graph API endpoint do
# Response includes: "id": "contoso.sharepoint.com,guid1,guid2"
```
4. **Configure Moltbot:**
4. **Configure OpenClaw:**
```json5
{
channels: {
@@ -544,13 +544,13 @@ Per-user sharing is more secure as only the chat participants can access the fil
### Files stored location
Uploaded files are stored in a `/MoltbotShared/` folder in the configured SharePoint site's default document library.
Uploaded files are stored in a `/OpenClawShared/` folder in the configured SharePoint site's default document library.
## Polls (Adaptive Cards)
Moltbot sends Teams polls as Adaptive Cards (there is no native Teams poll API).
OpenClaw sends Teams polls as Adaptive Cards (there is no native Teams poll API).
- CLI: `moltbot message poll --channel msteams --target conversation:<id> ...`
- Votes are recorded by the gateway in `~/.clawdbot/msteams-polls.json`.
- CLI: `openclaw message poll --channel msteams --target conversation:<id> ...`
- Votes are recorded by the gateway in `~/.openclaw/msteams-polls.json`.
- The gateway must stay online to record votes.
- Polls do not auto-post result summaries yet (inspect the store file if needed).
@@ -575,7 +575,7 @@ The `card` parameter accepts an Adaptive Card JSON object. When `card` is provid
**CLI:**
```bash
moltbot message send --channel msteams \
openclaw message send --channel msteams \
--target "conversation:19:abc...@thread.tacv2" \
--card '{"type":"AdaptiveCard","version":"1.5","body":[{"type":"TextBlock","text":"Hello!"}]}'
```
@@ -596,16 +596,16 @@ MSTeams targets use prefixes to distinguish between users and conversations:
**CLI examples:**
```bash
# Send to a user by ID
moltbot message send --channel msteams --target "user:40a1a0ed-..." --message "Hello"
openclaw message send --channel msteams --target "user:40a1a0ed-..." --message "Hello"
# Send to a user by display name (triggers Graph API lookup)
moltbot message send --channel msteams --target "user:John Smith" --message "Hello"
openclaw message send --channel msteams --target "user:John Smith" --message "Hello"
# Send to a group chat or channel
moltbot message send --channel msteams --target "conversation:19:abc...@thread.tacv2" --message "Hello"
openclaw message send --channel msteams --target "conversation:19:abc...@thread.tacv2" --message "Hello"
# Send an Adaptive Card to a conversation
moltbot message send --channel msteams --target "conversation:19:abc...@thread.tacv2" \
openclaw message send --channel msteams --target "conversation:19:abc...@thread.tacv2" \
--card '{"type":"AdaptiveCard","version":"1.5","body":[{"type":"TextBlock","text":"Hello"}]}'
```

14
docs/channels/nextcloud-talk.md
View File

@@ -12,16 +12,16 @@ Nextcloud Talk ships as a plugin and is not bundled with the core install.
Install via CLI (npm registry):
```bash
moltbot plugins install @moltbot/nextcloud-talk
openclaw plugins install @openclaw/nextcloud-talk
```
Local checkout (when running from a git repo):
```bash
moltbot plugins install ./extensions/nextcloud-talk
openclaw plugins install ./extensions/nextcloud-talk
```
If you choose Nextcloud Talk during configure/onboarding and a git checkout is detected,
Moltbot will offer the local install path automatically.
OpenClaw will offer the local install path automatically.
Details: [Plugins](/plugin)
@@ -29,10 +29,10 @@ Details: [Plugins](/plugin)
1) Install the Nextcloud Talk plugin.
2) On your Nextcloud server, create a bot:
```bash
./occ talk:bot:install "Moltbot" "<shared-secret>" "<webhook-url>" --feature reaction
./occ talk:bot:install "OpenClaw" "<shared-secret>" "<webhook-url>" --feature reaction
```
3) Enable the bot in the target room settings.
4) Configure Moltbot:
4) Configure OpenClaw:
- Config: `channels.nextcloud-talk.baseUrl` + `channels.nextcloud-talk.botSecret`
- Or env: `NEXTCLOUD_TALK_BOT_SECRET` (default account only)
5) Restart the gateway (or finish onboarding).
@@ -60,8 +60,8 @@ Minimal config:
## Access control (DMs)
- Default: `channels.nextcloud-talk.dmPolicy = "pairing"`. Unknown senders get a pairing code.
- Approve via:
- `moltbot pairing list nextcloud-talk`
- `moltbot pairing approve nextcloud-talk <CODE>`
- `openclaw pairing list nextcloud-talk`
- `openclaw pairing approve nextcloud-talk <CODE>`
- Public DMs: `channels.nextcloud-talk.dmPolicy="open"` plus `channels.nextcloud-talk.allowFrom=["*"]`.
## Rooms (groups)

18
docs/channels/nostr.md
View File

@@ -1,20 +1,20 @@
---
summary: "Nostr DM channel via NIP-04 encrypted messages"
read_when:
- You want Moltbot to receive DMs via Nostr
- You want OpenClaw to receive DMs via Nostr
- You're setting up decentralized messaging
---
# Nostr
**Status:** Optional plugin (disabled by default).
Nostr is a decentralized protocol for social networking. This channel enables Moltbot to receive and respond to encrypted direct messages (DMs) via NIP-04.
Nostr is a decentralized protocol for social networking. This channel enables OpenClaw to receive and respond to encrypted direct messages (DMs) via NIP-04.
## Install (on demand)
### Onboarding (recommended)
- The onboarding wizard (`moltbot onboard`) and `moltbot channels add` list optional channel plugins.
- The onboarding wizard (`openclaw onboard`) and `openclaw channels add` list optional channel plugins.
- Selecting Nostr prompts you to install the plugin on demand.
Install defaults:
@@ -27,13 +27,13 @@ You can always override the choice in the prompt.
### Manual install
```bash
moltbot plugins install @moltbot/nostr
openclaw plugins install @openclaw/nostr
```
Use a local checkout (dev workflows):
```bash
moltbot plugins install --link <path-to-moltbot>/extensions/nostr
openclaw plugins install --link <path-to-openclaw>/extensions/nostr
```
Restart the Gateway after installing or enabling plugins.
@@ -91,14 +91,14 @@ Example:
"nostr": {
"privateKey": "${NOSTR_PRIVATE_KEY}",
"profile": {
"name": "moltbot",
"displayName": "Moltbot",
"name": "openclaw",
"displayName": "OpenClaw",
"about": "Personal assistant DM bot",
"picture": "https://example.com/avatar.png",
"banner": "https://example.com/banner.png",
"website": "https://example.com",
"nip05": "moltbot@example.com",
"lud16": "moltbot@example.com"
"nip05": "openclaw@example.com",
"lud16": "openclaw@example.com"
}
}
}

18
docs/channels/signal.md
View File

@@ -13,8 +13,8 @@ Status: external CLI integration. Gateway talks to `signal-cli` over HTTP JSON-R
1) Use a **separate Signal number** for the bot (recommended).
2) Install `signal-cli` (Java required).
3) Link the bot device and start the daemon:
- `signal-cli link -n "Moltbot"`
4) Configure Moltbot and start the gateway.
- `signal-cli link -n "OpenClaw"`
4) Configure OpenClaw and start the gateway.
Minimal config:
```json5
@@ -54,7 +54,7 @@ Disable with:
## Setup (fast path)
1) Install `signal-cli` (Java required).
2) Link a bot account:
- `signal-cli link -n "Moltbot"` then scan the QR in Signal.
- `signal-cli link -n "OpenClaw"` then scan the QR in Signal.
3) Configure Signal and start the gateway.
Example:
@@ -75,7 +75,7 @@ Example:
Multi-account support: use `channels.signal.accounts` with per-account config and optional `name`. See [`gateway/configuration`](/gateway/configuration#telegramaccounts--discordaccounts--slackaccounts--signalaccounts--imessageaccounts) for the shared pattern.
## External daemon mode (httpUrl)
If you want to manage `signal-cli` yourself (slow JVM cold starts, container init, or shared CPUs), run the daemon separately and point Moltbot at it:
If you want to manage `signal-cli` yourself (slow JVM cold starts, container init, or shared CPUs), run the daemon separately and point OpenClaw at it:
```json5
{
@@ -88,15 +88,15 @@ If you want to manage `signal-cli` yourself (slow JVM cold starts, container ini
}
```
This skips auto-spawn and the startup wait inside Moltbot. For slow starts when auto-spawning, set `channels.signal.startupTimeoutMs`.
This skips auto-spawn and the startup wait inside OpenClaw. For slow starts when auto-spawning, set `channels.signal.startupTimeoutMs`.
## Access control (DMs + groups)
DMs:
- Default: `channels.signal.dmPolicy = "pairing"`.
- Unknown senders receive a pairing code; messages are ignored until approved (codes expire after 1 hour).
- Approve via:
- `moltbot pairing list signal`
- `moltbot pairing approve signal <CODE>`
- `openclaw pairing list signal`
- `openclaw pairing approve signal <CODE>`
- Pairing is the default token exchange for Signal DMs. Details: [Pairing](/start/pairing)
- UUID-only senders (from `sourceUuid`) are stored as `uuid:<id>` in `channels.signal.allowFrom`.
@@ -118,8 +118,8 @@ Groups:
- Group history context uses `channels.signal.historyLimit` (or `channels.signal.accounts.*.historyLimit`), falling back to `messages.groupChat.historyLimit`. Set `0` to disable (default 50).
## Typing + read receipts
- **Typing indicators**: Moltbot sends typing signals via `signal-cli sendTyping` and refreshes them while a reply is running.
- **Read receipts**: when `channels.signal.sendReadReceipts` is true, Moltbot forwards read receipts for allowed DMs.
- **Typing indicators**: OpenClaw sends typing signals via `signal-cli sendTyping` and refreshes them while a reply is running.
- **Read receipts**: when `channels.signal.sendReadReceipts` is true, OpenClaw forwards read receipts for allowed DMs.
- Signal-cli does not expose read receipts for groups.
## Reactions (message tool)

32
docs/channels/slack.md
View File

@@ -10,7 +10,7 @@ read_when: "Setting up Slack or debugging Slack socket/HTTP mode"
### Quick setup (beginner)
1) Create a Slack app and enable **Socket Mode**.
2) Create an **App Token** (`xapp-...`) and **Bot Token** (`xoxb-...`).
3) Set tokens for Moltbot and start the gateway.
3) Set tokens for OpenClaw and start the gateway.
Minimal config:
```json5
@@ -38,14 +38,14 @@ Minimal config:
- `channel_rename`
- `pin_added`, `pin_removed`
6) Invite the bot to channels you want it to read.
7) Slash Commands → create `/clawd` if you use `channels.slack.slashCommand`. If you enable native commands, add one slash command per built-in command (same names as `/help`). Native defaults to off for Slack unless you set `channels.slack.commands.native: true` (global `commands.native` is `"auto"` which leaves Slack off).
7) Slash Commands → create `/openclaw` if you use `channels.slack.slashCommand`. If you enable native commands, add one slash command per built-in command (same names as `/help`). Native defaults to off for Slack unless you set `channels.slack.commands.native: true` (global `commands.native` is `"auto"` which leaves Slack off).
8) App Home → enable the **Messages Tab** so users can DM the bot.
Use the manifest below so scopes and events stay in sync.
Multi-account support: use `channels.slack.accounts` with per-account tokens and optional `name`. See [`gateway/configuration`](/gateway/configuration#telegramaccounts--discordaccounts--slackaccounts--signalaccounts--imessageaccounts) for the shared pattern.
### Moltbot config (minimal)
### OpenClaw config (minimal)
Set tokens via env vars (recommended):
- `SLACK_APP_TOKEN=xapp-...`
@@ -66,7 +66,7 @@ Or via config:
```
### User token (optional)
Moltbot can use a Slack user token (`xoxp-...`) for read operations (history,
OpenClaw can use a Slack user token (`xoxp-...`) for read operations (history,
pins, reactions, emoji, member info). By default this stays read-only: reads
prefer the user token when present, and writes still use the bot token unless
you explicitly opt in. Even with `userTokenReadOnly: false`, the bot token stays
@@ -109,7 +109,7 @@ Example with userTokenReadOnly explicitly set (allow user token writes):
search) prefer the user token when configured, otherwise the bot token.
- Write operations (send/edit/delete messages, add/remove reactions, pin/unpin,
file uploads) use the bot token by default. If `userTokenReadOnly: false` and
no bot token is available, Moltbot falls back to the user token.
no bot token is available, OpenClaw falls back to the user token.
### History context
- `channels.slack.historyLimit` (or `channels.slack.accounts.*.historyLimit`) controls how many recent channel/group messages are wrapped into the prompt.
@@ -130,7 +130,7 @@ HTTP mode uses the Events API + Interactivity + Slash Commands with a shared req
Example request URL:
`https://gateway-host/slack/events`
### Moltbot config (minimal)
### OpenClaw config (minimal)
```json5
{
channels: {
@@ -155,12 +155,12 @@ user scopes if you plan to configure a user token.
```json
{
"display_information": {
"name": "Moltbot",
"description": "Slack connector for Moltbot"
"name": "OpenClaw",
"description": "Slack connector for OpenClaw"
},
"features": {
"bot_user": {
"display_name": "Moltbot",
"display_name": "OpenClaw",
"always_online": false
},
"app_home": {
@@ -169,8 +169,8 @@ user scopes if you plan to configure a user token.
},
"slash_commands": [
{
"command": "/clawd",
"description": "Send a message to Moltbot",
"command": "/openclaw",
"description": "Send a message to OpenClaw",
"should_escape": false
}
]
@@ -329,7 +329,7 @@ Slack uses Socket Mode only (no HTTP webhook server). Provide both tokens:
},
"slashCommand": {
"enabled": true,
"name": "clawd",
"name": "openclaw",
"sessionPrefix": "slack:slash",
"ephemeral": true
},
@@ -353,7 +353,7 @@ ack reaction after the bot replies.
- Media uploads are capped by `channels.slack.mediaMaxMb` (default 20).
## Reply threading
By default, Moltbot replies in the main channel. Use `channels.slack.replyToMode` to control automatic threading:
By default, OpenClaw replies in the main channel. Use `channels.slack.replyToMode` to control automatic threading:
| Mode | Behavior |
| --- | --- |
@@ -439,13 +439,13 @@ For fine-grained control, use these tags in agent responses:
- DMs share the `main` session (like WhatsApp/Telegram).
- Channels map to `agent:<agentId>:slack:channel:<channelId>` sessions.
- Slash commands use `agent:<agentId>:slack:slash:<userId>` sessions (prefix configurable via `channels.slack.slashCommand.sessionPrefix`).
- If Slack doesn’t provide `channel_type`, Moltbot infers it from the channel ID prefix (`D`, `C`, `G`) and defaults to `channel` to keep session keys stable.
- If Slack doesn’t provide `channel_type`, OpenClaw infers it from the channel ID prefix (`D`, `C`, `G`) and defaults to `channel` to keep session keys stable.
- Native command registration uses `commands.native` (global default `"auto"` → Slack off) and can be overridden per-workspace with `channels.slack.commands.native`. Text commands require standalone `/...` messages and can be disabled with `commands.text: false`. Slack slash commands are managed in the Slack app and are not removed automatically. Use `commands.useAccessGroups: false` to bypass access-group checks for commands.
- Full command list + config: [Slash commands](/tools/slash-commands)
## DM security (pairing)
- Default: `channels.slack.dm.policy="pairing"` — unknown DM senders get a pairing code (expires after 1 hour).
- Approve via: `moltbot pairing approve slack <code>`.
- Approve via: `openclaw pairing approve slack <code>`.
- To allow anyone: set `channels.slack.dm.policy="open"` and `channels.slack.dm.allowFrom=["*"]`.
- `channels.slack.dm.allowFrom` accepts user IDs, @handles, or emails (resolved at startup when tokens allow). The wizard accepts usernames and resolves them to ids during setup when tokens allow.
@@ -457,7 +457,7 @@ For fine-grained control, use these tags in agent responses:
`channels.defaults.groupPolicy`, or a channel allowlist to lock it down.
- The configure wizard accepts `#channel` names and resolves them to IDs when possible
(public + private); if multiple matches exist, it prefers the active channel.
- On startup, Moltbot resolves channel/user names in allowlists to IDs (when tokens allow)
- On startup, OpenClaw resolves channel/user names in allowlists to IDs (when tokens allow)
and logs the mapping; unresolved entries are kept as typed.
- To allow **no channels**, set `channels.slack.groupPolicy: "disabled"` (or keep an empty allowlist).

46
docs/channels/telegram.md
View File

@@ -101,10 +101,10 @@ group messages, so use admin if you need full visibility.
- Outbound Telegram text uses `parse_mode: "HTML"` (Telegram’s supported tag subset).
- Markdown-ish input is rendered into **Telegram-safe HTML** (bold/italic/strike/code/links); block elements are flattened to text with newlines/bullets.
- Raw HTML from models is escaped to avoid Telegram parse errors.
- If Telegram rejects the HTML payload, Moltbot retries the same message as plain text.
- If Telegram rejects the HTML payload, OpenClaw retries the same message as plain text.
## Commands (native + custom)
Moltbot registers native commands (like `/status`, `/reset`, `/model`) with Telegram’s bot menu on startup.
OpenClaw registers native commands (like `/status`, `/reset`, `/model`) with Telegram’s bot menu on startup.
You can add custom commands to the menu via config:
```json5
@@ -128,7 +128,7 @@ You can add custom commands to the menu via config:
More help: [Channel troubleshooting](/channels/troubleshooting).
Notes:
- Custom commands are **menu entries only**; Moltbot does not implement them unless you handle them elsewhere.
- Custom commands are **menu entries only**; OpenClaw does not implement them unless you handle them elsewhere.
- Command names are normalized (leading `/` stripped, lowercased) and must match `a-z`, `0-9`, `_` (1–32 chars).
- Custom commands **cannot override native commands**. Conflicts are ignored and logged.
- If `commands.native` is disabled, only custom commands are registered (or cleared if none).
@@ -202,13 +202,13 @@ Forward any message from the group to `@userinfobot` or `@getidsbot` on Telegram
**Tip:** For your own user ID, DM the bot and it will reply with your user ID (pairing message), or use `/whoami` once commands are enabled.
**Privacy note:** `@userinfobot` is a third-party bot. If you prefer, add the bot to the group, send a message, and use `moltbot logs --follow` to read `chat.id`, or use the Bot API `getUpdates`.
**Privacy note:** `@userinfobot` is a third-party bot. If you prefer, add the bot to the group, send a message, and use `openclaw logs --follow` to read `chat.id`, or use the Bot API `getUpdates`.
## Config writes
By default, Telegram is allowed to write config updates triggered by channel events or `/config set|unset`.
This happens when:
- A group is upgraded to a supergroup and Telegram emits `migrate_to_chat_id` (chat ID changes). Moltbot can migrate `channels.telegram.groups` automatically.
- A group is upgraded to a supergroup and Telegram emits `migrate_to_chat_id` (chat ID changes). OpenClaw can migrate `channels.telegram.groups` automatically.
- You run `/config set` or `/config unset` in a Telegram chat (requires `commands.config: true`).
Disable with:
@@ -219,7 +219,7 @@ Disable with:
```
## Topics (forum supergroups)
Telegram forum topics include a `message_thread_id` per message. Moltbot:
Telegram forum topics include a `message_thread_id` per message. OpenClaw:
- Appends `:topic:<threadId>` to the Telegram group session key so each topic is isolated.
- Sends typing indicators and replies with `message_thread_id` so responses stay in the topic.
- General topic (thread id `1`) is special: message sends omit `message_thread_id` (Telegram rejects it), but typing indicators still include it.
@@ -227,7 +227,7 @@ Telegram forum topics include a `message_thread_id` per message. Moltbot:
- Topic-specific configuration is available under `channels.telegram.groups.<chatId>.topics.<threadId>` (skills, allowlists, auto-reply, system prompts, disable).
- Topic configs inherit group settings (requireMention, allowlists, skills, prompts, enabled) unless overridden per topic.
Private chats can include `message_thread_id` in some edge cases. Moltbot keeps the DM session key unchanged, but still uses the thread id for replies/draft streaming when it is present.
Private chats can include `message_thread_id` in some edge cases. OpenClaw keeps the DM session key unchanged, but still uses the thread id for replies/draft streaming when it is present.
## Inline Buttons
@@ -310,15 +310,15 @@ Use the global setting when all Telegram bots/accounts should behave the same. U
### DM access
- Default: `channels.telegram.dmPolicy = "pairing"`. Unknown senders receive a pairing code; messages are ignored until approved (codes expire after 1 hour).
- Approve via:
- `moltbot pairing list telegram`
- `moltbot pairing approve telegram <CODE>`
- `openclaw pairing list telegram`
- `openclaw pairing approve telegram <CODE>`
- Pairing is the default token exchange used for Telegram DMs. Details: [Pairing](/start/pairing)
- `channels.telegram.allowFrom` accepts numeric user IDs (recommended) or `@username` entries. It is **not** the bot username; use the human sender’s ID. The wizard accepts `@username` and resolves it to the numeric ID when possible.
#### Finding your Telegram user ID
Safer (no third-party bot):
1) Start the gateway and DM your bot.
2) Run `moltbot logs --follow` and look for `from.id`.
2) Run `openclaw logs --follow` and look for `from.id`.
Alternate (official Bot API):
1) DM your bot.
@@ -363,7 +363,7 @@ Controlled by `channels.telegram.replyToMode`:
## Audio messages (voice vs file)
Telegram distinguishes **voice notes** (round bubble) from **audio files** (metadata card).
Moltbot defaults to audio files for backward compatibility.
OpenClaw defaults to audio files for backward compatibility.
To force a voice note bubble in agent replies, include this tag anywhere in the reply:
- `[[audio_as_voice]]` — send audio as a voice note instead of a file.
@@ -385,11 +385,11 @@ For message tool sends, set `asVoice: true` with a voice-compatible audio `media
## Stickers
Moltbot supports receiving and sending Telegram stickers with intelligent caching.
OpenClaw supports receiving and sending Telegram stickers with intelligent caching.
### Receiving stickers
When a user sends a sticker, Moltbot handles it based on the sticker type:
When a user sends a sticker, OpenClaw handles it based on the sticker type:
- **Static stickers (WEBP):** Downloaded and processed through vision. The sticker appears as a `<media:sticker>` placeholder in the message content.
- **Animated stickers (TGS):** Skipped (Lottie format not supported for processing).
@@ -405,7 +405,7 @@ Template context field available when receiving stickers:
### Sticker cache
Stickers are processed through the AI's vision capabilities to generate descriptions. Since the same stickers are often sent repeatedly, Moltbot caches these descriptions to avoid redundant API calls.
Stickers are processed through the AI's vision capabilities to generate descriptions. Since the same stickers are often sent repeatedly, OpenClaw caches these descriptions to avoid redundant API calls.
**How it works:**
@@ -413,7 +413,7 @@ Stickers are processed through the AI's vision capabilities to generate descript
2. **Cache storage:** The description is saved along with the sticker's file ID, emoji, and set name.
3. **Subsequent encounters:** When the same sticker is seen again, the cached description is used directly. The image is not sent to the AI.
**Cache location:** `~/.clawdbot/telegram/sticker-cache.json`
**Cache location:** `~/.openclaw/telegram/sticker-cache.json`
**Cache entry format:**
```json
@@ -512,7 +512,7 @@ The search uses fuzzy matching across description text, emoji characters, and se
## Streaming (drafts)
Telegram can stream **draft bubbles** while the agent is generating a response.
Moltbot uses Bot API `sendMessageDraft` (not real messages) and then sends the
OpenClaw uses Bot API `sendMessageDraft` (not real messages) and then sends the
final reply as a normal message.
Requirements (Telegram Bot API 9.3+):
@@ -552,7 +552,7 @@ Outbound Telegram API calls retry on transient network/429 errors with exponenti
## Reaction notifications
**How reactions work:**
Telegram reactions arrive as **separate `message_reaction` events**, not as properties in message payloads. When a user adds a reaction, Moltbot:
Telegram reactions arrive as **separate `message_reaction` events**, not as properties in message payloads. When a user adds a reaction, OpenClaw:
1. Receives the `message_reaction` update from Telegram API
2. Converts it to a **system event** with format: `"Telegram reaction added: {emoji} by {user} on msg {id}"`
@@ -588,28 +588,28 @@ The agent sees reactions as **system notifications** in the conversation history
```
**Requirements:**
- Telegram bots must explicitly request `message_reaction` in `allowed_updates` (configured automatically by Moltbot)
- Telegram bots must explicitly request `message_reaction` in `allowed_updates` (configured automatically by OpenClaw)
- For webhook mode, reactions are included in the webhook `allowed_updates`
- For polling mode, reactions are included in the `getUpdates` `allowed_updates`
## Delivery targets (CLI/cron)
- Use a chat id (`123456789`) or a username (`@name`) as the target.
- Example: `moltbot message send --channel telegram --target 123456789 --message "hi"`.
- Example: `openclaw message send --channel telegram --target 123456789 --message "hi"`.
## Troubleshooting
**Bot doesn’t respond to non-mention messages in a group:**
- If you set `channels.telegram.groups.*.requireMention=false`, Telegram’s Bot API **privacy mode** must be disabled.
- BotFather: `/setprivacy` → **Disable** (then remove + re-add the bot to the group)
- `moltbot channels status` shows a warning when config expects unmentioned group messages.
- `moltbot channels status --probe` can additionally check membership for explicit numeric group IDs (it can’t audit wildcard `"*"` rules).
- `openclaw channels status` shows a warning when config expects unmentioned group messages.
- `openclaw channels status --probe` can additionally check membership for explicit numeric group IDs (it can’t audit wildcard `"*"` rules).
- Quick test: `/activation always` (session-only; use config for persistence)
**Bot not seeing group messages at all:**
- If `channels.telegram.groups` is set, the group must be listed or use `"*"`
- Check Privacy Settings in @BotFather → "Group Privacy" should be **OFF**
- Verify bot is actually a member (not just an admin with no read access)
- Check gateway logs: `moltbot logs --follow` (look for "skipping group message")
- Check gateway logs: `openclaw logs --follow` (look for "skipping group message")
**Bot responds to mentions but not `/activation always`:**
- The `/activation` command updates session state but doesn't persist to config
@@ -621,7 +621,7 @@ The agent sees reactions as **system notifications** in the conversation history
**Long-polling aborts immediately on Node 22+ (often with proxies/custom fetch):**
- Node 22+ is stricter about `AbortSignal` instances; foreign signals can abort `fetch` calls right away.
- Upgrade to a Moltbot build that normalizes abort signals, or run the gateway on Node 20 until you can upgrade.
- Upgrade to a OpenClaw build that normalizes abort signals, or run the gateway on Node 20 until you can upgrade.
**Bot starts, then silently stops responding (or logs `HttpError: Network request ... failed`):**
- Some hosts resolve `api.telegram.org` to IPv6 first. If your server does not have working IPv6 egress, grammY can get stuck on IPv6-only requests.

10
docs/channels/tlon.md
View File

@@ -5,7 +5,7 @@ read_when:
---
# Tlon (plugin)
Tlon is a decentralized messenger built on Urbit. Moltbot connects to your Urbit ship and can
Tlon is a decentralized messenger built on Urbit. OpenClaw connects to your Urbit ship and can
respond to DMs and group chat messages. Group replies require an @ mention by default and can
be further restricted via allowlists.
@@ -19,13 +19,13 @@ Tlon ships as a plugin and is not bundled with the core install.
Install via CLI (npm registry):
```bash
moltbot plugins install @moltbot/tlon
openclaw plugins install @openclaw/tlon
```
Local checkout (when running from a git repo):
```bash
moltbot plugins install ./extensions/tlon
openclaw plugins install ./extensions/tlon
```
Details: [Plugins](/plugin)
@@ -121,7 +121,7 @@ Group authorization (restricted by default):
## Delivery targets (CLI/cron)
Use these with `moltbot message send` or cron delivery:
Use these with `openclaw message send` or cron delivery:
- DM: `~sampel-palnet` or `dm/~sampel-palnet`
- Group: `chat/~host-ship/channel` or `group:~host-ship/channel`
@@ -129,5 +129,5 @@ Use these with `moltbot message send` or cron delivery:
## Notes
- Group replies require a mention (e.g. `~your-bot-ship`) to respond.
- Thread replies: if the inbound message is in a thread, Moltbot replies in-thread.
- Thread replies: if the inbound message is in a thread, OpenClaw replies in-thread.
- Media: `sendMedia` falls back to text + URL (no native upload).

4
docs/channels/troubleshooting.md
View File

@@ -9,8 +9,8 @@ read_when:
Start with:
```bash
moltbot doctor
moltbot channels status --probe
openclaw doctor
openclaw channels status --probe
```
`channels status --probe` prints warnings when it can detect common channel misconfigurations, and includes small live checks (credentials, some permissions/membership).

28
docs/channels/twitch.md
View File

@@ -1,11 +1,11 @@
---
summary: "Twitch chat bot configuration and setup"
read_when:
- Setting up Twitch chat integration for Moltbot
- Setting up Twitch chat integration for OpenClaw
---
# Twitch (plugin)
Twitch chat support via IRC connection. Moltbot connects as a Twitch user (bot account) to receive and send messages in channels.
Twitch chat support via IRC connection. OpenClaw connects as a Twitch user (bot account) to receive and send messages in channels.
## Plugin required
@@ -14,13 +14,13 @@ Twitch ships as a plugin and is not bundled with the core install.
Install via CLI (npm registry):
```bash
moltbot plugins install @moltbot/twitch
openclaw plugins install @openclaw/twitch
```
Local checkout (when running from a git repo):
```bash
moltbot plugins install ./extensions/twitch
openclaw plugins install ./extensions/twitch
```
Details: [Plugins](/plugin)
@@ -34,7 +34,7 @@ Details: [Plugins](/plugin)
- Copy the **Client ID** and **Access Token**
3) Find your Twitch user ID: https://www.streamweasels.com/tools/convert-twitch-username-to-user-id/
4) Configure the token:
- Env: `CLAWDBOT_TWITCH_ACCESS_TOKEN=...` (default account only)
- Env: `OPENCLAW_TWITCH_ACCESS_TOKEN=...` (default account only)
- Or config: `channels.twitch.accessToken`
- If both are set, config takes precedence (env fallback is default-account only).
5) Start the gateway.
@@ -48,8 +48,8 @@ Minimal config:
channels: {
twitch: {
enabled: true,
username: "moltbot", // Bot's Twitch account
accessToken: "oauth:abc123...", // OAuth Access Token (or use CLAWDBOT_TWITCH_ACCESS_TOKEN env var)
username: "openclaw", // Bot's Twitch account
accessToken: "oauth:abc123...", // OAuth Access Token (or use OPENCLAW_TWITCH_ACCESS_TOKEN env var)
clientId: "xyz789...", // Client ID from Token Generator
channel: "vevisk", // Which Twitch channel's chat to join (required)
allowFrom: ["123456789"] // (recommended) Your Twitch user ID only - get it from https://www.streamweasels.com/tools/convert-twitch-username-to-user-id/
@@ -80,7 +80,7 @@ No manual app registration needed. Tokens expire after several hours.
**Env var (default account only):**
```bash
CLAWDBOT_TWITCH_ACCESS_TOKEN=oauth:abc123...
OPENCLAW_TWITCH_ACCESS_TOKEN=oauth:abc123...
```
**Or config:**
@@ -89,7 +89,7 @@ CLAWDBOT_TWITCH_ACCESS_TOKEN=oauth:abc123...
channels: {
twitch: {
enabled: true,
username: "moltbot",
username: "openclaw",
accessToken: "oauth:abc123...",
clientId: "xyz789...",
channel: "vevisk"
@@ -150,13 +150,13 @@ Example (one bot account in two channels):
twitch: {
accounts: {
channel1: {
username: "moltbot",
username: "openclaw",
accessToken: "oauth:abc123...",
clientId: "xyz789...",
channel: "vevisk"
},
channel2: {
username: "moltbot",
username: "openclaw",
accessToken: "oauth:def456...",
clientId: "uvw012...",
channel: "secondchannel"
@@ -245,8 +245,8 @@ By default, `requireMention` is `true`. To disable and respond to all messages:
First, run diagnostic commands:
```bash
moltbot doctor
moltbot channels status --probe
openclaw doctor
openclaw channels status --probe
```
### Bot doesn't respond to messages
@@ -305,7 +305,7 @@ Full example:
channels: {
twitch: {
enabled: true,
username: "moltbot",
username: "openclaw",
accessToken: "oauth:abc123...",
clientId: "xyz789...",
channel: "vevisk",

50
docs/channels/whatsapp.md
View File

@@ -10,8 +10,8 @@ Status: WhatsApp Web via Baileys only. Gateway owns the session(s).
## Quick setup (beginner)
1) Use a **separate phone number** if possible (recommended).
2) Configure WhatsApp in `~/.clawdbot/moltbot.json`.
3) Run `moltbot channels login` to scan the QR code (Linked Devices).
2) Configure WhatsApp in `~/.openclaw/openclaw.json`.
3) Run `openclaw channels login` to scan the QR code (Linked Devices).
4) Start the gateway.
Minimal config:
@@ -48,12 +48,12 @@ Disable with:
## Getting a phone number (two modes)
WhatsApp requires a real mobile number for verification. VoIP and virtual numbers are usually blocked. There are two supported ways to run Moltbot on WhatsApp:
WhatsApp requires a real mobile number for verification. VoIP and virtual numbers are usually blocked. There are two supported ways to run OpenClaw on WhatsApp:
### Dedicated number (recommended)
Use a **separate phone number** for Moltbot. Best UX, clean routing, no self-chat quirks. Ideal setup: **spare/old Android phone + eSIM**. Leave it on Wi‑Fi and power, and link it via QR.
Use a **separate phone number** for OpenClaw. Best UX, clean routing, no self-chat quirks. Ideal setup: **spare/old Android phone + eSIM**. Leave it on Wi‑Fi and power, and link it via QR.
**WhatsApp Business:** You can use WhatsApp Business on the same device with a different number. Great for keeping your personal WhatsApp separate — install WhatsApp Business and register the Moltbot number there.
**WhatsApp Business:** You can use WhatsApp Business on the same device with a different number. Great for keeping your personal WhatsApp separate — install WhatsApp Business and register the OpenClaw number there.
**Sample config (dedicated number, single-user allowlist):**
```json5
@@ -69,10 +69,10 @@ Use a **separate phone number** for Moltbot. Best UX, clean routing, no self-cha
**Pairing mode (optional):**
If you want pairing instead of allowlist, set `channels.whatsapp.dmPolicy` to `pairing`. Unknown senders get a pairing code; approve with:
`moltbot pairing approve whatsapp <code>`
`openclaw pairing approve whatsapp <code>`
### Personal number (fallback)
Quick fallback: run Moltbot on **your own number**. Message yourself (WhatsApp “Message yourself”) for testing so you don’t spam contacts. Expect to read verification codes on your main phone during setup and experiments. **Must enable self-chat mode.**
Quick fallback: run OpenClaw on **your own number**. Message yourself (WhatsApp “Message yourself”) for testing so you don’t spam contacts. Expect to read verification codes on your main phone during setup and experiments. **Must enable self-chat mode.**
When the wizard asks for your personal WhatsApp number, enter the phone you will message from (the owner/sender), not the assistant number.
**Sample config (personal number, self-chat):**
@@ -86,7 +86,7 @@ When the wizard asks for your personal WhatsApp number, enter the phone you will
}
```
Self-chat replies default to `[{identity.name}]` when set (otherwise `[moltbot]`)
Self-chat replies default to `[{identity.name}]` when set (otherwise `[openclaw]`)
if `messages.responsePrefix` is unset. Set it explicitly to customize or disable
the prefix (use `""` to remove it).
@@ -101,20 +101,20 @@ the prefix (use `""` to remove it).
**Tip:** The number only needs to receive one verification SMS. After that, WhatsApp Web sessions persist via `creds.json`.
## Why Not Twilio?
- Early Moltbot builds supported Twilio’s WhatsApp Business integration.
- Early OpenClaw builds supported Twilio’s WhatsApp Business integration.
- WhatsApp Business numbers are a poor fit for a personal assistant.
- Meta enforces a 24‑hour reply window; if you haven’t responded in the last 24 hours, the business number can’t initiate new messages.
- High-volume or “chatty” usage triggers aggressive blocking, because business accounts aren’t meant to send dozens of personal assistant messages.
- Result: unreliable delivery and frequent blocks, so support was removed.
## Login + credentials
- Login command: `moltbot channels login` (QR via Linked Devices).
- Multi-account login: `moltbot channels login --account <id>` (`<id>` = `accountId`).
- Login command: `openclaw channels login` (QR via Linked Devices).
- Multi-account login: `openclaw channels login --account <id>` (`<id>` = `accountId`).
- Default account (when `--account` is omitted): `default` if present, otherwise the first configured account id (sorted).
- Credentials stored in `~/.clawdbot/credentials/whatsapp/<accountId>/creds.json`.
- Credentials stored in `~/.openclaw/credentials/whatsapp/<accountId>/creds.json`.
- Backup copy at `creds.json.bak` (restored on corruption).
- Legacy compatibility: older installs stored Baileys files directly in `~/.clawdbot/credentials/`.
- Logout: `moltbot channels logout` (or `--account <id>`) deletes WhatsApp auth state (but keeps shared `oauth.json`).
- Legacy compatibility: older installs stored Baileys files directly in `~/.openclaw/credentials/`.
- Logout: `openclaw channels logout` (or `--account <id>`) deletes WhatsApp auth state (but keeps shared `oauth.json`).
- Logged-out socket => error instructs re-link.
## Inbound flow (DM + group)
@@ -123,12 +123,12 @@ the prefix (use `""` to remove it).
- Status/broadcast chats are ignored.
- Direct chats use E.164; groups use group JID.
- **DM policy**: `channels.whatsapp.dmPolicy` controls direct chat access (default: `pairing`).
- Pairing: unknown senders get a pairing code (approve via `moltbot pairing approve whatsapp <code>`; codes expire after 1 hour).
- Pairing: unknown senders get a pairing code (approve via `openclaw pairing approve whatsapp <code>`; codes expire after 1 hour).
- Open: requires `channels.whatsapp.allowFrom` to include `"*"`.
- Your linked WhatsApp number is implicitly trusted, so self messages skip ⁠`channels.whatsapp.dmPolicy` and `channels.whatsapp.allowFrom` checks.
### Personal-number mode (fallback)
If you run Moltbot on your **personal WhatsApp number**, enable `channels.whatsapp.selfChatMode` (see sample above).
If you run OpenClaw on your **personal WhatsApp number**, enable `channels.whatsapp.selfChatMode` (see sample above).
Behavior:
- Outbound DMs never trigger pairing replies (prevents spamming contacts).
@@ -164,16 +164,16 @@ Notes:
## WhatsApp FAQ: sending messages + pairing
**Will Moltbot message random contacts when I link WhatsApp?**
No. Default DM policy is **pairing**, so unknown senders only get a pairing code and their message is **not processed**. Moltbot only replies to chats it receives, or to sends you explicitly trigger (agent/CLI).
**Will OpenClaw message random contacts when I link WhatsApp?**
No. Default DM policy is **pairing**, so unknown senders only get a pairing code and their message is **not processed**. OpenClaw only replies to chats it receives, or to sends you explicitly trigger (agent/CLI).
**How does pairing work on WhatsApp?**
Pairing is a DM gate for unknown senders:
- First DM from a new sender returns a short code (message is not processed).
- Approve with: `moltbot pairing approve whatsapp <code>` (list with `moltbot pairing list whatsapp`).
- Approve with: `openclaw pairing approve whatsapp <code>` (list with `openclaw pairing list whatsapp`).
- Codes expire after 1 hour; pending requests are capped at 3 per channel.
**Can multiple people use different Moltbots on one WhatsApp number?**
**Can multiple people use different OpenClaw instances on one WhatsApp number?**
Yes, by routing each sender to a different agent via `bindings` (peer `kind: "dm"`, sender E.164 like `+15551234567`). Replies still come from the **same WhatsApp account**, and direct chats collapse to each agent’s main session, so use **one agent per person**. DM access control (`dmPolicy`/`allowFrom`) is global per WhatsApp account. See [Multi-Agent Routing](/concepts/multi-agent).
**Why do you ask for my phone number in the wizard?**
@@ -284,12 +284,12 @@ WhatsApp can automatically send emoji reactions to incoming messages immediately
- Caption only on first media item.
- Media fetch supports HTTP(S) and local paths.
- Animated GIFs: WhatsApp expects MP4 with `gifPlayback: true` for inline looping.
- CLI: `moltbot message send --media <mp4> --gif-playback`
- CLI: `openclaw message send --media <mp4> --gif-playback`
- Gateway: `send` params include `gifPlayback: true`
## Voice notes (PTT audio)
WhatsApp sends audio as **voice notes** (PTT bubble).
- Best results: OGG/Opus. Moltbot rewrites `audio/ogg` to `audio/ogg; codecs=opus`.
- Best results: OGG/Opus. OpenClaw rewrites `audio/ogg` to `audio/ogg; codecs=opus`.
- `[[audio_as_voice]]` is ignored for WhatsApp (audio already ships as voice note).
## Media limits + optimization
@@ -344,18 +344,18 @@ WhatsApp sends audio as **voice notes** (PTT bubble).
## Logs + troubleshooting
- Subsystems: `whatsapp/inbound`, `whatsapp/outbound`, `web-heartbeat`, `web-reconnect`.
- Log file: `/tmp/moltbot/moltbot-YYYY-MM-DD.log` (configurable).
- Log file: `/tmp/openclaw/openclaw-YYYY-MM-DD.log` (configurable).
- Troubleshooting guide: [Gateway troubleshooting](/gateway/troubleshooting).
## Troubleshooting (quick)
**Not linked / QR login required**
- Symptom: `channels status` shows `linked: false` or warns “Not linked”.
- Fix: run `moltbot channels login` on the gateway host and scan the QR (WhatsApp → Settings → Linked Devices).
- Fix: run `openclaw channels login` on the gateway host and scan the QR (WhatsApp → Settings → Linked Devices).
**Linked but disconnected / reconnect loop**
- Symptom: `channels status` shows `running, disconnected` or warns “Linked but disconnected”.
- Fix: `moltbot doctor` (or restart the gateway). If it persists, relink via `channels login` and inspect `moltbot logs --follow`.
- Fix: `openclaw doctor` (or restart the gateway). If it persists, relink via `channels login` and inspect `openclaw logs --follow`.
**Bun runtime**
- Bun is **not recommended**. WhatsApp (Baileys) and Telegram are unreliable on Bun.

16
docs/channels/zalo.md
View File

@@ -9,14 +9,14 @@ Status: experimental. Direct messages only; groups coming soon per Zalo docs.
## Plugin required
Zalo ships as a plugin and is not bundled with the core install.
- Install via CLI: `moltbot plugins install @moltbot/zalo`
- Install via CLI: `openclaw plugins install @openclaw/zalo`
- Or select **Zalo** during onboarding and confirm the install prompt
- Details: [Plugins](/plugin)
## Quick setup (beginner)
1) Install the Zalo plugin:
- From a source checkout: `moltbot plugins install ./extensions/zalo`
- From npm (if published): `moltbot plugins install @moltbot/zalo`
- From a source checkout: `openclaw plugins install ./extensions/zalo`
- From npm (if published): `openclaw plugins install @openclaw/zalo`
- Or pick **Zalo** in onboarding and confirm the install prompt
2) Set the token:
- Env: `ZALO_BOT_TOKEN=...`
@@ -89,8 +89,8 @@ Multi-account support: use `channels.zalo.accounts` with per-account tokens and
### DM access
- Default: `channels.zalo.dmPolicy = "pairing"`. Unknown senders receive a pairing code; messages are ignored until approved (codes expire after 1 hour).
- Approve via:
- `moltbot pairing list zalo`
- `moltbot pairing approve zalo <CODE>`
- `openclaw pairing list zalo`
- `openclaw pairing approve zalo <CODE>`
- Pairing is the default token exchange. Details: [Pairing](/start/pairing)
- `channels.zalo.allowFrom` accepts numeric user IDs (no username lookup available).
@@ -124,14 +124,14 @@ Multi-account support: use `channels.zalo.accounts` with per-account tokens and
## Delivery targets (CLI/cron)
- Use a chat id as the target.
- Example: `moltbot message send --channel zalo --target 123456789 --message "hi"`.
- Example: `openclaw message send --channel zalo --target 123456789 --message "hi"`.
## Troubleshooting
**Bot doesn't respond:**
- Check that the token is valid: `moltbot channels status --probe`
- Check that the token is valid: `openclaw channels status --probe`
- Verify the sender is approved (pairing or allowFrom)
- Check gateway logs: `moltbot logs --follow`
- Check gateway logs: `openclaw logs --follow`
**Webhook not receiving events:**
- Ensure webhook URL uses HTTPS

24
docs/channels/zalouser.md
View File

@@ -1,7 +1,7 @@
---
summary: "Zalo personal account support via zca-cli (QR login), capabilities, and configuration"
read_when:
- Setting up Zalo Personal for Moltbot
- Setting up Zalo Personal for OpenClaw
- Debugging Zalo Personal login or message flow
---
# Zalo Personal (unofficial)
@@ -12,8 +12,8 @@ Status: experimental. This integration automates a **personal Zalo account** via
## Plugin required
Zalo Personal ships as a plugin and is not bundled with the core install.
- Install via CLI: `moltbot plugins install @moltbot/zalouser`
- Or from a source checkout: `moltbot plugins install ./extensions/zalouser`
- Install via CLI: `openclaw plugins install @openclaw/zalouser`
- Or from a source checkout: `openclaw plugins install ./extensions/zalouser`
- Details: [Plugins](/plugin)
## Prerequisite: zca-cli
@@ -25,7 +25,7 @@ The Gateway machine must have the `zca` binary available in `PATH`.
## Quick setup (beginner)
1) Install the plugin (see above).
2) Login (QR, on the Gateway machine):
- `moltbot channels login --channel zalouser`
- `openclaw channels login --channel zalouser`
- Scan the QR code in the terminal with the Zalo mobile app.
3) Enable the channel:
@@ -55,9 +55,9 @@ Channel id is `zalouser` to make it explicit this automates a **personal Zalo us
Use the directory CLI to discover peers/groups and their IDs:
```bash
moltbot directory self --channel zalouser
moltbot directory peers list --channel zalouser --query "name"
moltbot directory groups list --channel zalouser --query "work"
openclaw directory self --channel zalouser
openclaw directory peers list --channel zalouser --query "name"
openclaw directory groups list --channel zalouser --query "work"
```
## Limits
@@ -69,8 +69,8 @@ moltbot directory groups list --channel zalouser --query "work"
`channels.zalouser.allowFrom` accepts user IDs or names. The wizard resolves names to IDs via `zca friend find` when available.
Approve via:
- `moltbot pairing list zalouser`
- `moltbot pairing approve zalouser <code>`
- `openclaw pairing list zalouser`
- `openclaw pairing approve zalouser <code>`
## Group access (optional)
- Default: `channels.zalouser.groupPolicy = "open"` (groups allowed). Use `channels.defaults.groupPolicy` to override the default when unset.
@@ -79,7 +79,7 @@ Approve via:
- `channels.zalouser.groups` (keys are group IDs or names)
- Block all groups: `channels.zalouser.groupPolicy = "disabled"`.
- The configure wizard can prompt for group allowlists.
- On startup, Moltbot resolves group/user names in allowlists to IDs and logs the mapping; unresolved entries are kept as typed.
- On startup, OpenClaw resolves group/user names in allowlists to IDs and logs the mapping; unresolved entries are kept as typed.
Example:
```json5
@@ -119,5 +119,5 @@ Accounts map to zca profiles. Example:
- Install zca-cli and ensure it’s on `PATH` for the Gateway process.
**Login doesn’t stick:**
- `moltbot channels status --probe`
- Re-login: `moltbot channels logout --channel zalouser && moltbot channels login --channel zalouser`
- `openclaw channels status --probe`
- Re-login: `openclaw channels logout --channel zalouser && openclaw channels login --channel zalouser`

48
docs/cli/acp.md
View File

@@ -7,7 +7,7 @@ read_when:
# acp
Run the ACP (Agent Client Protocol) bridge that talks to a Moltbot Gateway.
Run the ACP (Agent Client Protocol) bridge that talks to a OpenClaw Gateway.
This command speaks ACP over stdio for IDEs and forwards prompts to the Gateway
over WebSocket. It keeps ACP sessions mapped to Gateway session keys.
@@ -15,19 +15,19 @@ over WebSocket. It keeps ACP sessions mapped to Gateway session keys.
## Usage
```bash
moltbot acp
openclaw acp
# Remote Gateway
moltbot acp --url wss://gateway-host:18789 --token <token>
openclaw acp --url wss://gateway-host:18789 --token <token>
# Attach to an existing session key
moltbot acp --session agent:main:main
openclaw acp --session agent:main:main
# Attach by label (must already exist)
moltbot acp --session-label "support inbox"
openclaw acp --session-label "support inbox"
# Reset the session key before the first prompt
moltbot acp --session agent:main:main --reset-session
openclaw acp --session agent:main:main --reset-session
```
## ACP client (debug)
@@ -36,35 +36,35 @@ Use the built-in ACP client to sanity-check the bridge without an IDE.
It spawns the ACP bridge and lets you type prompts interactively.
```bash
moltbot acp client
openclaw acp client
# Point the spawned bridge at a remote Gateway
moltbot acp client --server-args --url wss://gateway-host:18789 --token <token>
openclaw acp client --server-args --url wss://gateway-host:18789 --token <token>
# Override the server command (default: moltbot)
moltbot acp client --server "node" --server-args moltbot.mjs acp --url ws://127.0.0.1:19001
# Override the server command (default: openclaw)
openclaw acp client --server "node" --server-args openclaw.mjs acp --url ws://127.0.0.1:19001
```
## How to use this
Use ACP when an IDE (or other client) speaks Agent Client Protocol and you want
it to drive a Moltbot Gateway session.
it to drive a OpenClaw Gateway session.
1. Ensure the Gateway is running (local or remote).
2. Configure the Gateway target (config or flags).
3. Point your IDE to run `moltbot acp` over stdio.
3. Point your IDE to run `openclaw acp` over stdio.
Example config (persisted):
```bash
moltbot config set gateway.remote.url wss://gateway-host:18789
moltbot config set gateway.remote.token <token>
openclaw config set gateway.remote.url wss://gateway-host:18789
openclaw config set gateway.remote.token <token>
```
Example direct run (no config write):
```bash
moltbot acp --url wss://gateway-host:18789 --token <token>
openclaw acp --url wss://gateway-host:18789 --token <token>
```
## Selecting agents
@@ -74,9 +74,9 @@ ACP does not pick agents directly. It routes by the Gateway session key.
Use agent-scoped session keys to target a specific agent:
```bash
moltbot acp --session agent:main:main
moltbot acp --session agent:design:main
moltbot acp --session agent:qa:bug-123
openclaw acp --session agent:main:main
openclaw acp --session agent:design:main
openclaw acp --session agent:qa:bug-123
```
Each ACP session maps to a single Gateway session key. One agent can have many
@@ -90,9 +90,9 @@ Add a custom ACP agent in `~/.config/zed/settings.json` (or use Zed’s Settings
```json
{
"agent_servers": {
"Moltbot ACP": {
"OpenClaw ACP": {
"type": "custom",
"command": "moltbot",
"command": "openclaw",
"args": ["acp"],
"env": {}
}
@@ -105,9 +105,9 @@ To target a specific Gateway or agent:
```json
{
"agent_servers": {
"Moltbot ACP": {
"OpenClaw ACP": {
"type": "custom",
"command": "moltbot",
"command": "openclaw",
"args": [
"acp",
"--url", "wss://gateway-host:18789",
@@ -120,7 +120,7 @@ To target a specific Gateway or agent:
}
```
In Zed, open the Agent panel and select “Moltbot ACP” to start a thread.
In Zed, open the Agent panel and select “OpenClaw ACP” to start a thread.
## Session mapping
@@ -160,7 +160,7 @@ Learn more about session keys at [/concepts/session](/concepts/session).
### `acp client` options
- `--cwd <dir>`: working directory for the ACP session.
- `--server <command>`: ACP server command (default: `moltbot`).
- `--server <command>`: ACP server command (default: `openclaw`).
- `--server-args <args...>`: extra arguments passed to the ACP server.
- `--server-verbose`: enable verbose logging on the ACP server.
- `--verbose, -v`: verbose client logging.

12
docs/cli/agent.md
View File

@@ -1,10 +1,10 @@
---
summary: "CLI reference for `moltbot agent` (send one agent turn via the Gateway)"
summary: "CLI reference for `openclaw agent` (send one agent turn via the Gateway)"
read_when:
- You want to run one agent turn from scripts (optionally deliver reply)
---
# `moltbot agent`
# `openclaw agent`
Run an agent turn via the Gateway (use `--local` for embedded).
Use `--agent <id>` to target a configured agent directly.
@@ -15,8 +15,8 @@ Related:
## Examples
```bash
moltbot agent --to +15555550123 --message "status update" --deliver
moltbot agent --agent ops --message "Summarize logs"
moltbot agent --session-id 1234 --message "Summarize inbox" --thinking medium
moltbot agent --agent ops --message "Generate report" --deliver --reply-channel slack --reply-to "#reports"
openclaw agent --to +15555550123 --message "status update" --deliver
openclaw agent --agent ops --message "Summarize logs"
openclaw agent --session-id 1234 --message "Summarize inbox" --thinking medium
openclaw agent --agent ops --message "Generate report" --deliver --reply-channel slack --reply-to "#reports"
```

24
docs/cli/agents.md
View File

@@ -1,10 +1,10 @@
---
summary: "CLI reference for `moltbot agents` (list/add/delete/set identity)"
summary: "CLI reference for `openclaw agents` (list/add/delete/set identity)"
read_when:
- You want multiple isolated agents (workspaces + routing + auth)
---
# `moltbot agents`
# `openclaw agents`
Manage isolated agents (workspaces + auth + routing).
@@ -15,17 +15,17 @@ Related:
## Examples
```bash
moltbot agents list
moltbot agents add work --workspace ~/clawd-work
moltbot agents set-identity --workspace ~/clawd --from-identity
moltbot agents set-identity --agent main --avatar avatars/clawd.png
moltbot agents delete work
openclaw agents list
openclaw agents add work --workspace ~/.openclaw/workspace-work
openclaw agents set-identity --workspace ~/.openclaw/workspace --from-identity
openclaw agents set-identity --agent main --avatar avatars/openclaw.png
openclaw agents delete work
```
## Identity files
Each agent workspace can include an `IDENTITY.md` at the workspace root:
- Example path: `~/clawd/IDENTITY.md`
- Example path: `~/.openclaw/workspace/IDENTITY.md`
- `set-identity --from-identity` reads from the workspace root (or an explicit `--identity-file`)
Avatar paths resolve relative to the workspace root.
@@ -41,13 +41,13 @@ Avatar paths resolve relative to the workspace root.
Load from `IDENTITY.md`:
```bash
moltbot agents set-identity --workspace ~/clawd --from-identity
openclaw agents set-identity --workspace ~/.openclaw/workspace --from-identity
```
Override fields explicitly:
```bash
moltbot agents set-identity --agent main --name "Clawd" --emoji "🦞" --avatar avatars/clawd.png
openclaw agents set-identity --agent main --name "OpenClaw" --emoji "🦞" --avatar avatars/openclaw.png
```
Config sample:
@@ -59,10 +59,10 @@ Config sample:
{
id: "main",
identity: {
name: "Clawd",
name: "OpenClaw",
theme: "space lobster",
emoji: "🦞",
avatar: "avatars/clawd.png"
avatar: "avatars/openclaw.png"
}
}
]

28
docs/cli/approvals.md
View File

@@ -1,11 +1,11 @@
---
summary: "CLI reference for `moltbot approvals` (exec approvals for gateway or node hosts)"
summary: "CLI reference for `openclaw approvals` (exec approvals for gateway or node hosts)"
read_when:
- You want to edit exec approvals from the CLI
- You need to manage allowlists on gateway or node hosts
---
# `moltbot approvals`
# `openclaw approvals`
Manage exec approvals for the **local host**, **gateway host**, or a **node host**.
By default, commands target the local approvals file on disk. Use `--gateway` to target the gateway, or `--node` to target a specific node.
@@ -17,32 +17,32 @@ Related:
## Common commands
```bash
moltbot approvals get
moltbot approvals get --node <id|name|ip>
moltbot approvals get --gateway
openclaw approvals get
openclaw approvals get --node <id|name|ip>
openclaw approvals get --gateway
```
## Replace approvals from a file
```bash
moltbot approvals set --file ./exec-approvals.json
moltbot approvals set --node <id|name|ip> --file ./exec-approvals.json
moltbot approvals set --gateway --file ./exec-approvals.json
openclaw approvals set --file ./exec-approvals.json
openclaw approvals set --node <id|name|ip> --file ./exec-approvals.json
openclaw approvals set --gateway --file ./exec-approvals.json
```
## Allowlist helpers
```bash
moltbot approvals allowlist add "~/Projects/**/bin/rg"
moltbot approvals allowlist add --agent main --node <id|name|ip> "/usr/bin/uptime"
moltbot approvals allowlist add --agent "*" "/usr/bin/uname"
openclaw approvals allowlist add "~/Projects/**/bin/rg"
openclaw approvals allowlist add --agent main --node <id|name|ip> "/usr/bin/uptime"
openclaw approvals allowlist add --agent "*" "/usr/bin/uname"
moltbot approvals allowlist remove "~/Projects/**/bin/rg"
openclaw approvals allowlist remove "~/Projects/**/bin/rg"
```
## Notes
- `--node` uses the same resolver as `moltbot nodes` (id, name, ip, or id prefix).
- `--node` uses the same resolver as `openclaw nodes` (id, name, ip, or id prefix).
- `--agent` defaults to `"*"`, which applies to all agents.
- The node host must advertise `system.execApprovals.get/set` (macOS app or headless node host).
- Approvals files are stored per host at `~/.clawdbot/exec-approvals.json`.
- Approvals files are stored per host at `~/.openclaw/exec-approvals.json`.

48
docs/cli/browser.md
View File

@@ -1,14 +1,14 @@
---
summary: "CLI reference for `moltbot browser` (profiles, tabs, actions, extension relay)"
summary: "CLI reference for `openclaw browser` (profiles, tabs, actions, extension relay)"
read_when:
- You use `moltbot browser` and want examples for common tasks
- You use `openclaw browser` and want examples for common tasks
- You want to control a browser running on another machine via a node host
- You want to use the Chrome extension relay (attach/detach via toolbar button)
---
# `moltbot browser`
# `openclaw browser`
Manage Moltbot’s browser control server and run browser actions (tabs, snapshots, screenshots, navigation, clicks, typing).
Manage OpenClaw’s browser control server and run browser actions (tabs, snapshots, screenshots, navigation, clicks, typing).
Related:
- Browser tool + API: [Browser tool](/tools/browser)
@@ -25,37 +25,37 @@ Related:
## Quick start (local)
```bash
moltbot browser --browser-profile chrome tabs
moltbot browser --browser-profile clawd start
moltbot browser --browser-profile clawd open https://example.com
moltbot browser --browser-profile clawd snapshot
openclaw browser --browser-profile chrome tabs
openclaw browser --browser-profile openclaw start
openclaw browser --browser-profile openclaw open https://example.com
openclaw browser --browser-profile openclaw snapshot
```
## Profiles
Profiles are named browser routing configs. In practice:
- `clawd`: launches/attaches to a dedicated Moltbot-managed Chrome instance (isolated user data dir).
- `openclaw`: launches/attaches to a dedicated OpenClaw-managed Chrome instance (isolated user data dir).
- `chrome`: controls your existing Chrome tab(s) via the Chrome extension relay.
```bash
moltbot browser profiles
moltbot browser create-profile --name work --color "#FF5A36"
moltbot browser delete-profile --name work
openclaw browser profiles
openclaw browser create-profile --name work --color "#FF5A36"
openclaw browser delete-profile --name work
```
Use a specific profile:
```bash
moltbot browser --browser-profile work tabs
openclaw browser --browser-profile work tabs
```
## Tabs
```bash
moltbot browser tabs
moltbot browser open https://docs.molt.bot
moltbot browser focus <targetId>
moltbot browser close <targetId>
openclaw browser tabs
openclaw browser open https://docs.openclaw.ai
openclaw browser focus <targetId>
openclaw browser close <targetId>
```
## Snapshot / screenshot / actions
@@ -63,21 +63,21 @@ moltbot browser close <targetId>
Snapshot:
```bash
moltbot browser snapshot
openclaw browser snapshot
```
Screenshot:
```bash
moltbot browser screenshot
openclaw browser screenshot
```
Navigate/click/type (ref-based UI automation):
```bash
moltbot browser navigate https://example.com
moltbot browser click <ref>
moltbot browser type <ref> "hello"
openclaw browser navigate https://example.com
openclaw browser click <ref>
openclaw browser type <ref> "hello"
```
## Chrome extension relay (attach via toolbar button)
@@ -87,8 +87,8 @@ This mode lets the agent control an existing Chrome tab that you attach manually
Install the unpacked extension to a stable path:
```bash
moltbot browser extension install
moltbot browser extension path
openclaw browser extension install
openclaw browser extension path
```
Then Chrome → `chrome://extensions` → enable “Developer mode” → “Load unpacked” → select the printed folder.

42
docs/cli/channels.md
View File

@@ -1,11 +1,11 @@
---
summary: "CLI reference for `moltbot channels` (accounts, status, login/logout, logs)"
summary: "CLI reference for `openclaw channels` (accounts, status, login/logout, logs)"
read_when:
- You want to add/remove channel accounts (WhatsApp/Telegram/Discord/Google Chat/Slack/Mattermost (plugin)/Signal/iMessage)
- You want to check channel status or tail channel logs
---
# `moltbot channels`
# `openclaw channels`
Manage chat channel accounts and their runtime status on the Gateway.
@@ -16,43 +16,43 @@ Related docs:
## Common commands
```bash
moltbot channels list
moltbot channels status
moltbot channels capabilities
moltbot channels capabilities --channel discord --target channel:123
moltbot channels resolve --channel slack "#general" "@jane"
moltbot channels logs --channel all
openclaw channels list
openclaw channels status
openclaw channels capabilities
openclaw channels capabilities --channel discord --target channel:123
openclaw channels resolve --channel slack "#general" "@jane"
openclaw channels logs --channel all
```
## Add / remove accounts
```bash
moltbot channels add --channel telegram --token <bot-token>
moltbot channels remove --channel telegram --delete
openclaw channels add --channel telegram --token <bot-token>
openclaw channels remove --channel telegram --delete
```
Tip: `moltbot channels add --help` shows per-channel flags (token, app token, signal-cli paths, etc).
Tip: `openclaw channels add --help` shows per-channel flags (token, app token, signal-cli paths, etc).
## Login / logout (interactive)
```bash
moltbot channels login --channel whatsapp
moltbot channels logout --channel whatsapp
openclaw channels login --channel whatsapp
openclaw channels logout --channel whatsapp
```
## Troubleshooting
- Run `moltbot status --deep` for a broad probe.
- Use `moltbot doctor` for guided fixes.
- `moltbot channels list` prints `Claude: HTTP 403 ... user:profile` → usage snapshot needs the `user:profile` scope. Use `--no-usage`, or provide a claude.ai session key (`CLAUDE_WEB_SESSION_KEY` / `CLAUDE_WEB_COOKIE`), or re-auth via Claude Code CLI.
- Run `openclaw status --deep` for a broad probe.
- Use `openclaw doctor` for guided fixes.
- `openclaw channels list` prints `Claude: HTTP 403 ... user:profile` → usage snapshot needs the `user:profile` scope. Use `--no-usage`, or provide a claude.ai session key (`CLAUDE_WEB_SESSION_KEY` / `CLAUDE_WEB_COOKIE`), or re-auth via Claude Code CLI.
## Capabilities probe
Fetch provider capability hints (intents/scopes where available) plus static feature support:
```bash
moltbot channels capabilities
moltbot channels capabilities --channel discord --target channel:123
openclaw channels capabilities
openclaw channels capabilities --channel discord --target channel:123
```
Notes:
@@ -65,9 +65,9 @@ Notes:
Resolve channel/user names to IDs using the provider directory:
```bash
moltbot channels resolve --channel slack "#general" "@jane"
moltbot channels resolve --channel discord "My Server/#support" "@someone"
moltbot channels resolve --channel matrix "Project Room"
openclaw channels resolve --channel slack "#general" "@jane"
openclaw channels resolve --channel discord "My Server/#support" "@someone"
openclaw channels resolve --channel matrix "Project Room"
```
Notes:

30
docs/cli/config.md
View File

@@ -1,22 +1,22 @@
---
summary: "CLI reference for `moltbot config` (get/set/unset config values)"
summary: "CLI reference for `openclaw config` (get/set/unset config values)"
read_when:
- You want to read or edit config non-interactively
---
# `moltbot config`
# `openclaw config`
Config helpers: get/set/unset values by path. Run without a subcommand to open
the configure wizard (same as `moltbot configure`).
the configure wizard (same as `openclaw configure`).
## Examples
```bash
moltbot config get browser.executablePath
moltbot config set browser.executablePath "/usr/bin/google-chrome"
moltbot config set agents.defaults.heartbeat.every "2h"
moltbot config set agents.list[0].tools.exec.node "node-id-or-name"
moltbot config unset tools.web.search.apiKey
openclaw config get browser.executablePath
openclaw config set browser.executablePath "/usr/bin/google-chrome"
openclaw config set agents.defaults.heartbeat.every "2h"
openclaw config set agents.list[0].tools.exec.node "node-id-or-name"
openclaw config unset tools.web.search.apiKey
```
## Paths
@@ -24,15 +24,15 @@ moltbot config unset tools.web.search.apiKey
Paths use dot or bracket notation:
```bash
moltbot config get agents.defaults.workspace
moltbot config get agents.list[0].id
openclaw config get agents.defaults.workspace
openclaw config get agents.list[0].id
```
Use the agent list index to target a specific agent:
```bash
moltbot config get agents.list
moltbot config set agents.list[1].tools.exec.node "node-id-or-name"
openclaw config get agents.list
openclaw config set agents.list[1].tools.exec.node "node-id-or-name"
```
## Values
@@ -41,9 +41,9 @@ Values are parsed as JSON5 when possible; otherwise they are treated as strings.
Use `--json` to require JSON5 parsing.
```bash
moltbot config set agents.defaults.heartbeat.every "0m"
moltbot config set gateway.port 19001 --json
moltbot config set channels.whatsapp.groups '["*"]' --json
openclaw config set agents.defaults.heartbeat.every "0m"
openclaw config set gateway.port 19001 --json
openclaw config set channels.whatsapp.groups '["*"]' --json
```
Restart the gateway after edits.

12
docs/cli/configure.md
View File

@@ -1,18 +1,18 @@
---
summary: "CLI reference for `moltbot configure` (interactive configuration prompts)"
summary: "CLI reference for `openclaw configure` (interactive configuration prompts)"
read_when:
- You want to tweak credentials, devices, or agent defaults interactively
---
# `moltbot configure`
# `openclaw configure`
Interactive prompt to set up credentials, devices, and agent defaults.
Note: The **Model** section now includes a multi-select for the
`agents.defaults.models` allowlist (what shows up in `/model` and the model picker).
Tip: `moltbot config` without a subcommand opens the same wizard. Use
`moltbot config get|set|unset` for non-interactive edits.
Tip: `openclaw config` without a subcommand opens the same wizard. Use
`openclaw config get|set|unset` for non-interactive edits.
Related:
- Gateway configuration reference: [Configuration](/gateway/configuration)
@@ -25,6 +25,6 @@ Notes:
## Examples
```bash
moltbot configure
moltbot configure --section models --section channels
openclaw configure
openclaw configure --section models --section channels
```

10
docs/cli/cron.md
View File

@@ -1,29 +1,29 @@
---
summary: "CLI reference for `moltbot cron` (schedule and run background jobs)"
summary: "CLI reference for `openclaw cron` (schedule and run background jobs)"
read_when:
- You want scheduled jobs and wakeups
- You’re debugging cron execution and logs
---
# `moltbot cron`
# `openclaw cron`
Manage cron jobs for the Gateway scheduler.
Related:
- Cron jobs: [Cron jobs](/automation/cron-jobs)
Tip: run `moltbot cron --help` for the full command surface.
Tip: run `openclaw cron --help` for the full command surface.
## Common edits
Update delivery settings without changing the message:
```bash
moltbot cron edit <job-id> --deliver --channel telegram --to "123456789"
openclaw cron edit <job-id> --deliver --channel telegram --to "123456789"
```
Disable delivery for an isolated job:
```bash
moltbot cron edit <job-id> --no-deliver
openclaw cron edit <job-id> --no-deliver
```

8
docs/cli/dashboard.md
View File

@@ -1,16 +1,16 @@
---
summary: "CLI reference for `moltbot dashboard` (open the Control UI)"
summary: "CLI reference for `openclaw dashboard` (open the Control UI)"
read_when:
- You want to open the Control UI with your current token
- You want to print the URL without launching a browser
---
# `moltbot dashboard`
# `openclaw dashboard`
Open the Control UI using your current auth.
```bash
moltbot dashboard
moltbot dashboard --no-open
openclaw dashboard
openclaw dashboard --no-open
```

26
docs/cli/devices.md
View File

@@ -1,55 +1,55 @@
---
summary: "CLI reference for `moltbot devices` (device pairing + token rotation/revocation)"
summary: "CLI reference for `openclaw devices` (device pairing + token rotation/revocation)"
read_when:
- You are approving device pairing requests
- You need to rotate or revoke device tokens
---
# `moltbot devices`
# `openclaw devices`
Manage device pairing requests and device-scoped tokens.
## Commands
### `moltbot devices list`
### `openclaw devices list`
List pending pairing requests and paired devices.
```
moltbot devices list
moltbot devices list --json
openclaw devices list
openclaw devices list --json
```
### `moltbot devices approve <requestId>`
### `openclaw devices approve <requestId>`
Approve a pending device pairing request.
```
moltbot devices approve <requestId>
openclaw devices approve <requestId>
```
### `moltbot devices reject <requestId>`
### `openclaw devices reject <requestId>`
Reject a pending device pairing request.
```
moltbot devices reject <requestId>
openclaw devices reject <requestId>
```
### `moltbot devices rotate --device <id> --role <role> [--scope <scope...>]`
### `openclaw devices rotate --device <id> --role <role> [--scope <scope...>]`
Rotate a device token for a specific role (optionally updating scopes).
```
moltbot devices rotate --device <deviceId> --role operator --scope operator.read --scope operator.write
openclaw devices rotate --device <deviceId> --role operator --scope operator.read --scope operator.write
```
### `moltbot devices revoke --device <id> --role <role>`
### `openclaw devices revoke --device <id> --role <role>`
Revoke a device token for a specific role.
```
moltbot devices revoke --device <deviceId> --role node
openclaw devices revoke --device <deviceId> --role node
```
## Common options

24
docs/cli/directory.md
View File

@@ -1,11 +1,11 @@
---
summary: "CLI reference for `moltbot directory` (self, peers, groups)"
summary: "CLI reference for `openclaw directory` (self, peers, groups)"
read_when:
- You want to look up contacts/groups/self ids for a channel
- You are developing a channel directory adapter
---
# `moltbot directory`
# `openclaw directory`
Directory lookups for channels that support it (contacts/peers, groups, and “me”).
@@ -15,15 +15,15 @@ Directory lookups for channels that support it (contacts/peers, groups, and “m
- `--json`: output JSON
## Notes
- `directory` is meant to help you find IDs you can paste into other commands (especially `moltbot message send --target ...`).
- `directory` is meant to help you find IDs you can paste into other commands (especially `openclaw message send --target ...`).
- For many channels, results are config-backed (allowlists / configured groups) rather than a live provider directory.
- Default output is `id` (and sometimes `name`) separated by a tab; use `--json` for scripting.
## Using results with `message send`
```bash
moltbot directory peers list --channel slack --query "U0"
moltbot message send --channel slack --target user:U012ABCDEF --message "hello"
openclaw directory peers list --channel slack --query "U0"
openclaw message send --channel slack --target user:U012ABCDEF --message "hello"
```
## ID formats (by channel)
@@ -40,21 +40,21 @@ moltbot message send --channel slack --target user:U012ABCDEF --message "hello"
## Self (“me”)
```bash
moltbot directory self --channel zalouser
openclaw directory self --channel zalouser
```
## Peers (contacts/users)
```bash
moltbot directory peers list --channel zalouser
moltbot directory peers list --channel zalouser --query "name"
moltbot directory peers list --channel zalouser --limit 50
openclaw directory peers list --channel zalouser
openclaw directory peers list --channel zalouser --query "name"
openclaw directory peers list --channel zalouser --limit 50
```
## Groups
```bash
moltbot directory groups list --channel zalouser
moltbot directory groups list --channel zalouser --query "work"
moltbot directory groups members --channel zalouser --group-id <id>
openclaw directory groups list --channel zalouser
openclaw directory groups list --channel zalouser --query "work"
openclaw directory groups members --channel zalouser --group-id <id>
```

11
docs/cli/dns.md
View File

@@ -1,11 +1,11 @@
---
summary: "CLI reference for `moltbot dns` (wide-area discovery helpers)"
summary: "CLI reference for `openclaw dns` (wide-area discovery helpers)"
read_when:
- You want wide-area discovery (DNS-SD) via Tailscale + CoreDNS
- You’re setting up split DNS for moltbot.internal
- You’re setting up split DNS for a custom discovery domain (example: openclaw.internal)
---
# `moltbot dns`
# `openclaw dns`
DNS helpers for wide-area discovery (Tailscale + CoreDNS). Currently focused on macOS + Homebrew CoreDNS.
@@ -16,7 +16,6 @@ Related:
## Setup
```bash
moltbot dns setup
moltbot dns setup --apply
openclaw dns setup
openclaw dns setup --apply
```

10
docs/cli/docs.md
View File

@@ -1,15 +1,15 @@
---
summary: "CLI reference for `moltbot docs` (search the live docs index)"
summary: "CLI reference for `openclaw docs` (search the live docs index)"
read_when:
- You want to search the live Moltbot docs from the terminal
- You want to search the live OpenClaw docs from the terminal
---
# `moltbot docs`
# `openclaw docs`
Search the live docs index.
```bash
moltbot docs browser extension
moltbot docs sandbox allowHostControl
openclaw docs browser extension
openclaw docs sandbox allowHostControl
```

22
docs/cli/doctor.md
View File

@@ -1,11 +1,11 @@
---
summary: "CLI reference for `moltbot doctor` (health checks + guided repairs)"
summary: "CLI reference for `openclaw doctor` (health checks + guided repairs)"
read_when:
- You have connectivity/auth issues and want guided fixes
- You updated and want a sanity check
---
# `moltbot doctor`
# `openclaw doctor`
Health checks + quick fixes for the gateway and channels.
@@ -16,23 +16,23 @@ Related:
## Examples
```bash
moltbot doctor
moltbot doctor --repair
moltbot doctor --deep
openclaw doctor
openclaw doctor --repair
openclaw doctor --deep
```
Notes:
- Interactive prompts (like keychain/OAuth fixes) only run when stdin is a TTY and `--non-interactive` is **not** set. Headless runs (cron, Telegram, no terminal) will skip prompts.
- `--fix` (alias for `--repair`) writes a backup to `~/.clawdbot/moltbot.json.bak` and drops unknown config keys, listing each removal.
- `--fix` (alias for `--repair`) writes a backup to `~/.openclaw/openclaw.json.bak` and drops unknown config keys, listing each removal.
## macOS: `launchctl` env overrides
If you previously ran `launchctl setenv CLAWDBOT_GATEWAY_TOKEN ...` (or `...PASSWORD`), that value overrides your config file and can cause persistent “unauthorized” errors.
If you previously ran `launchctl setenv OPENCLAW_GATEWAY_TOKEN ...` (or `...PASSWORD`), that value overrides your config file and can cause persistent “unauthorized” errors.
```bash
launchctl getenv CLAWDBOT_GATEWAY_TOKEN
launchctl getenv CLAWDBOT_GATEWAY_PASSWORD
launchctl getenv OPENCLAW_GATEWAY_TOKEN
launchctl getenv OPENCLAW_GATEWAY_PASSWORD
launchctl unsetenv CLAWDBOT_GATEWAY_TOKEN
launchctl unsetenv CLAWDBOT_GATEWAY_PASSWORD
launchctl unsetenv OPENCLAW_GATEWAY_TOKEN
launchctl unsetenv OPENCLAW_GATEWAY_PASSWORD
```

52
docs/cli/gateway.md
View File

@@ -1,5 +1,5 @@
---
summary: "Moltbot Gateway CLI (`moltbot gateway`) — run, query, and discover gateways"
summary: "OpenClaw Gateway CLI (`openclaw gateway`) — run, query, and discover gateways"
read_when:
- Running the Gateway from the CLI (dev or servers)
- Debugging Gateway auth, bind modes, and connectivity
@@ -8,9 +8,9 @@ read_when:
# Gateway CLI
The Gateway is Moltbot’s WebSocket server (channels, nodes, sessions, hooks).
The Gateway is OpenClaw’s WebSocket server (channels, nodes, sessions, hooks).
Subcommands in this page live under `moltbot gateway …`.
Subcommands in this page live under `openclaw gateway …`.
Related docs:
- [/gateway/bonjour](/gateway/bonjour)
@@ -22,17 +22,17 @@ Related docs:
Run a local Gateway process:
```bash
moltbot gateway
openclaw gateway
```
Foreground alias:
```bash
moltbot gateway run
openclaw gateway run
```
Notes:
- By default, the Gateway refuses to start unless `gateway.mode=local` is set in `~/.clawdbot/moltbot.json`. Use `--allow-unconfigured` for ad-hoc/dev runs.
- By default, the Gateway refuses to start unless `gateway.mode=local` is set in `~/.openclaw/openclaw.json`. Use `--allow-unconfigured` for ad-hoc/dev runs.
- Binding beyond loopback without auth is blocked (safety guardrail).
- `SIGUSR1` triggers an in-process restart when authorized (enable `commands.restart` or use the gateway tool/config apply/update).
- `SIGINT`/`SIGTERM` handlers stop the gateway process, but they don’t restore any custom terminal state. If you wrap the CLI with a TUI or raw-mode input, restore the terminal before exit.
@@ -42,8 +42,8 @@ Notes:
- `--port <port>`: WebSocket port (default comes from config/env; usually `18789`).
- `--bind <loopback|lan|tailnet|auto|custom>`: listener bind mode.
- `--auth <token|password>`: auth mode override.
- `--token <token>`: token override (also sets `CLAWDBOT_GATEWAY_TOKEN` for the process).
- `--password <password>`: password override (also sets `CLAWDBOT_GATEWAY_PASSWORD` for the process).
- `--token <token>`: token override (also sets `OPENCLAW_GATEWAY_TOKEN` for the process).
- `--password <password>`: password override (also sets `OPENCLAW_GATEWAY_PASSWORD` for the process).
- `--tailscale <off|serve|funnel>`: expose the Gateway via Tailscale.
- `--tailscale-reset-on-exit`: reset Tailscale serve/funnel config on shutdown.
- `--allow-unconfigured`: allow gateway start without `gateway.mode=local` in config.
@@ -76,7 +76,7 @@ Shared options (where supported):
### `gateway health`
```bash
moltbot gateway health --url ws://127.0.0.1:18789
openclaw gateway health --url ws://127.0.0.1:18789
```
### `gateway status`
@@ -84,8 +84,8 @@ moltbot gateway health --url ws://127.0.0.1:18789
`gateway status` shows the Gateway service (launchd/systemd/schtasks) plus an optional RPC probe.
```bash
moltbot gateway status
moltbot gateway status --json
openclaw gateway status
openclaw gateway status --json
```
Options:
@@ -105,8 +105,8 @@ Options:
If multiple gateways are reachable, it prints all of them. Multiple gateways are supported when you use isolated profiles/ports (e.g., a rescue bot), but most installs still run a single gateway.
```bash
moltbot gateway probe
moltbot gateway probe --json
openclaw gateway probe
openclaw gateway probe --json
```
#### Remote over SSH (Mac app parity)
@@ -116,7 +116,7 @@ The macOS app “Remote over SSH” mode uses a local port-forward so the remote
CLI equivalent:
```bash
moltbot gateway probe --ssh user@gateway-host
openclaw gateway probe --ssh user@gateway-host
```
Options:
@@ -133,18 +133,18 @@ Config (optional, used as defaults):
Low-level RPC helper.
```bash
moltbot gateway call status
moltbot gateway call logs.tail --params '{"sinceMs": 60000}'
openclaw gateway call status
openclaw gateway call logs.tail --params '{"sinceMs": 60000}'
```
## Manage the Gateway service
```bash
moltbot gateway install
moltbot gateway start
moltbot gateway stop
moltbot gateway restart
moltbot gateway uninstall
openclaw gateway install
openclaw gateway start
openclaw gateway stop
openclaw gateway restart
openclaw gateway uninstall
```
Notes:
@@ -153,10 +153,10 @@ Notes:
## Discover gateways (Bonjour)
`gateway discover` scans for Gateway beacons (`_moltbot-gw._tcp`).
`gateway discover` scans for Gateway beacons (`_openclaw-gw._tcp`).
- Multicast DNS-SD: `local.`
- Unicast DNS-SD (Wide-Area Bonjour): `moltbot.internal.` (requires split DNS + DNS server; see [/gateway/bonjour](/gateway/bonjour))
- Unicast DNS-SD (Wide-Area Bonjour): choose a domain (example: `openclaw.internal.`) and set up split DNS + a DNS server; see [/gateway/bonjour](/gateway/bonjour)
Only gateways with Bonjour discovery enabled (default) advertise the beacon.
@@ -172,7 +172,7 @@ Wide-Area discovery records include (TXT):
### `gateway discover`
```bash
moltbot gateway discover
openclaw gateway discover
```
Options:
@@ -182,6 +182,6 @@ Options:
Examples:
```bash
moltbot gateway discover --timeout 4000
moltbot gateway discover --json | jq '.beacons[].wsUrl'
openclaw gateway discover --timeout 4000
openclaw gateway discover --json | jq '.beacons[].wsUrl'
```

10
docs/cli/health.md
View File

@@ -1,17 +1,17 @@
---
summary: "CLI reference for `moltbot health` (gateway health endpoint via RPC)"
summary: "CLI reference for `openclaw health` (gateway health endpoint via RPC)"
read_when:
- You want to quickly check the running Gateway’s health
---
# `moltbot health`
# `openclaw health`
Fetch health from the running Gateway.
```bash
moltbot health
moltbot health --json
moltbot health --verbose
openclaw health
openclaw health --json
openclaw health --verbose
```
Notes:

70
docs/cli/hooks.md
View File

@@ -1,11 +1,11 @@
---
summary: "CLI reference for `moltbot hooks` (agent hooks)"
summary: "CLI reference for `openclaw hooks` (agent hooks)"
read_when:
- You want to manage agent hooks
- You want to install or update hooks
---
# `moltbot hooks`
# `openclaw hooks`
Manage agent hooks (event-driven automations for commands like `/new`, `/reset`, and gateway startup).
@@ -16,7 +16,7 @@ Related:
## List All Hooks
```bash
moltbot hooks list
openclaw hooks list
```
List all discovered hooks from workspace, managed, and bundled directories.
@@ -41,7 +41,7 @@ Ready:
**Example (verbose):**
```bash
moltbot hooks list --verbose
openclaw hooks list --verbose
```
Shows missing requirements for ineligible hooks.
@@ -49,7 +49,7 @@ Shows missing requirements for ineligible hooks.
**Example (JSON):**
```bash
moltbot hooks list --json
openclaw hooks list --json
```
Returns structured JSON for programmatic use.
@@ -57,7 +57,7 @@ Returns structured JSON for programmatic use.
## Get Hook Information
```bash
moltbot hooks info <name>
openclaw hooks info <name>
```
Show detailed information about a specific hook.
@@ -71,7 +71,7 @@ Show detailed information about a specific hook.
**Example:**
```bash
moltbot hooks info session-memory
openclaw hooks info session-memory
```
**Output:**
@@ -82,10 +82,10 @@ moltbot hooks info session-memory
Save session context to memory when /new command is issued
Details:
Source: moltbot-bundled
Path: /path/to/moltbot/hooks/bundled/session-memory/HOOK.md
Handler: /path/to/moltbot/hooks/bundled/session-memory/handler.ts
Homepage: https://docs.molt.bot/hooks#session-memory
Source: openclaw-bundled
Path: /path/to/openclaw/hooks/bundled/session-memory/HOOK.md
Handler: /path/to/openclaw/hooks/bundled/session-memory/handler.ts
Homepage: https://docs.openclaw.ai/hooks#session-memory
Events: command:new
Requirements:
@@ -95,7 +95,7 @@ Requirements:
## Check Hooks Eligibility
```bash
moltbot hooks check
openclaw hooks check
```
Show summary of hook eligibility status (how many are ready vs. not ready).
@@ -116,12 +116,12 @@ Not ready: 0
## Enable a Hook
```bash
moltbot hooks enable <name>
openclaw hooks enable <name>
```
Enable a specific hook by adding it to your config (`~/.clawdbot/config.json`).
Enable a specific hook by adding it to your config (`~/.openclaw/config.json`).
**Note:** Hooks managed by plugins show `plugin:<id>` in `moltbot hooks list` and
**Note:** Hooks managed by plugins show `plugin:<id>` in `openclaw hooks list` and
can’t be enabled/disabled here. Enable/disable the plugin instead.
**Arguments:**
@@ -130,7 +130,7 @@ can’t be enabled/disabled here. Enable/disable the plugin instead.
**Example:**
```bash
moltbot hooks enable session-memory
openclaw hooks enable session-memory
```
**Output:**
@@ -150,7 +150,7 @@ moltbot hooks enable session-memory
## Disable a Hook
```bash
moltbot hooks disable <name>
openclaw hooks disable <name>
```
Disable a specific hook by updating your config.
@@ -161,7 +161,7 @@ Disable a specific hook by updating your config.
**Example:**
```bash
moltbot hooks disable command-logger
openclaw hooks disable command-logger
```
**Output:**
@@ -176,13 +176,13 @@ moltbot hooks disable command-logger
## Install Hooks
```bash
moltbot hooks install <path-or-spec>
openclaw hooks install <path-or-spec>
```
Install a hook pack from a local folder/archive or npm.
**What it does:**
- Copies the hook pack into `~/.clawdbot/hooks/<id>`
- Copies the hook pack into `~/.openclaw/hooks/<id>`
- Enables the installed hooks in `hooks.internal.entries.*`
- Records the install under `hooks.internal.installs`
@@ -195,23 +195,23 @@ Install a hook pack from a local folder/archive or npm.
```bash
# Local directory
moltbot hooks install ./my-hook-pack
openclaw hooks install ./my-hook-pack
# Local archive
moltbot hooks install ./my-hook-pack.zip
openclaw hooks install ./my-hook-pack.zip
# NPM package
moltbot hooks install @moltbot/my-hook-pack
openclaw hooks install @openclaw/my-hook-pack
# Link a local directory without copying
moltbot hooks install -l ./my-hook-pack
openclaw hooks install -l ./my-hook-pack
```
## Update Hooks
```bash
moltbot hooks update <id>
moltbot hooks update --all
openclaw hooks update <id>
openclaw hooks update --all
```
Update installed hook packs (npm installs only).
@@ -229,10 +229,10 @@ Saves session context to memory when you issue `/new`.
**Enable:**
```bash
moltbot hooks enable session-memory
openclaw hooks enable session-memory
```
**Output:** `~/clawd/memory/YYYY-MM-DD-slug.md`
**Output:** `~/.openclaw/workspace/memory/YYYY-MM-DD-slug.md`
**See:** [session-memory documentation](/hooks#session-memory)
@@ -243,22 +243,22 @@ Logs all command events to a centralized audit file.
**Enable:**
```bash
moltbot hooks enable command-logger
openclaw hooks enable command-logger
```
**Output:** `~/.clawdbot/logs/commands.log`
**Output:** `~/.openclaw/logs/commands.log`
**View logs:**
```bash
# Recent commands
tail -n 20 ~/.clawdbot/logs/commands.log
tail -n 20 ~/.openclaw/logs/commands.log
# Pretty-print
cat ~/.clawdbot/logs/commands.log | jq .
cat ~/.openclaw/logs/commands.log | jq .
# Filter by action
grep '"action":"new"' ~/.clawdbot/logs/commands.log | jq .
grep '"action":"new"' ~/.openclaw/logs/commands.log | jq .
```
**See:** [command-logger documentation](/hooks#command-logger)
@@ -270,7 +270,7 @@ Swaps injected `SOUL.md` content with `SOUL_EVIL.md` during a purge window or by
**Enable:**
```bash
moltbot hooks enable soul-evil
openclaw hooks enable soul-evil
```
**See:** [SOUL Evil Hook](/hooks/soul-evil)
@@ -284,7 +284,7 @@ Runs `BOOT.md` when the gateway starts (after channels start).
**Enable**:
```bash
moltbot hooks enable boot-md
openclaw hooks enable boot-md
```
**See:** [boot-md documentation](/hooks#boot-md)

84
docs/cli/index.md
View File

@@ -1,5 +1,5 @@
---
summary: "Moltbot CLI reference for `moltbot` commands, subcommands, and options"
summary: "OpenClaw CLI reference for `openclaw` commands, subcommands, and options"
read_when:
- Adding or modifying CLI commands or options
- Documenting new command surfaces
@@ -53,10 +53,10 @@ This page describes the current CLI behavior. If commands change, update this do
## Global flags
- `--dev`: isolate state under `~/.clawdbot-dev` and shift default ports.
- `--profile <name>`: isolate state under `~/.clawdbot-<name>`.
- `--dev`: isolate state under `~/.openclaw-dev` and shift default ports.
- `--profile <name>`: isolate state under `~/.openclaw-<name>`.
- `--no-color`: disable ANSI colors.
- `--update`: shorthand for `moltbot update` (source installs only).
- `--update`: shorthand for `openclaw update` (source installs only).
- `-V`, `--version`, `-v`: print version and exit.
## Output styling
@@ -69,7 +69,7 @@ This page describes the current CLI behavior. If commands change, update this do
## Color palette
Moltbot uses a lobster palette for CLI output.
OpenClaw uses a lobster palette for CLI output.
- `accent` (#FF5A2D): headings, labels, primary highlights.
- `accentBright` (#FF7A3D): command names, emphasis.
@@ -85,7 +85,7 @@ Palette source of truth: `src/terminal/palette.ts` (aka “lobster seam”).
## Command tree
```
moltbot [--dev] [--profile <name>] <command>
openclaw [--dev] [--profile <name>] <command>
setup
onboard
configure
@@ -236,23 +236,23 @@ moltbot [--dev] [--profile <name>] <command>
tui
```
Note: plugins can add additional top-level commands (for example `moltbot voicecall`).
Note: plugins can add additional top-level commands (for example `openclaw voicecall`).
## Security
- `moltbot security audit` — audit config + local state for common security foot-guns.
- `moltbot security audit --deep` — best-effort live Gateway probe.
- `moltbot security audit --fix` — tighten safe defaults and chmod state/config.
- `openclaw security audit` — audit config + local state for common security foot-guns.
- `openclaw security audit --deep` — best-effort live Gateway probe.
- `openclaw security audit --fix` — tighten safe defaults and chmod state/config.
## Plugins
Manage extensions and their config:
- `moltbot plugins list` — discover plugins (use `--json` for machine output).
- `moltbot plugins info <id>` — show details for a plugin.
- `moltbot plugins install <path|.tgz|npm-spec>` — install a plugin (or add a plugin path to `plugins.load.paths`).
- `moltbot plugins enable <id>` / `disable <id>` — toggle `plugins.entries.<id>.enabled`.
- `moltbot plugins doctor` — report plugin load errors.
- `openclaw plugins list` — discover plugins (use `--json` for machine output).
- `openclaw plugins info <id>` — show details for a plugin.
- `openclaw plugins install <path|.tgz|npm-spec>` — install a plugin (or add a plugin path to `plugins.load.paths`).
- `openclaw plugins enable <id>` / `disable <id>` — toggle `plugins.entries.<id>.enabled`.
- `openclaw plugins doctor` — report plugin load errors.
Most plugin changes require a gateway restart. See [/plugin](/plugin).
@@ -260,9 +260,9 @@ Most plugin changes require a gateway restart. See [/plugin](/plugin).
Vector search over `MEMORY.md` + `memory/*.md`:
- `moltbot memory status` — show index stats.
- `moltbot memory index` — reindex memory files.
- `moltbot memory search "<query>"` — semantic search over memory.
- `openclaw memory status` — show index stats.
- `openclaw memory index` — reindex memory files.
- `openclaw memory search "<query>"` — semantic search over memory.
## Chat slash commands
@@ -279,7 +279,7 @@ Highlights:
Initialize config + workspace.
Options:
- `--workspace <dir>`: agent workspace path (default `~/clawd`).
- `--workspace <dir>`: agent workspace path (default `~/.openclaw/workspace`).
- `--wizard`: run the onboarding wizard.
- `--non-interactive`: run wizard without prompts.
- `--mode <local|remote>`: wizard mode.
@@ -335,7 +335,7 @@ Options:
Interactive configuration wizard (models, channels, skills, gateway).
### `config`
Non-interactive config helpers (get/set/unset). Running `moltbot config` with no
Non-interactive config helpers (get/set/unset). Running `openclaw config` with no
subcommand launches the wizard.
Subcommands:
@@ -359,8 +359,8 @@ Manage chat channel accounts (WhatsApp/Telegram/Discord/Google Chat/Slack/Matter
Subcommands:
- `channels list`: show configured channels and auth profiles.
- `channels status`: check gateway reachability and channel health (`--probe` runs extra checks; use `moltbot health` or `moltbot status --deep` for gateway health probes).
- Tip: `channels status` prints warnings with suggested fixes when it can detect common misconfigurations (then points you to `moltbot doctor`).
- `channels status`: check gateway reachability and channel health (`--probe` runs extra checks; use `openclaw health` or `openclaw status --deep` for gateway health probes).
- Tip: `channels status` prints warnings with suggested fixes when it can detect common misconfigurations (then points you to `openclaw doctor`).
- `channels logs`: show recent channel logs from the gateway log file.
- `channels add`: wizard-style setup when no flags are passed; flags switch to non-interactive mode.
- `channels remove`: disable by default; pass `--delete` to remove config entries without prompts.
@@ -394,11 +394,11 @@ More detail: [/concepts/oauth](/concepts/oauth)
Examples:
```bash
moltbot channels add --channel telegram --account alerts --name "Alerts Bot" --token $TELEGRAM_BOT_TOKEN
moltbot channels add --channel discord --account work --name "Work Bot" --token $DISCORD_BOT_TOKEN
moltbot channels remove --channel discord --account work --delete
moltbot channels status --probe
moltbot status --deep
openclaw channels add --channel telegram --account alerts --name "Alerts Bot" --token $TELEGRAM_BOT_TOKEN
openclaw channels add --channel discord --account work --name "Work Bot" --token $DISCORD_BOT_TOKEN
openclaw channels remove --channel discord --account work --delete
openclaw channels status --probe
openclaw status --deep
```
### `skills`
@@ -455,8 +455,8 @@ Subcommands:
- `message event <list|create>`
Examples:
- `moltbot message send --target +15555550123 --message "Hi"`
- `moltbot message poll --channel discord --target channel:123 --poll-question "Snack?" --poll-option Pizza --poll-option Sushi`
- `openclaw message send --target +15555550123 --message "Hi"`
- `openclaw message poll --channel discord --target channel:123 --poll-question "Snack?" --poll-option Pizza --poll-option Sushi`
### `agent`
Run one agent turn via the Gateway (or `--local` embedded).
@@ -526,11 +526,11 @@ Notes:
- Overview includes Gateway + node host service status when available.
### Usage tracking
Moltbot can surface provider usage/quota when OAuth/API creds are available.
OpenClaw can surface provider usage/quota when OAuth/API creds are available.
Surfaces:
- `/status` (adds a short provider usage line when available)
- `moltbot status --usage` (prints full provider breakdown)
- `openclaw status --usage` (prints full provider breakdown)
- macOS menu bar (Usage section under Context)
Notes:
@@ -624,7 +624,7 @@ Subcommands:
Notes:
- `gateway status` probes the Gateway RPC by default using the service’s resolved port/config (override with `--url/--token/--password`).
- `gateway status` supports `--no-probe`, `--deep`, and `--json` for scripting.
- `gateway status` also surfaces legacy or extra gateway services when it can detect them (`--deep` adds system-level scans). Profile-named Moltbot services are treated as first-class and aren't flagged as "extra".
- `gateway status` also surfaces legacy or extra gateway services when it can detect them (`--deep` adds system-level scans). Profile-named OpenClaw services are treated as first-class and aren't flagged as "extra".
- `gateway status` prints which config path the CLI uses vs which config the service likely uses (service env), plus the resolved probe target URL.
- `gateway install|uninstall|start|stop|restart` support `--json` for scripting (default output stays human-friendly).
- `gateway install` defaults to Node runtime; bun is **not recommended** (WhatsApp/Telegram bugs).
@@ -639,11 +639,11 @@ Notes:
Examples:
```bash
moltbot logs --follow
moltbot logs --limit 200
moltbot logs --plain
moltbot logs --json
moltbot logs --no-color
openclaw logs --follow
openclaw logs --limit 200
openclaw logs --plain
openclaw logs --json
openclaw logs --no-color
```
### `gateway <subcommand>`
@@ -674,12 +674,12 @@ Preferred Anthropic auth (setup-token):
```bash
claude setup-token
moltbot models auth setup-token --provider anthropic
moltbot models status
openclaw models auth setup-token --provider anthropic
openclaw models status
```
### `models` (root)
`moltbot models` is an alias for `models status`.
`openclaw models` is an alias for `models status`.
Root options:
- `--status-json` (alias for `models status --json`)
@@ -807,7 +807,7 @@ All `cron` commands accept `--url`, `--token`, `--timeout`, `--expect-final`.
## Node host
`node` runs a **headless node host** or manages it as a background service. See
[`moltbot node`](/cli/node).
[`openclaw node`](/cli/node).
Subcommands:
- `node run --host <gateway-host> --port 18789`
@@ -856,7 +856,7 @@ Location:
## Browser
Browser control CLI (dedicated Chrome/Brave/Edge/Chromium). See [`moltbot browser`](/cli/browser) and the [Browser tool](/tools/browser).
Browser control CLI (dedicated Chrome/Brave/Edge/Chromium). See [`openclaw browser`](/cli/browser) and the [Browser tool](/tools/browser).
Common options:
- `--url`, `--token`, `--timeout`, `--json`

12
docs/cli/logs.md
View File

@@ -1,11 +1,11 @@
---
summary: "CLI reference for `moltbot logs` (tail gateway logs via RPC)"
summary: "CLI reference for `openclaw logs` (tail gateway logs via RPC)"
read_when:
- You need to tail Gateway logs remotely (without SSH)
- You want JSON log lines for tooling
---
# `moltbot logs`
# `openclaw logs`
Tail Gateway file logs over RPC (works in remote mode).
@@ -15,9 +15,9 @@ Related:
## Examples
```bash
moltbot logs
moltbot logs --follow
moltbot logs --json
moltbot logs --limit 500
openclaw logs
openclaw logs --follow
openclaw logs --json
openclaw logs --limit 500
```

22
docs/cli/memory.md
View File

@@ -1,11 +1,11 @@
---
summary: "CLI reference for `moltbot memory` (status/index/search)"
summary: "CLI reference for `openclaw memory` (status/index/search)"
read_when:
- You want to index or search semantic memory
- You’re debugging memory availability or indexing
---
# `moltbot memory`
# `openclaw memory`
Manage semantic memory indexing and search.
Provided by the active memory plugin (default: `memory-core`; set `plugins.slots.memory = "none"` to disable).
@@ -17,15 +17,15 @@ Related:
## Examples
```bash
moltbot memory status
moltbot memory status --deep
moltbot memory status --deep --index
moltbot memory status --deep --index --verbose
moltbot memory index
moltbot memory index --verbose
moltbot memory search "release checklist"
moltbot memory status --agent main
moltbot memory index --agent main --verbose
openclaw memory status
openclaw memory status --deep
openclaw memory status --deep --index
openclaw memory status --deep --index --verbose
openclaw memory index
openclaw memory index --verbose
openclaw memory search "release checklist"
openclaw memory status --agent main
openclaw memory index --agent main --verbose
```
## Options

22
docs/cli/message.md
View File

@@ -1,11 +1,11 @@
---
summary: "CLI reference for `moltbot message` (send + channel actions)"
summary: "CLI reference for `openclaw message` (send + channel actions)"
read_when:
- Adding or modifying message CLI actions
- Changing outbound channel behavior
---
# `moltbot message`
# `openclaw message`
Single outbound command for sending messages and channel actions
(Discord/Google Chat/Slack/Mattermost (plugin)/Telegram/WhatsApp/Signal/iMessage/MS Teams).
@@ -13,7 +13,7 @@ Single outbound command for sending messages and channel actions
## Usage
```
moltbot message <subcommand> [flags]
openclaw message <subcommand> [flags]
```
Channel selection:
@@ -34,7 +34,7 @@ Target formats (`--target`):
Name lookup:
- For supported providers (Discord/Slack/etc), channel names like `Help` or `#help` are resolved via the directory cache.
- On cache miss, Moltbot will attempt a live directory lookup when the provider supports it.
- On cache miss, OpenClaw will attempt a live directory lookup when the provider supports it.
## Common flags
@@ -181,13 +181,13 @@ Name lookup:
Send a Discord reply:
```
moltbot message send --channel discord \
openclaw message send --channel discord \
--target channel:123 --message "hi" --reply-to 456
```
Create a Discord poll:
```
moltbot message poll --channel discord \
openclaw message poll --channel discord \
--target channel:123 \
--poll-question "Snack?" \
--poll-option Pizza --poll-option Sushi \
@@ -196,13 +196,13 @@ moltbot message poll --channel discord \
Send a Teams proactive message:
```
moltbot message send --channel msteams \
openclaw message send --channel msteams \
--target conversation:19:abc@thread.tacv2 --message "hi"
```
Create a Teams poll:
```
moltbot message poll --channel msteams \
openclaw message poll --channel msteams \
--target conversation:19:abc@thread.tacv2 \
--poll-question "Lunch?" \
--poll-option Pizza --poll-option Sushi
@@ -210,19 +210,19 @@ moltbot message poll --channel msteams \
React in Slack:
```
moltbot message react --channel slack \
openclaw message react --channel slack \
--target C123 --message-id 456 --emoji "✅"
```
React in a Signal group:
```
moltbot message react --channel signal \
openclaw message react --channel signal \
--target signal:group:abc123 --message-id 1737630212345 \
--emoji "✅" --target-author-uuid 123e4567-e89b-12d3-a456-426614174000
```
Send Telegram inline buttons:
```
moltbot message send --channel telegram --target @mychat --message "Choose:" \
openclaw message send --channel telegram --target @mychat --message "Choose:" \
--buttons '[ [{"text":"Yes","callback_data":"cmd:yes"}], [{"text":"No","callback_data":"cmd:no"}] ]'
```

30
docs/cli/models.md
View File

@@ -1,11 +1,11 @@
---
summary: "CLI reference for `moltbot models` (status/list/set/scan, aliases, fallbacks, auth)"
summary: "CLI reference for `openclaw models` (status/list/set/scan, aliases, fallbacks, auth)"
read_when:
- You want to change default models or view provider auth status
- You want to scan available models/providers and debug auth profiles
---
# `moltbot models`
# `openclaw models`
Model discovery, scanning, and configuration (default model, fallbacks, auth profiles).
@@ -16,13 +16,13 @@ Related:
## Common commands
```bash
moltbot models status
moltbot models list
moltbot models set <model-or-alias>
moltbot models scan
openclaw models status
openclaw models list
openclaw models set <model-or-alias>
openclaw models scan
```
`moltbot models status` shows the resolved default/fallbacks plus an auth overview.
`openclaw models status` shows the resolved default/fallbacks plus an auth overview.
When provider usage snapshots are available, the OAuth/token status section includes
provider usage headers.
Add `--probe` to run live auth probes against each configured provider profile.
@@ -31,7 +31,7 @@ Probes are real requests (may consume tokens and trigger rate limits).
Notes:
- `models set <model-or-alias>` accepts `provider/model` or an alias.
- Model refs are parsed by splitting on the **first** `/`. If the model ID includes `/` (OpenRouter-style), include the provider prefix (example: `openrouter/moonshotai/kimi-k2`).
- If you omit the provider, Moltbot treats the input as an alias or a model for the **default provider** (only works when there is no `/` in the model ID).
- If you omit the provider, OpenClaw treats the input as an alias or a model for the **default provider** (only works when there is no `/` in the model ID).
### `models status`
Options:
@@ -48,20 +48,20 @@ Options:
## Aliases + fallbacks
```bash
moltbot models aliases list
moltbot models fallbacks list
openclaw models aliases list
openclaw models fallbacks list
```
## Auth profiles
```bash
moltbot models auth add
moltbot models auth login --provider <id>
moltbot models auth setup-token
moltbot models auth paste-token
openclaw models auth add
openclaw models auth login --provider <id>
openclaw models auth setup-token
openclaw models auth paste-token
```
`models auth login` runs a provider plugin’s auth flow (OAuth/API key). Use
`moltbot plugins list` to see which providers are installed.
`openclaw plugins list` to see which providers are installed.
Notes:
- `setup-token` prompts for a setup-token value (generate it with `claude setup-token` on any machine).

28
docs/cli/node.md
View File

@@ -1,11 +1,11 @@
---
summary: "CLI reference for `moltbot node` (headless node host)"
summary: "CLI reference for `openclaw node` (headless node host)"
read_when:
- Running the headless node host
- Pairing a non-macOS node for system.run
---
# `moltbot node`
# `openclaw node`
Run a **headless node host** that connects to the Gateway WebSocket and exposes
`system.run` / `system.which` on this machine.
@@ -44,7 +44,7 @@ Disable it on the node if needed:
## Run (foreground)
```bash
moltbot node run --host <gateway-host> --port 18789
openclaw node run --host <gateway-host> --port 18789
```
Options:
@@ -60,7 +60,7 @@ Options:
Install a headless node host as a user service.
```bash
moltbot node install --host <gateway-host> --port 18789
openclaw node install --host <gateway-host> --port 18789
```
Options:
@@ -76,13 +76,13 @@ Options:
Manage the service:
```bash
moltbot node status
moltbot node stop
moltbot node restart
moltbot node uninstall
openclaw node status
openclaw node stop
openclaw node restart
openclaw node uninstall
```
Use `moltbot node run` for a foreground node host (no service).
Use `openclaw node run` for a foreground node host (no service).
Service commands accept `--json` for machine-readable output.
@@ -92,17 +92,17 @@ The first connection creates a pending node pair request on the Gateway.
Approve it via:
```bash
moltbot nodes pending
moltbot nodes approve <requestId>
openclaw nodes pending
openclaw nodes approve <requestId>
```
The node host stores its node id, token, display name, and gateway connection info in
`~/.clawdbot/node.json`.
`~/.openclaw/node.json`.
## Exec approvals
`system.run` is gated by local exec approvals:
- `~/.clawdbot/exec-approvals.json`
- `~/.openclaw/exec-approvals.json`
- [Exec approvals](/tools/exec-approvals)
- `moltbot approvals --node <id|name|ip>` (edit from the Gateway)
- `openclaw approvals --node <id|name|ip>` (edit from the Gateway)

28
docs/cli/nodes.md
View File

@@ -1,11 +1,11 @@
---
summary: "CLI reference for `moltbot nodes` (list/status/approve/invoke, camera/canvas/screen)"
summary: "CLI reference for `openclaw nodes` (list/status/approve/invoke, camera/canvas/screen)"
read_when:
- You’re managing paired nodes (cameras, screen, canvas)
- You need to approve requests or invoke node commands
---
# `moltbot nodes`
# `openclaw nodes`
Manage paired nodes (devices) and invoke node capabilities.
@@ -20,14 +20,14 @@ Common options:
## Common commands
```bash
moltbot nodes list
moltbot nodes list --connected
moltbot nodes list --last-connected 24h
moltbot nodes pending
moltbot nodes approve <requestId>
moltbot nodes status
moltbot nodes status --connected
moltbot nodes status --last-connected 24h
openclaw nodes list
openclaw nodes list --connected
openclaw nodes list --last-connected 24h
openclaw nodes pending
openclaw nodes approve <requestId>
openclaw nodes status
openclaw nodes status --connected
openclaw nodes status --last-connected 24h
```
`nodes list` prints pending/paired tables. Paired rows include the most recent connect age (Last Connect).
@@ -37,10 +37,10 @@ filter to nodes that connected within a duration (e.g. `24h`, `7d`).
## Invoke / run
```bash
moltbot nodes invoke --node <id|name|ip> --command <command> --params <json>
moltbot nodes run --node <id|name|ip> <command...>
moltbot nodes run --raw "git status"
moltbot nodes run --agent main --node <id|name|ip> --raw "git status"
openclaw nodes invoke --node <id|name|ip> --command <command> --params <json>
openclaw nodes run --node <id|name|ip> <command...>
openclaw nodes run --raw "git status"
openclaw nodes run --agent main --node <id|name|ip> --raw "git status"
```
Invoke flags:

14
docs/cli/onboard.md
View File

@@ -1,10 +1,10 @@
---
summary: "CLI reference for `moltbot onboard` (interactive onboarding wizard)"
summary: "CLI reference for `openclaw onboard` (interactive onboarding wizard)"
read_when:
- You want guided setup for gateway, workspace, auth, channels, and skills
---
# `moltbot onboard`
# `openclaw onboard`
Interactive onboarding wizard (local or remote Gateway setup).
@@ -14,13 +14,13 @@ Related:
## Examples
```bash
moltbot onboard
moltbot onboard --flow quickstart
moltbot onboard --flow manual
moltbot onboard --mode remote --remote-url ws://gateway-host:18789
openclaw onboard
openclaw onboard --flow quickstart
openclaw onboard --flow manual
openclaw onboard --mode remote --remote-url ws://gateway-host:18789
```
Flow notes:
- `quickstart`: minimal prompts, auto-generates a gateway token.
- `manual`: full prompts for port/bind/auth (alias of `advanced`).
- Fastest first chat: `moltbot dashboard` (Control UI, no channel setup).
- Fastest first chat: `openclaw dashboard` (Control UI, no channel setup).

8
docs/cli/pairing.md
View File

@@ -1,10 +1,10 @@
---
summary: "CLI reference for `moltbot pairing` (approve/list pairing requests)"
summary: "CLI reference for `openclaw pairing` (approve/list pairing requests)"
read_when:
- You’re using pairing-mode DMs and need to approve senders
---
# `moltbot pairing`
# `openclaw pairing`
Approve or inspect DM pairing requests (for channels that support pairing).
@@ -14,7 +14,7 @@ Related:
## Commands
```bash
moltbot pairing list whatsapp
moltbot pairing approve whatsapp <code> --notify
openclaw pairing list whatsapp
openclaw pairing approve whatsapp <code> --notify
```

32
docs/cli/plugins.md
View File

@@ -1,11 +1,11 @@
---
summary: "CLI reference for `moltbot plugins` (list, install, enable/disable, doctor)"
summary: "CLI reference for `openclaw plugins` (list, install, enable/disable, doctor)"
read_when:
- You want to install or manage in-process Gateway plugins
- You want to debug plugin load failures
---
# `moltbot plugins`
# `openclaw plugins`
Manage Gateway plugins/extensions (loaded in-process).
@@ -17,26 +17,26 @@ Related:
## Commands
```bash
moltbot plugins list
moltbot plugins info <id>
moltbot plugins enable <id>
moltbot plugins disable <id>
moltbot plugins doctor
moltbot plugins update <id>
moltbot plugins update --all
openclaw plugins list
openclaw plugins info <id>
openclaw plugins enable <id>
openclaw plugins disable <id>
openclaw plugins doctor
openclaw plugins update <id>
openclaw plugins update --all
```
Bundled plugins ship with Moltbot but start disabled. Use `plugins enable` to
Bundled plugins ship with OpenClaw but start disabled. Use `plugins enable` to
activate them.
All plugins must ship a `moltbot.plugin.json` file with an inline JSON Schema
All plugins must ship a `openclaw.plugin.json` file with an inline JSON Schema
(`configSchema`, even if empty). Missing/invalid manifests or schemas prevent
the plugin from loading and fail config validation.
### Install
```bash
moltbot plugins install <path-or-spec>
openclaw plugins install <path-or-spec>
```
Security note: treat plugin installs like running code. Prefer pinned versions.
@@ -46,15 +46,15 @@ Supported archives: `.zip`, `.tgz`, `.tar.gz`, `.tar`.
Use `--link` to avoid copying a local directory (adds to `plugins.load.paths`):
```bash
moltbot plugins install -l ./my-plugin
openclaw plugins install -l ./my-plugin
```
### Update
```bash
moltbot plugins update <id>
moltbot plugins update --all
moltbot plugins update <id> --dry-run
openclaw plugins update <id>
openclaw plugins update --all
openclaw plugins update <id> --dry-run
```
Updates only apply to plugins installed from npm (tracked in `plugins.installs`).

10
docs/cli/reset.md
View File

@@ -1,17 +1,17 @@
---
summary: "CLI reference for `moltbot reset` (reset local state/config)"
summary: "CLI reference for `openclaw reset` (reset local state/config)"
read_when:
- You want to wipe local state while keeping the CLI installed
- You want a dry-run of what would be removed
---
# `moltbot reset`
# `openclaw reset`
Reset local config/state (keeps the CLI installed).
```bash
moltbot reset
moltbot reset --dry-run
moltbot reset --scope config+creds+sessions --yes --non-interactive
openclaw reset
openclaw reset --dry-run
openclaw reset --scope config+creds+sessions --yes --non-interactive
```

56
docs/cli/sandbox.md
View File

@@ -11,29 +11,29 @@ Manage Docker-based sandbox containers for isolated agent execution.
## Overview
Moltbot can run agents in isolated Docker containers for security. The `sandbox` commands help you manage these containers, especially after updates or configuration changes.
OpenClaw can run agents in isolated Docker containers for security. The `sandbox` commands help you manage these containers, especially after updates or configuration changes.
## Commands
### `moltbot sandbox explain`
### `openclaw sandbox explain`
Inspect the **effective** sandbox mode/scope/workspace access, sandbox tool policy, and elevated gates (with fix-it config key paths).
```bash
moltbot sandbox explain
moltbot sandbox explain --session agent:main:main
moltbot sandbox explain --agent work
moltbot sandbox explain --json
openclaw sandbox explain
openclaw sandbox explain --session agent:main:main
openclaw sandbox explain --agent work
openclaw sandbox explain --json
```
### `moltbot sandbox list`
### `openclaw sandbox list`
List all sandbox containers with their status and configuration.
```bash
moltbot sandbox list
moltbot sandbox list --browser # List only browser containers
moltbot sandbox list --json # JSON output
openclaw sandbox list
openclaw sandbox list --browser # List only browser containers
openclaw sandbox list --json # JSON output
```
**Output includes:**
@@ -43,16 +43,16 @@ moltbot sandbox list --json # JSON output
- Idle time (time since last use)
- Associated session/agent
### `moltbot sandbox recreate`
### `openclaw sandbox recreate`
Remove sandbox containers to force recreation with updated images/config.
```bash
moltbot sandbox recreate --all # Recreate all containers
moltbot sandbox recreate --session main # Specific session
moltbot sandbox recreate --agent mybot # Specific agent
moltbot sandbox recreate --browser # Only browser containers
moltbot sandbox recreate --all --force # Skip confirmation
openclaw sandbox recreate --all # Recreate all containers
openclaw sandbox recreate --session main # Specific session
openclaw sandbox recreate --agent mybot # Specific agent
openclaw sandbox recreate --browser # Only browser containers
openclaw sandbox recreate --all --force # Skip confirmation
```
**Options:**
@@ -70,14 +70,14 @@ moltbot sandbox recreate --all --force # Skip confirmation
```bash
# Pull new image
docker pull moltbot-sandbox:latest
docker tag moltbot-sandbox:latest moltbot-sandbox:bookworm-slim
docker pull openclaw-sandbox:latest
docker tag openclaw-sandbox:latest openclaw-sandbox:bookworm-slim
# Update config to use new image
# Edit config: agents.defaults.sandbox.docker.image (or agents.list[].sandbox.docker.image)
# Recreate containers
moltbot sandbox recreate --all
openclaw sandbox recreate --all
```
### After changing sandbox configuration
@@ -86,15 +86,15 @@ moltbot sandbox recreate --all
# Edit config: agents.defaults.sandbox.* (or agents.list[].sandbox.*)
# Recreate to apply new config
moltbot sandbox recreate --all
openclaw sandbox recreate --all
```
### After changing setupCommand
```bash
moltbot sandbox recreate --all
openclaw sandbox recreate --all
# or just one agent:
moltbot sandbox recreate --agent family
openclaw sandbox recreate --agent family
```
@@ -102,7 +102,7 @@ moltbot sandbox recreate --agent family
```bash
# Update only one agent's containers
moltbot sandbox recreate --agent alfred
openclaw sandbox recreate --agent alfred
```
## Why is this needed?
@@ -112,14 +112,14 @@ moltbot sandbox recreate --agent alfred
- Containers are only pruned after 24h of inactivity
- Regularly-used agents keep old containers running indefinitely
**Solution:** Use `moltbot sandbox recreate` to force removal of old containers. They'll be recreated automatically with current settings when next needed.
**Solution:** Use `openclaw sandbox recreate` to force removal of old containers. They'll be recreated automatically with current settings when next needed.
Tip: prefer `moltbot sandbox recreate` over manual `docker rm`. It uses the
Tip: prefer `openclaw sandbox recreate` over manual `docker rm`. It uses the
Gateway’s container naming and avoids mismatches when scope/session keys change.
## Configuration
Sandbox settings live in `~/.clawdbot/moltbot.json` under `agents.defaults.sandbox` (per-agent overrides go in `agents.list[].sandbox`):
Sandbox settings live in `~/.openclaw/openclaw.json` under `agents.defaults.sandbox` (per-agent overrides go in `agents.list[].sandbox`):
```jsonc
{
@@ -129,8 +129,8 @@ Sandbox settings live in `~/.clawdbot/moltbot.json` under `agents.defaults.sandb
"mode": "all", // off, non-main, all
"scope": "agent", // session, agent, shared
"docker": {
"image": "moltbot-sandbox:bookworm-slim",
"containerPrefix": "moltbot-sbx-"
"image": "openclaw-sandbox:bookworm-slim",
"containerPrefix": "openclaw-sbx-"
// ... more Docker options
},
"prune": {

10
docs/cli/security.md
View File

@@ -1,11 +1,11 @@
---
summary: "CLI reference for `moltbot security` (audit and fix common security footguns)"
summary: "CLI reference for `openclaw security` (audit and fix common security footguns)"
read_when:
- You want to run a quick security audit on config/state
- You want to apply safe “fix” suggestions (chmod, tighten defaults)
---
# `moltbot security`
# `openclaw security`
Security tools (audit + optional fixes).
@@ -15,9 +15,9 @@ Related:
## Audit
```bash
moltbot security audit
moltbot security audit --deep
moltbot security audit --fix
openclaw security audit
openclaw security audit --deep
openclaw security audit --fix
```
The audit warns when multiple DM senders share the main session and recommends `session.dmScope="per-channel-peer"` (or `per-account-channel-peer` for multi-account channels) for shared inboxes.

10
docs/cli/sessions.md
View File

@@ -1,16 +1,16 @@
---
summary: "CLI reference for `moltbot sessions` (list stored sessions + usage)"
summary: "CLI reference for `openclaw sessions` (list stored sessions + usage)"
read_when:
- You want to list stored sessions and see recent activity
---
# `moltbot sessions`
# `openclaw sessions`
List stored conversation sessions.
```bash
moltbot sessions
moltbot sessions --active 120
moltbot sessions --json
openclaw sessions
openclaw sessions --active 120
openclaw sessions --json
```

12
docs/cli/setup.md
View File

@@ -1,13 +1,13 @@
---
summary: "CLI reference for `moltbot setup` (initialize config + workspace)"
summary: "CLI reference for `openclaw setup` (initialize config + workspace)"
read_when:
- You’re doing first-run setup without the full onboarding wizard
- You want to set the default workspace path
---
# `moltbot setup`
# `openclaw setup`
Initialize `~/.clawdbot/moltbot.json` and the agent workspace.
Initialize `~/.openclaw/openclaw.json` and the agent workspace.
Related:
- Getting started: [Getting started](/start/getting-started)
@@ -16,13 +16,13 @@ Related:
## Examples
```bash
moltbot setup
moltbot setup --workspace ~/clawd
openclaw setup
openclaw setup --workspace ~/.openclaw/workspace
```
To run the wizard via setup:
```bash
moltbot setup --wizard
openclaw setup --wizard
```

12
docs/cli/skills.md
View File

@@ -1,11 +1,11 @@
---
summary: "CLI reference for `moltbot skills` (list/info/check) and skill eligibility"
summary: "CLI reference for `openclaw skills` (list/info/check) and skill eligibility"
read_when:
- You want to see which skills are available and ready to run
- You want to debug missing binaries/env/config for skills
---
# `moltbot skills`
# `openclaw skills`
Inspect skills (bundled + workspace + managed overrides) and see what’s eligible vs missing requirements.
@@ -17,9 +17,9 @@ Related:
## Commands
```bash
moltbot skills list
moltbot skills list --eligible
moltbot skills info <name>
moltbot skills check
openclaw skills list
openclaw skills list --eligible
openclaw skills info <name>
openclaw skills check
```

14
docs/cli/status.md
View File

@@ -1,19 +1,19 @@
---
summary: "CLI reference for `moltbot status` (diagnostics, probes, usage snapshots)"
summary: "CLI reference for `openclaw status` (diagnostics, probes, usage snapshots)"
read_when:
- You want a quick diagnosis of channel health + recent session recipients
- You want a pasteable “all” status for debugging
---
# `moltbot status`
# `openclaw status`
Diagnostics for channels + sessions.
```bash
moltbot status
moltbot status --all
moltbot status --deep
moltbot status --usage
openclaw status
openclaw status --all
openclaw status --deep
openclaw status --usage
```
Notes:
@@ -21,4 +21,4 @@ Notes:
- Output includes per-agent session stores when multiple agents are configured.
- Overview includes Gateway + node host service install/runtime status when available.
- Overview includes update channel + git SHA (for source checkouts).
- Update info surfaces in the Overview; if an update is available, status prints a hint to run `moltbot update` (see [Updating](/install/updating)).
- Update info surfaces in the Overview; if an update is available, status prints a hint to run `openclaw update` (see [Updating](/install/updating)).

12
docs/cli/system.md
View File

@@ -1,12 +1,12 @@
---
summary: "CLI reference for `moltbot system` (system events, heartbeat, presence)"
summary: "CLI reference for `openclaw system` (system events, heartbeat, presence)"
read_when:
- You want to enqueue a system event without creating a cron job
- You need to enable or disable heartbeats
- You want to inspect system presence entries
---
# `moltbot system`
# `openclaw system`
System-level helpers for the Gateway: enqueue system events, control heartbeats,
and view presence.
@@ -14,10 +14,10 @@ and view presence.
## Common commands
```bash
moltbot system event --text "Check for urgent follow-ups" --mode now
moltbot system heartbeat enable
moltbot system heartbeat last
moltbot system presence
openclaw system event --text "Check for urgent follow-ups" --mode now
openclaw system heartbeat enable
openclaw system heartbeat last
openclaw system presence
```
## `system event`

10
docs/cli/tui.md
View File

@@ -1,11 +1,11 @@
---
summary: "CLI reference for `moltbot tui` (terminal UI connected to the Gateway)"
summary: "CLI reference for `openclaw tui` (terminal UI connected to the Gateway)"
read_when:
- You want a terminal UI for the Gateway (remote-friendly)
- You want to pass url/token/session from scripts
---
# `moltbot tui`
# `openclaw tui`
Open the terminal UI connected to the Gateway.
@@ -15,8 +15,8 @@ Related:
## Examples
```bash
moltbot tui
moltbot tui --url ws://127.0.0.1:18789 --token <token>
moltbot tui --session main --deliver
openclaw tui
openclaw tui --url ws://127.0.0.1:18789 --token <token>
openclaw tui --session main --deliver
```

10
docs/cli/uninstall.md
View File

@@ -1,17 +1,17 @@
---
summary: "CLI reference for `moltbot uninstall` (remove gateway service + local data)"
summary: "CLI reference for `openclaw uninstall` (remove gateway service + local data)"
read_when:
- You want to remove the gateway service and/or local state
- You want a dry-run first
---
# `moltbot uninstall`
# `openclaw uninstall`
Uninstall the gateway service + local data (CLI remains).
```bash
moltbot uninstall
moltbot uninstall --all --yes
moltbot uninstall --dry-run
openclaw uninstall
openclaw uninstall --all --yes
openclaw uninstall --dry-run
```

40
docs/cli/update.md
View File

@@ -1,28 +1,28 @@
---
summary: "CLI reference for `moltbot update` (safe-ish source update + gateway auto-restart)"
summary: "CLI reference for `openclaw update` (safe-ish source update + gateway auto-restart)"
read_when:
- You want to update a source checkout safely
- You need to understand `--update` shorthand behavior
---
# `moltbot update`
# `openclaw update`
Safely update Moltbot and switch between stable/beta/dev channels.
Safely update OpenClaw and switch between stable/beta/dev channels.
If you installed via **npm/pnpm** (global install, no git metadata), updates happen via the package manager flow in [Updating](/install/updating).
## Usage
```bash
moltbot update
moltbot update status
moltbot update wizard
moltbot update --channel beta
moltbot update --channel dev
moltbot update --tag beta
moltbot update --no-restart
moltbot update --json
moltbot --update
openclaw update
openclaw update status
openclaw update wizard
openclaw update --channel beta
openclaw update --channel dev
openclaw update --tag beta
openclaw update --no-restart
openclaw update --json
openclaw --update
```
## Options
@@ -40,9 +40,9 @@ Note: downgrades require confirmation because older versions can break configura
Show the active update channel + git tag/branch/SHA (for source checkouts), plus update availability.
```bash
moltbot update status
moltbot update status --json
moltbot update status --timeout 10
openclaw update status
openclaw update status --json
openclaw update status --timeout 10
```
Options:
@@ -57,10 +57,10 @@ offers to create one.
## What it does
When you switch channels explicitly (`--channel ...`), Moltbot also keeps the
When you switch channels explicitly (`--channel ...`), OpenClaw also keeps the
install method aligned:
- `dev` → ensures a git checkout (default: `~/moltbot`, override with `CLAWDBOT_GIT_DIR`),
- `dev` → ensures a git checkout (default: `~/openclaw`, override with `OPENCLAW_GIT_DIR`),
updates it, and installs the global CLI from that checkout.
- `stable`/`beta` → installs from npm using the matching dist-tag.
@@ -81,16 +81,16 @@ High-level:
5. Rebases onto the selected commit (dev only).
6. Installs deps (pnpm preferred; npm fallback).
7. Builds + builds the Control UI.
8. Runs `moltbot doctor` as the final “safe update” check.
8. Runs `openclaw doctor` as the final “safe update” check.
9. Syncs plugins to the active channel (dev uses bundled extensions; stable/beta uses npm) and updates npm-installed plugins.
## `--update` shorthand
`moltbot --update` rewrites to `moltbot update` (useful for shells and launcher scripts).
`openclaw --update` rewrites to `openclaw update` (useful for shells and launcher scripts).
## See also
- `moltbot doctor` (offers to run update first on git checkouts)
- `openclaw doctor` (offers to run update first on git checkouts)
- [Development channels](/install/development-channels)
- [Updating](/install/updating)
- [CLI reference](/cli)

18
docs/cli/voicecall.md
View File

@@ -1,11 +1,11 @@
---
summary: "CLI reference for `moltbot voicecall` (voice-call plugin command surface)"
summary: "CLI reference for `openclaw voicecall` (voice-call plugin command surface)"
read_when:
- You use the voice-call plugin and want the CLI entry points
- You want quick examples for `voicecall call|continue|status|tail|expose`
---
# `moltbot voicecall`
# `openclaw voicecall`
`voicecall` is a plugin-provided command. It only appears if the voice-call plugin is installed and enabled.
@@ -15,18 +15,18 @@ Primary doc:
## Common commands
```bash
moltbot voicecall status --call-id <id>
moltbot voicecall call --to "+15555550123" --message "Hello" --mode notify
moltbot voicecall continue --call-id <id> --message "Any questions?"
moltbot voicecall end --call-id <id>
openclaw voicecall status --call-id <id>
openclaw voicecall call --to "+15555550123" --message "Hello" --mode notify
openclaw voicecall continue --call-id <id> --message "Any questions?"
openclaw voicecall end --call-id <id>
```
## Exposing webhooks (Tailscale)
```bash
moltbot voicecall expose --mode serve
moltbot voicecall expose --mode funnel
moltbot voicecall unexpose
openclaw voicecall expose --mode serve
openclaw voicecall expose --mode funnel
openclaw voicecall unexpose
```
Security note: only expose the webhook endpoint to networks you trust. Prefer Tailscale Serve over Funnel when possible.

10
docs/cli/webhooks.md
View File

@@ -1,11 +1,11 @@
---
summary: "CLI reference for `moltbot webhooks` (webhook helpers + Gmail Pub/Sub)"
summary: "CLI reference for `openclaw webhooks` (webhook helpers + Gmail Pub/Sub)"
read_when:
- You want to wire Gmail Pub/Sub events into Moltbot
- You want to wire Gmail Pub/Sub events into OpenClaw
- You want webhook helper commands
---
# `moltbot webhooks`
# `openclaw webhooks`
Webhook helpers and integrations (Gmail Pub/Sub, webhook helpers).
@@ -16,8 +16,8 @@ Related:
## Gmail
```bash
moltbot webhooks gmail setup --account you@example.com
moltbot webhooks gmail run
openclaw webhooks gmail setup --account you@example.com
openclaw webhooks gmail run
```
See [Gmail Pub/Sub documentation](/automation/gmail-pubsub) for details.

10
docs/concepts/agent-loop.md
View File

@@ -3,13 +3,13 @@ summary: "Agent loop lifecycle, streams, and wait semantics"
read_when:
- You need an exact walkthrough of the agent loop or lifecycle events
---
# Agent Loop (Moltbot)
# Agent Loop (OpenClaw)
An agentic loop is the full “real” run of an agent: intake → context assembly → model inference →
tool execution → streaming replies → persistence. It’s the authoritative path that turns a message
into actions and a final reply, while keeping session state consistent.
In Moltbot, a loop is a single, serialized run per session that emits lifecycle and stream events
In OpenClaw, a loop is a single, serialized run per session that emits lifecycle and stream events
as the model thinks, calls tools, and streams output. This doc explains how that authentic loop is
wired end-to-end.
@@ -30,7 +30,7 @@ wired end-to-end.
- subscribes to pi events and streams assistant/tool deltas
- enforces timeout -> aborts run if exceeded
- returns payloads + usage metadata
4) `subscribeEmbeddedPiSession` bridges pi-agent-core events to Moltbot `agent` stream:
4) `subscribeEmbeddedPiSession` bridges pi-agent-core events to OpenClaw `agent` stream:
- tool events => `stream: "tool"`
- assistant deltas => `stream: "assistant"`
- lifecycle events => `stream: "lifecycle"` (`phase: "start" | "end" | "error"`)
@@ -51,12 +51,12 @@ wired end-to-end.
- A session write lock is acquired; `SessionManager` is opened and prepared before streaming.
## Prompt assembly + system prompt
- System prompt is built from Moltbot’s base prompt, skills prompt, bootstrap context, and per-run overrides.
- System prompt is built from OpenClaw’s base prompt, skills prompt, bootstrap context, and per-run overrides.
- Model-specific limits and compaction reserve tokens are enforced.
- See [System prompt](/concepts/system-prompt) for what the model sees.
## Hook points (where you can intercept)
Moltbot has two hook systems:
OpenClaw has two hook systems:
- **Internal hooks** (Gateway hooks): event-driven scripts for commands and lifecycle events.
- **Plugin hooks**: extension points inside the agent/tool lifecycle and gateway pipeline.

54
docs/concepts/agent-workspace.md
View File

@@ -9,7 +9,7 @@ read_when:
The workspace is the agent's home. It is the only working directory used for
file tools and for workspace context. Keep it private and treat it as memory.
This is separate from `~/.clawdbot/`, which stores config, credentials, and
This is separate from `~/.openclaw/`, which stores config, credentials, and
sessions.
**Important:** the workspace is the **default cwd**, not a hard sandbox. Tools
@@ -17,24 +17,24 @@ resolve relative paths against the workspace, but absolute paths can still reach
elsewhere on the host unless sandboxing is enabled. If you need isolation, use
[`agents.defaults.sandbox`](/gateway/sandboxing) (and/or per‑agent sandbox config).
When sandboxing is enabled and `workspaceAccess` is not `"rw"`, tools operate
inside a sandbox workspace under `~/.clawdbot/sandboxes`, not your host workspace.
inside a sandbox workspace under `~/.openclaw/sandboxes`, not your host workspace.
## Default location
- Default: `~/clawd`
- If `CLAWDBOT_PROFILE` is set and not `"default"`, the default becomes
`~/clawd-<profile>`.
- Override in `~/.clawdbot/moltbot.json`:
- Default: `~/.openclaw/workspace`
- If `OPENCLAW_PROFILE` is set and not `"default"`, the default becomes
`~/.openclaw/workspace-<profile>`.
- Override in `~/.openclaw/openclaw.json`:
```json5
{
agent: {
workspace: "~/clawd"
workspace: "~/.openclaw/workspace"
}
}
```
`moltbot onboard`, `moltbot configure`, or `moltbot setup` will create the
`openclaw onboard`, `openclaw configure`, or `openclaw setup` will create the
workspace and seed the bootstrap files if they are missing.
If you already manage the workspace files yourself, you can disable bootstrap
@@ -46,20 +46,20 @@ file creation:
## Extra workspace folders
Older installs may have created `~/moltbot`. Keeping multiple workspace
Older installs may have created `~/openclaw`. Keeping multiple workspace
directories around can cause confusing auth or state drift, because only one
workspace is active at a time.
**Recommendation:** keep a single active workspace. If you no longer use the
extra folders, archive or move them to Trash (for example `trash ~/moltbot`).
extra folders, archive or move them to Trash (for example `trash ~/openclaw`).
If you intentionally keep multiple workspaces, make sure
`agents.defaults.workspace` points to the active one.
`moltbot doctor` warns when it detects extra workspace directories.
`openclaw doctor` warns when it detects extra workspace directories.
## Workspace file map (what each file means)
These are the standard files Moltbot expects inside the workspace:
These are the standard files OpenClaw expects inside the workspace:
- `AGENTS.md`
- Operating instructions for the agent and how it should use memory.
@@ -112,20 +112,20 @@ See [Memory](/concepts/memory) for the workflow and automatic memory flush.
- `canvas/` (optional)
- Canvas UI files for node displays (for example `canvas/index.html`).
If any bootstrap file is missing, Moltbot injects a "missing file" marker into
If any bootstrap file is missing, OpenClaw injects a "missing file" marker into
the session and continues. Large bootstrap files are truncated when injected;
adjust the limit with `agents.defaults.bootstrapMaxChars` (default: 20000).
`moltbot setup` can recreate missing defaults without overwriting existing
`openclaw setup` can recreate missing defaults without overwriting existing
files.
## What is NOT in the workspace
These live under `~/.clawdbot/` and should NOT be committed to the workspace repo:
These live under `~/.openclaw/` and should NOT be committed to the workspace repo:
- `~/.clawdbot/moltbot.json` (config)
- `~/.clawdbot/credentials/` (OAuth tokens, API keys)
- `~/.clawdbot/agents/<agentId>/sessions/` (session transcripts + metadata)
- `~/.clawdbot/skills/` (managed skills)
- `~/.openclaw/openclaw.json` (config)
- `~/.openclaw/credentials/` (OAuth tokens, API keys)
- `~/.openclaw/agents/<agentId>/sessions/` (session transcripts + metadata)
- `~/.openclaw/skills/` (managed skills)
If you need to migrate sessions or config, copy them separately and keep them
out of version control.
@@ -144,7 +144,7 @@ If git is installed, brand-new workspaces are initialized automatically. If this
workspace is not already a repo, run:
```bash
cd ~/clawd
cd ~/.openclaw/workspace
git init
git add AGENTS.md SOUL.md TOOLS.md IDENTITY.md USER.md HEARTBEAT.md memory/
git commit -m "Add agent workspace"
@@ -169,7 +169,7 @@ Option B: GitHub CLI (`gh`)
```bash
gh auth login
gh repo create clawd-workspace --private --source . --remote origin --push
gh repo create openclaw-workspace --private --source . --remote origin --push
```
Option C: GitLab web UI
@@ -199,11 +199,11 @@ git push
Even in a private repo, avoid storing secrets in the workspace:
- API keys, OAuth tokens, passwords, or private credentials.
- Anything under `~/.clawdbot/`.
- Anything under `~/.openclaw/`.
- Raw dumps of chats or sensitive attachments.
If you must store sensitive references, use placeholders and keep the real
secret elsewhere (password manager, environment variables, or `~/.clawdbot/`).
secret elsewhere (password manager, environment variables, or `~/.openclaw/`).
Suggested `.gitignore` starter:
@@ -217,10 +217,10 @@ Suggested `.gitignore` starter:
## Moving the workspace to a new machine
1. Clone the repo to the desired path (default `~/clawd`).
2. Set `agents.defaults.workspace` to that path in `~/.clawdbot/moltbot.json`.
3. Run `moltbot setup --workspace <path>` to seed any missing files.
4. If you need sessions, copy `~/.clawdbot/agents/<agentId>/sessions/` from the
1. Clone the repo to the desired path (default `~/.openclaw/workspace`).
2. Set `agents.defaults.workspace` to that path in `~/.openclaw/openclaw.json`.
3. Run `openclaw setup --workspace <path>` to seed any missing files.
4. If you need sessions, copy `~/.openclaw/agents/<agentId>/sessions/` from the
old machine separately.
## Advanced notes

24
docs/concepts/agent.md
View File

@@ -5,13 +5,13 @@ read_when:
---
# Agent Runtime 🤖
Moltbot runs a single embedded agent runtime derived from **p-mono**.
OpenClaw runs a single embedded agent runtime derived from **p-mono**.
## Workspace (required)
Moltbot uses a single agent workspace directory (`agents.defaults.workspace`) as the agent’s **only** working directory (`cwd`) for tools and context.
OpenClaw uses a single agent workspace directory (`agents.defaults.workspace`) as the agent’s **only** working directory (`cwd`) for tools and context.
Recommended: use `moltbot setup` to create `~/.clawdbot/moltbot.json` if missing and initialize the workspace files.
Recommended: use `openclaw setup` to create `~/.openclaw/openclaw.json` if missing and initialize the workspace files.
Full workspace layout + backup guide: [Agent workspace](/concepts/agent-workspace)
@@ -21,7 +21,7 @@ per-session workspaces under `agents.defaults.sandbox.workspaceRoot` (see
## Bootstrap files (injected)
Inside `agents.defaults.workspace`, Moltbot expects these user-editable files:
Inside `agents.defaults.workspace`, OpenClaw expects these user-editable files:
- `AGENTS.md` — operating instructions + “memory”
- `SOUL.md` — persona, boundaries, tone
- `TOOLS.md` — user-maintained tool notes (e.g. `imsg`, `sag`, conventions)
@@ -29,11 +29,11 @@ Inside `agents.defaults.workspace`, Moltbot expects these user-editable files:
- `IDENTITY.md` — agent name/vibe/emoji
- `USER.md` — user profile + preferred address
On the first turn of a new session, Moltbot injects the contents of these files directly into the agent context.
On the first turn of a new session, OpenClaw injects the contents of these files directly into the agent context.
Blank files are skipped. Large files are trimmed and truncated with a marker so prompts stay lean (read the file for full content).
If a file is missing, Moltbot injects a single “missing file” marker line (and `moltbot setup` will create a safe default template).
If a file is missing, OpenClaw injects a single “missing file” marker line (and `openclaw setup` will create a safe default template).
`BOOTSTRAP.md` is only created for a **brand new workspace** (no other bootstrap files present). If you delete it after completing the ritual, it should not be recreated on later restarts.
@@ -52,16 +52,16 @@ guidance for how *you* want them used.
## Skills
Moltbot loads skills from three locations (workspace wins on name conflict):
OpenClaw loads skills from three locations (workspace wins on name conflict):
- Bundled (shipped with the install)
- Managed/local: `~/.clawdbot/skills`
- Managed/local: `~/.openclaw/skills`
- Workspace: `<workspace>/skills`
Skills can be gated by config/env (see `skills` in [Gateway configuration](/gateway/configuration)).
## p-mono integration
Moltbot reuses pieces of the p-mono codebase (models/tools), but **session management, discovery, and tool wiring are Moltbot-owned**.
OpenClaw reuses pieces of the p-mono codebase (models/tools), but **session management, discovery, and tool wiring are OpenClaw-owned**.
- No p-coding agent runtime.
- No `~/.pi/agent` or `<workspace>/.pi` settings are consulted.
@@ -69,9 +69,9 @@ Moltbot reuses pieces of the p-mono codebase (models/tools), but **session manag
## Sessions
Session transcripts are stored as JSONL at:
- `~/.clawdbot/agents/<agentId>/sessions/<SessionId>.jsonl`
- `~/.openclaw/agents/<agentId>/sessions/<SessionId>.jsonl`
The session ID is stable and chosen by Moltbot.
The session ID is stable and chosen by OpenClaw.
Legacy Pi/Tau session folders are **not** read.
## Steering while streaming
@@ -104,7 +104,7 @@ Model refs in config (for example `agents.defaults.model` and `agents.defaults.m
- Use `provider/model` when configuring models.
- If the model ID itself contains `/` (OpenRouter-style), include the provider prefix (example: `openrouter/moonshotai/kimi-k2`).
- If you omit the provider, Moltbot treats the input as an alias or a model for the **default provider** (only works when there is no `/` in the model ID).
- If you omit the provider, OpenClaw treats the input as an alias or a model for the **default provider** (only works when there is no `/` in the model ID).
## Configuration (minimal)

4
docs/concepts/architecture.md
View File

@@ -72,7 +72,7 @@ Client Gateway
- After handshake:
- Requests: `{type:"req", id, method, params}` → `{type:"res", id, ok, payload|error}`
- Events: `{type:"event", event, payload, seq?, stateVersion?}`
- If `CLAWDBOT_GATEWAY_TOKEN` (or `--token`) is set, `connect.params.auth.token`
- If `OPENCLAW_GATEWAY_TOKEN` (or `--token`) is set, `connect.params.auth.token`
must match or the socket closes.
- Idempotency keys are required for side‑effecting methods (`send`, `agent`) to
safely retry; the server keeps a short‑lived dedupe cache.
@@ -111,7 +111,7 @@ Details: [Gateway protocol](/gateway/protocol), [Pairing](/start/pairing),
## Operations snapshot
- Start: `moltbot gateway` (foreground, logs to stdout).
- Start: `openclaw gateway` (foreground, logs to stdout).
- Health: `health` over WS (also included in `hello-ok`).
- Supervision: launchd/systemd for auto‑restart.

10
docs/concepts/channel-routing.md
View File

@@ -6,7 +6,7 @@ read_when:
# Channels & routing
Moltbot routes replies **back to the channel where a message came from**. The
OpenClaw routes replies **back to the channel where a message came from**. The
model does not choose a channel; routing is deterministic and controlled by the
host configuration.
@@ -53,7 +53,7 @@ The matched agent determines which workspace and session store are used.
## Broadcast groups (run multiple agents)
Broadcast groups let you run **multiple agents** for the same peer **when Moltbot would normally reply** (for example: in WhatsApp groups, after mention/activation gating).
Broadcast groups let you run **multiple agents** for the same peer **when OpenClaw would normally reply** (for example: in WhatsApp groups, after mention/activation gating).
Config:
@@ -80,7 +80,7 @@ Example:
{
agents: {
list: [
{ id: "support", name: "Support", workspace: "~/clawd-support" }
{ id: "support", name: "Support", workspace: "~/.openclaw/workspace-support" }
]
},
bindings: [
@@ -92,9 +92,9 @@ Example:
## Session storage
Session stores live under the state directory (default `~/.clawdbot`):
Session stores live under the state directory (default `~/.openclaw`):
- `~/.clawdbot/agents/<agentId>/sessions/sessions.json`
- `~/.openclaw/agents/<agentId>/sessions/sessions.json`
- JSONL transcripts live alongside the store
You can override the store path via `session.store` and `{agentId}` templating.

10
docs/concepts/compaction.md
View File

@@ -1,12 +1,12 @@
---
summary: "Context window + compaction: how Moltbot keeps sessions under model limits"
summary: "Context window + compaction: how OpenClaw keeps sessions under model limits"
read_when:
- You want to understand auto-compaction and /compact
- You are debugging long sessions hitting context limits
---
# Context Window & Compaction
Every model has a **context window** (max tokens it can see). Long-running chats accumulate messages and tool results; once the window is tight, Moltbot **compacts** older history to stay within limits.
Every model has a **context window** (max tokens it can see). Long-running chats accumulate messages and tool results; once the window is tight, OpenClaw **compacts** older history to stay within limits.
## What compaction is
Compaction **summarizes older conversation** into a compact summary entry and keeps recent messages intact. The summary is stored in the session history, so future requests use:
@@ -19,13 +19,13 @@ Compaction **persists** in the session’s JSONL history.
See [Compaction config & modes](/concepts/compaction) for the `agents.defaults.compaction` settings.
## Auto-compaction (default on)
When a session nears or exceeds the model’s context window, Moltbot triggers auto-compaction and may retry the original request using the compacted context.
When a session nears or exceeds the model’s context window, OpenClaw triggers auto-compaction and may retry the original request using the compacted context.
You’ll see:
- `🧹 Auto-compaction complete` in verbose mode
- `/status` showing `🧹 Compactions: <count>`
Before compaction, Moltbot can run a **silent memory flush** turn to store
Before compaction, OpenClaw can run a **silent memory flush** turn to store
durable notes to disk. See [Memory](/concepts/memory) for details and config.
## Manual compaction
@@ -35,7 +35,7 @@ Use `/compact` (optionally with instructions) to force a compaction pass:
```
## Context window source
Context window is model-specific. Moltbot uses the model definition from the configured provider catalog to determine limits.
Context window is model-specific. OpenClaw uses the model definition from the configured provider catalog to determine limits.
## Compaction vs pruning
- **Compaction**: summarises and **persists** in JSONL.

12
docs/concepts/context.md
View File

@@ -1,16 +1,16 @@
---
summary: "Context: what the model sees, how it is built, and how to inspect it"
read_when:
- You want to understand what “context” means in Moltbot
- You want to understand what “context” means in OpenClaw
- You are debugging why the model “knows” something (or forgot it)
- You want to reduce context overhead (/context, /status, /compact)
---
# Context
“Context” is **everything Moltbot sends to the model for a run**. It is bounded by the model’s **context window** (token limit).
“Context” is **everything OpenClaw sends to the model for a run**. It is bounded by the model’s **context window** (token limit).
Beginner mental model:
- **System prompt** (Moltbot-built): rules, tools, skills list, time/runtime, and injected workspace files.
- **System prompt** (OpenClaw-built): rules, tools, skills list, time/runtime, and injected workspace files.
- **Conversation history**: your messages + the assistant’s messages for this session.
- **Tool calls/results + attachments**: command output, file reads, images/audio, etc.
@@ -83,9 +83,9 @@ Everything the model receives counts, including:
- Compaction summaries and pruning artifacts.
- Provider “wrappers” or hidden headers (not visible, still counted).
## How Moltbot builds the system prompt
## How OpenClaw builds the system prompt
The system prompt is **Moltbot-owned** and rebuilt each run. It includes:
The system prompt is **OpenClaw-owned** and rebuilt each run. It includes:
- Tool list + short descriptions.
- Skills list (metadata only; see below).
- Workspace location.
@@ -97,7 +97,7 @@ Full breakdown: [System Prompt](/concepts/system-prompt).
## Injected workspace files (Project Context)
By default, Moltbot injects a fixed set of workspace files (if present):
By default, OpenClaw injects a fixed set of workspace files (if present):
- `AGENTS.md`
- `SOUL.md`
- `TOOLS.md`

14
docs/concepts/group-messages.md
View File

@@ -19,7 +19,7 @@ Note: `agents.list[].groupChat.mentionPatterns` is now used by Telegram/Discord/
- Group system prompt: on the first turn of a group session (and whenever `/activation` changes the mode) we inject a short blurb into the system prompt like `You are replying inside the WhatsApp group "<subject>". Group members: Alice (+44...), Bob (+43...), … Activation: trigger-only … Address the specific sender noted in the message context.` If metadata isn’t available we still tell the agent it’s a group chat.
## Config example (WhatsApp)
Add a `groupChat` block to `~/.clawdbot/moltbot.json` so display-name pings work even when WhatsApp strips the visual `@` in the text body:
Add a `groupChat` block to `~/.openclaw/openclaw.json` so display-name pings work even when WhatsApp strips the visual `@` in the text body:
```json5
{
@@ -37,7 +37,7 @@ Add a `groupChat` block to `~/.clawdbot/moltbot.json` so display-name pings work
groupChat: {
historyLimit: 50,
mentionPatterns: [
"@?moltbot",
"@?openclaw",
"\\+?15555550123"
]
}
@@ -48,7 +48,7 @@ Add a `groupChat` block to `~/.clawdbot/moltbot.json` so display-name pings work
```
Notes:
- The regexes are case-insensitive; they cover a display-name ping like `@moltbot` and the raw number with or without `+`/spaces.
- The regexes are case-insensitive; they cover a display-name ping like `@openclaw` and the raw number with or without `+`/spaces.
- WhatsApp still sends canonical mentions via `mentionedJids` when someone taps the contact, so the number fallback is rarely needed but is a useful safety net.
### Activation command (owner-only)
@@ -60,19 +60,19 @@ Use the group chat command:
Only the owner number (from `channels.whatsapp.allowFrom`, or the bot’s own E.164 when unset) can change this. Send `/status` as a standalone message in the group to see the current activation mode.
## How to use
1) Add your WhatsApp account (the one running Moltbot) to the group.
2) Say `@moltbot …` (or include the number). Only allowlisted senders can trigger it unless you set `groupPolicy: "open"`.
1) Add your WhatsApp account (the one running OpenClaw) to the group.
2) Say `@openclaw …` (or include the number). Only allowlisted senders can trigger it unless you set `groupPolicy: "open"`.
3) The agent prompt will include recent group context plus the trailing `[from: …]` marker so it can address the right person.
4) Session-level directives (`/verbose on`, `/think high`, `/new` or `/reset`, `/compact`) apply only to that group’s session; send them as standalone messages so they register. Your personal DM session remains independent.
## Testing / verification
- Manual smoke:
- Send an `@clawd` ping in the group and confirm a reply that references the sender name.
- Send an `@openclaw` ping in the group and confirm a reply that references the sender name.
- Send a second ping and verify the history block is included then cleared on the next turn.
- Check gateway logs (run with `--verbose`) to see `inbound web message` entries showing `from: <groupJid>` and the `[from: …]` suffix.
## Known considerations
- Heartbeats are intentionally skipped for groups to avoid noisy broadcasts.
- Echo suppression uses the combined batch string; if you send identical text twice without mentions, only the first will get a response.
- Session store entries will appear as `agent:<agentId>:whatsapp:group:<jid>` in the session store (`~/.clawdbot/agents/<agentId>/sessions/sessions.json` by default); a missing entry just means the group hasn’t triggered a run yet.
- Session store entries will appear as `agent:<agentId>:whatsapp:group:<jid>` in the session store (`~/.openclaw/agents/<agentId>/sessions/sessions.json` by default); a missing entry just means the group hasn’t triggered a run yet.
- Typing indicators in groups follow `agents.defaults.typingMode` (default: `message` when unmentioned).

10
docs/concepts/groups.md
View File

@@ -5,17 +5,17 @@ read_when:
---
# Groups
Moltbot treats group chats consistently across surfaces: WhatsApp, Telegram, Discord, Slack, Signal, iMessage, Microsoft Teams.
OpenClaw treats group chats consistently across surfaces: WhatsApp, Telegram, Discord, Slack, Signal, iMessage, Microsoft Teams.
## Beginner intro (2 minutes)
Moltbot “lives” on your own messaging accounts. There is no separate WhatsApp bot user.
If **you** are in a group, Moltbot can see that group and respond there.
OpenClaw “lives” on your own messaging accounts. There is no separate WhatsApp bot user.
If **you** are in a group, OpenClaw can see that group and respond there.
Default behavior:
- Groups are restricted (`groupPolicy: "allowlist"`).
- Replies require a mention unless you explicitly disable mention gating.
Translation: allowlisted senders can trigger Moltbot by mentioning it.
Translation: allowlisted senders can trigger OpenClaw by mentioning it.
> TL;DR
> - **DM access** is controlled by `*.allowFrom`.
@@ -215,7 +215,7 @@ Replying to a bot message counts as an implicit mention (when the channel suppor
{
id: "main",
groupChat: {
mentionPatterns: ["@clawd", "moltbot", "\\+15555550123"],
mentionPatterns: ["@openclaw", "openclaw", "\\+15555550123"],
historyLimit: 50
}
}

6
docs/concepts/markdown-formatting.md
View File

@@ -7,7 +7,7 @@ read_when:
---
# Markdown formatting
Moltbot formats outbound Markdown by converting it into a shared intermediate
OpenClaw formats outbound Markdown by converting it into a shared intermediate
representation (IR) before rendering channel-specific output. The IR keeps the
source text intact while carrying style/link spans so chunking and rendering can
stay consistent across channels.
@@ -39,7 +39,7 @@ stay consistent across channels.
Input Markdown:
```markdown
Hello **world** — see [docs](https://docs.molt.bot).
Hello **world** — see [docs](https://docs.openclaw.ai).
```
IR (schematic):
@@ -51,7 +51,7 @@ IR (schematic):
{ "start": 6, "end": 11, "style": "bold" }
],
"links": [
{ "start": 19, "end": 23, "href": "https://docs.molt.bot" }
{ "start": 19, "end": 23, "href": "https://docs.openclaw.ai" }
]
}
```

30
docs/concepts/memory.md
View File

@@ -1,12 +1,12 @@
---
summary: "How Moltbot memory works (workspace files + automatic memory flush)"
summary: "How OpenClaw memory works (workspace files + automatic memory flush)"
read_when:
- You want the memory file layout and workflow
- You want to tune the automatic pre-compaction memory flush
---
# Memory
Moltbot memory is **plain Markdown in the agent workspace**. The files are the
OpenClaw memory is **plain Markdown in the agent workspace**. The files are the
source of truth; the model only "remembers" what gets written to disk.
Memory search tools are provided by the active memory plugin (default:
@@ -24,7 +24,7 @@ The default workspace layout uses two memory layers:
- **Only load in the main, private session** (never in group contexts).
These files live under the workspace (`agents.defaults.workspace`, default
`~/clawd`). See [Agent workspace](/concepts/agent-workspace) for the full layout.
`~/.openclaw/workspace`). See [Agent workspace](/concepts/agent-workspace) for the full layout.
## When to write memory
@@ -36,7 +36,7 @@ These files live under the workspace (`agents.defaults.workspace`, default
## Automatic memory flush (pre-compaction ping)
When a session is **close to auto-compaction**, Moltbot triggers a **silent,
When a session is **close to auto-compaction**, OpenClaw triggers a **silent,
agentic turn** that reminds the model to write durable memory **before** the
context is compacted. The default prompts explicitly say the model *may reply*,
but usually `NO_REPLY` is the correct response so the user never sees this turn.
@@ -75,14 +75,14 @@ For the full compaction lifecycle, see
## Vector memory search
Moltbot can build a small vector index over `MEMORY.md` and `memory/*.md` (plus
OpenClaw can build a small vector index over `MEMORY.md` and `memory/*.md` (plus
any extra directories or files you opt in) so semantic queries can find related
notes even when wording differs.
Defaults:
- Enabled by default.
- Watches memory files for changes (debounced).
- Uses remote embeddings by default. If `memorySearch.provider` is not set, Moltbot auto-selects:
- Uses remote embeddings by default. If `memorySearch.provider` is not set, OpenClaw auto-selects:
1. `local` if a `memorySearch.local.modelPath` is configured and the file exists.
2. `openai` if an OpenAI key can be resolved.
3. `gemini` if a Gemini key can be resolved.
@@ -90,7 +90,7 @@ Defaults:
- Local mode uses node-llama-cpp and may require `pnpm approve-builds`.
- Uses sqlite-vec (when available) to accelerate vector search inside SQLite.
Remote embeddings **require** an API key for the embedding provider. Moltbot
Remote embeddings **require** an API key for the embedding provider. OpenClaw
resolves keys from auth profiles, `models.providers.*.apiKey`, or environment
variables. Codex OAuth only covers chat/completions and does **not** satisfy
embeddings for memory search. For Gemini, use `GEMINI_API_KEY` or
@@ -217,17 +217,17 @@ Local mode:
### What gets indexed (and when)
- File type: Markdown only (`MEMORY.md`, `memory/**/*.md`, plus any `.md` files under `memorySearch.extraPaths`).
- Index storage: per-agent SQLite at `~/.clawdbot/memory/<agentId>.sqlite` (configurable via `agents.defaults.memorySearch.store.path`, supports `{agentId}` token).
- Index storage: per-agent SQLite at `~/.openclaw/memory/<agentId>.sqlite` (configurable via `agents.defaults.memorySearch.store.path`, supports `{agentId}` token).
- Freshness: watcher on `MEMORY.md`, `memory/`, and `memorySearch.extraPaths` marks the index dirty (debounce 1.5s). Sync is scheduled on session start, on search, or on an interval and runs asynchronously. Session transcripts use delta thresholds to trigger background sync.
- Reindex triggers: the index stores the embedding **provider/model + endpoint fingerprint + chunking params**. If any of those change, Moltbot automatically resets and reindexes the entire store.
- Reindex triggers: the index stores the embedding **provider/model + endpoint fingerprint + chunking params**. If any of those change, OpenClaw automatically resets and reindexes the entire store.
### Hybrid search (BM25 + vector)
When enabled, Moltbot combines:
When enabled, OpenClaw combines:
- **Vector similarity** (semantic match, wording can differ)
- **BM25 keyword relevance** (exact tokens like IDs, env vars, code symbols)
If full-text search is unavailable on your platform, Moltbot falls back to vector-only search.
If full-text search is unavailable on your platform, OpenClaw falls back to vector-only search.
#### Why hybrid?
@@ -288,7 +288,7 @@ agents: {
### Embedding cache
Moltbot can cache **chunk embeddings** in SQLite so reindexing and frequent updates (especially session transcripts) don't re-embed unchanged text.
OpenClaw can cache **chunk embeddings** in SQLite so reindexing and frequent updates (especially session transcripts) don't re-embed unchanged text.
Config:
@@ -327,7 +327,7 @@ Notes:
- `memory_search` never blocks on indexing; results can be slightly stale until background sync finishes.
- Results still include snippets only; `memory_get` remains limited to memory files.
- Session indexing is isolated per agent (only that agent’s session logs are indexed).
- Session logs live on disk (`~/.clawdbot/agents/<agentId>/sessions/*.jsonl`). Any process/user with filesystem access can read them, so treat disk access as the trust boundary. For stricter isolation, run agents under separate OS users or hosts.
- Session logs live on disk (`~/.openclaw/agents/<agentId>/sessions/*.jsonl`). Any process/user with filesystem access can read them, so treat disk access as the trust boundary. For stricter isolation, run agents under separate OS users or hosts.
Delta thresholds (defaults shown):
@@ -348,7 +348,7 @@ agents: {
### SQLite vector acceleration (sqlite-vec)
When the sqlite-vec extension is available, Moltbot stores embeddings in a
When the sqlite-vec extension is available, OpenClaw stores embeddings in a
SQLite virtual table (`vec0`) and performs vector distance queries in the
database. This keeps search fast without loading every embedding into JS.
@@ -372,7 +372,7 @@ agents: {
Notes:
- `enabled` defaults to true; when disabled, search falls back to in-process
cosine similarity over stored embeddings.
- If the sqlite-vec extension is missing or fails to load, Moltbot logs the
- If the sqlite-vec extension is missing or fails to load, OpenClaw logs the
error and continues with the JS fallback (no vector table).
- `extensionPath` overrides the bundled sqlite-vec path (useful for custom builds
or non-standard install locations).

8
docs/concepts/messages.md
View File

@@ -7,7 +7,7 @@ read_when:
---
# Messages
This page ties together how Moltbot handles inbound messages, sessions, queueing,
This page ties together how OpenClaw handles inbound messages, sessions, queueing,
streaming, and reasoning visibility.
## Message flow (high level)
@@ -29,7 +29,7 @@ See [Configuration](/gateway/configuration) for full schema.
## Inbound dedupe
Channels can redeliver the same message after reconnects. Moltbot keeps a
Channels can redeliver the same message after reconnects. OpenClaw keeps a
short-lived cache keyed by channel/account/peer/session/message id so duplicate
deliveries do not trigger another agent run.
@@ -75,7 +75,7 @@ Details: [Session management](/concepts/session).
## Inbound bodies and history context
Moltbot separates the **prompt body** from the **command body**:
OpenClaw separates the **prompt body** from the **command body**:
- `Body`: prompt text sent to the agent. This may include channel envelopes and
optional history wrappers.
- `CommandBody`: raw user text for directive/command parsing.
@@ -127,7 +127,7 @@ Details: [Streaming + chunking](/concepts/streaming).
## Reasoning visibility and tokens
Moltbot can expose or hide model reasoning:
OpenClaw can expose or hide model reasoning:
- `/reasoning on|off|stream` controls visibility.
- Reasoning content still counts toward token usage when produced by the model.
- Telegram supports reasoning stream into the draft bubble.

28
docs/concepts/model-failover.md
View File

@@ -1,5 +1,5 @@
---
summary: "How Moltbot rotates auth profiles and falls back across models"
summary: "How OpenClaw rotates auth profiles and falls back across models"
read_when:
- Diagnosing auth profile rotation, cooldowns, or model fallback behavior
- Updating failover rules for auth profiles or models
@@ -7,7 +7,7 @@ read_when:
# Model failover
Moltbot handles failures in two stages:
OpenClaw handles failures in two stages:
1) **Auth profile rotation** within the current provider.
2) **Model fallback** to the next model in `agents.defaults.model.fallbacks`.
@@ -15,11 +15,11 @@ This doc explains the runtime rules and the data that backs them.
## Auth storage (keys + OAuth)
Moltbot uses **auth profiles** for both API keys and OAuth tokens.
OpenClaw uses **auth profiles** for both API keys and OAuth tokens.
- Secrets live in `~/.clawdbot/agents/<agentId>/agent/auth-profiles.json` (legacy: `~/.clawdbot/agent/auth-profiles.json`).
- Secrets live in `~/.openclaw/agents/<agentId>/agent/auth-profiles.json` (legacy: `~/.openclaw/agent/auth-profiles.json`).
- Config `auth.profiles` / `auth.order` are **metadata + routing only** (no secrets).
- Legacy import-only OAuth file: `~/.clawdbot/credentials/oauth.json` (imported into `auth-profiles.json` on first use).
- Legacy import-only OAuth file: `~/.openclaw/credentials/oauth.json` (imported into `auth-profiles.json` on first use).
More detail: [/concepts/oauth](/concepts/oauth)
@@ -33,24 +33,24 @@ OAuth logins create distinct profiles so multiple accounts can coexist.
- Default: `provider:default` when no email is available.
- OAuth with email: `provider:<email>` (for example `google-antigravity:user@gmail.com`).
Profiles live in `~/.clawdbot/agents/<agentId>/agent/auth-profiles.json` under `profiles`.
Profiles live in `~/.openclaw/agents/<agentId>/agent/auth-profiles.json` under `profiles`.
## Rotation order
When a provider has multiple profiles, Moltbot chooses an order like this:
When a provider has multiple profiles, OpenClaw chooses an order like this:
1) **Explicit config**: `auth.order[provider]` (if set).
2) **Configured profiles**: `auth.profiles` filtered by provider.
3) **Stored profiles**: entries in `auth-profiles.json` for the provider.
If no explicit order is configured, Moltbot uses a round‑robin order:
If no explicit order is configured, OpenClaw uses a round‑robin order:
- **Primary key:** profile type (**OAuth before API keys**).
- **Secondary key:** `usageStats.lastUsed` (oldest first, within each type).
- **Cooldown/disabled profiles** are moved to the end, ordered by soonest expiry.
### Session stickiness (cache-friendly)
Moltbot **pins the chosen auth profile per session** to keep provider caches warm.
OpenClaw **pins the chosen auth profile per session** to keep provider caches warm.
It does **not** rotate on every request. The pinned profile is reused until:
- the session is reset (`/new` / `/reset`)
- a compaction completes (compaction count increments)
@@ -60,9 +60,9 @@ Manual selection via `/model …@<profileId>` sets a **user override** for that
and is not auto‑rotated until a new session starts.
Auto‑pinned profiles (selected by the session router) are treated as a **preference**:
they are tried first, but Moltbot may rotate to another profile on rate limits/timeouts.
they are tried first, but OpenClaw may rotate to another profile on rate limits/timeouts.
User‑pinned profiles stay locked to that profile; if it fails and model fallbacks
are configured, Moltbot moves to the next model instead of switching profiles.
are configured, OpenClaw moves to the next model instead of switching profiles.
### Why OAuth can “look lost”
@@ -73,7 +73,7 @@ If you have both an OAuth profile and an API key profile for the same provider,
## Cooldowns
When a profile fails due to auth/rate‑limit errors (or a timeout that looks
like rate limiting), Moltbot marks it in cooldown and moves to the next profile.
like rate limiting), OpenClaw marks it in cooldown and moves to the next profile.
Format/invalid‑request errors (for example Cloud Code Assist tool call ID
validation failures) are treated as failover‑worthy and use the same cooldowns.
@@ -99,7 +99,7 @@ State is stored in `auth-profiles.json` under `usageStats`:
## Billing disables
Billing/credit failures (for example “insufficient credits” / “credit balance too low”) are treated as failover‑worthy, but they’re usually not transient. Instead of a short cooldown, Moltbot marks the profile as **disabled** (with a longer backoff) and rotates to the next profile/provider.
Billing/credit failures (for example “insufficient credits” / “credit balance too low”) are treated as failover‑worthy, but they’re usually not transient. Instead of a short cooldown, OpenClaw marks the profile as **disabled** (with a longer backoff) and rotates to the next profile/provider.
State is stored in `auth-profiles.json`:
@@ -120,7 +120,7 @@ Defaults:
## Model fallback
If all profiles for a provider fail, Moltbot moves to the next model in
If all profiles for a provider fail, OpenClaw moves to the next model in
`agents.defaults.model.fallbacks`. This applies to auth failures, rate limits, and
timeouts that exhausted profile rotation (other errors do not advance fallback).

42
docs/concepts/model-providers.md
View File

@@ -13,11 +13,11 @@ For model selection rules, see [/concepts/models](/concepts/models).
- Model refs use `provider/model` (example: `opencode/claude-opus-4-5`).
- If you set `agents.defaults.models`, it becomes the allowlist.
- CLI helpers: `moltbot onboard`, `moltbot models list`, `moltbot models set <provider/model>`.
- CLI helpers: `openclaw onboard`, `openclaw models list`, `openclaw models set <provider/model>`.
## Built-in providers (pi-ai catalog)
Moltbot ships with the pi‑ai catalog. These providers require **no**
OpenClaw ships with the pi‑ai catalog. These providers require **no**
`models.providers` config; just set auth + pick a model.
### OpenAI
@@ -25,7 +25,7 @@ Moltbot ships with the pi‑ai catalog. These providers require **no**
- Provider: `openai`
- Auth: `OPENAI_API_KEY`
- Example model: `openai/gpt-5.2`
- CLI: `moltbot onboard --auth-choice openai-api-key`
- CLI: `openclaw onboard --auth-choice openai-api-key`
```json5
{
@@ -38,7 +38,7 @@ Moltbot ships with the pi‑ai catalog. These providers require **no**
- Provider: `anthropic`
- Auth: `ANTHROPIC_API_KEY` or `claude setup-token`
- Example model: `anthropic/claude-opus-4-5`
- CLI: `moltbot onboard --auth-choice token` (paste setup-token) or `moltbot models auth paste-token --provider anthropic`
- CLI: `openclaw onboard --auth-choice token` (paste setup-token) or `openclaw models auth paste-token --provider anthropic`
```json5
{
@@ -51,7 +51,7 @@ Moltbot ships with the pi‑ai catalog. These providers require **no**
- Provider: `openai-codex`
- Auth: OAuth (ChatGPT)
- Example model: `openai-codex/gpt-5.2`
- CLI: `moltbot onboard --auth-choice openai-codex` or `moltbot models auth login --provider openai-codex`
- CLI: `openclaw onboard --auth-choice openai-codex` or `openclaw models auth login --provider openai-codex`
```json5
{
@@ -64,7 +64,7 @@ Moltbot ships with the pi‑ai catalog. These providers require **no**
- Provider: `opencode`
- Auth: `OPENCODE_API_KEY` (or `OPENCODE_ZEN_API_KEY`)
- Example model: `opencode/claude-opus-4-5`
- CLI: `moltbot onboard --auth-choice opencode-zen`
- CLI: `openclaw onboard --auth-choice opencode-zen`
```json5
{
@@ -77,19 +77,19 @@ Moltbot ships with the pi‑ai catalog. These providers require **no**
- Provider: `google`
- Auth: `GEMINI_API_KEY`
- Example model: `google/gemini-3-pro-preview`
- CLI: `moltbot onboard --auth-choice gemini-api-key`
- CLI: `openclaw onboard --auth-choice gemini-api-key`
### Google Vertex / Antigravity / Gemini CLI
- Providers: `google-vertex`, `google-antigravity`, `google-gemini-cli`
- Auth: Vertex uses gcloud ADC; Antigravity/Gemini CLI use their respective auth flows
- Antigravity OAuth is shipped as a bundled plugin (`google-antigravity-auth`, disabled by default).
- Enable: `moltbot plugins enable google-antigravity-auth`
- Login: `moltbot models auth login --provider google-antigravity --set-default`
- Enable: `openclaw plugins enable google-antigravity-auth`
- Login: `openclaw models auth login --provider google-antigravity --set-default`
- Gemini CLI OAuth is shipped as a bundled plugin (`google-gemini-cli-auth`, disabled by default).
- Enable: `moltbot plugins enable google-gemini-cli-auth`
- Login: `moltbot models auth login --provider google-gemini-cli --set-default`
- Note: you do **not** paste a client id or secret into `moltbot.json`. The CLI login flow stores
- Enable: `openclaw plugins enable google-gemini-cli-auth`
- Login: `openclaw models auth login --provider google-gemini-cli --set-default`
- Note: you do **not** paste a client id or secret into `openclaw.json`. The CLI login flow stores
tokens in auth profiles on the gateway host.
### Z.AI (GLM)
@@ -97,7 +97,7 @@ Moltbot ships with the pi‑ai catalog. These providers require **no**
- Provider: `zai`
- Auth: `ZAI_API_KEY`
- Example model: `zai/glm-4.7`
- CLI: `moltbot onboard --auth-choice zai-api-key`
- CLI: `openclaw onboard --auth-choice zai-api-key`
- Aliases: `z.ai/*` and `z-ai/*` normalize to `zai/*`
### Vercel AI Gateway
@@ -105,7 +105,7 @@ Moltbot ships with the pi‑ai catalog. These providers require **no**
- Provider: `vercel-ai-gateway`
- Auth: `AI_GATEWAY_API_KEY`
- Example model: `vercel-ai-gateway/anthropic/claude-opus-4.5`
- CLI: `moltbot onboard --auth-choice ai-gateway-api-key`
- CLI: `openclaw onboard --auth-choice ai-gateway-api-key`
### Other built-in providers
@@ -192,8 +192,8 @@ Qwen provides OAuth access to Qwen Coder + Vision via a device-code flow.
Enable the bundled plugin, then log in:
```bash
moltbot plugins enable qwen-portal-auth
moltbot models auth login --provider qwen-portal --set-default
openclaw plugins enable qwen-portal-auth
openclaw models auth login --provider qwen-portal --set-default
```
Model refs:
@@ -209,7 +209,7 @@ Synthetic provides Anthropic-compatible models behind the `synthetic` provider:
- Provider: `synthetic`
- Auth: `SYNTHETIC_API_KEY`
- Example model: `synthetic/hf:MiniMaxAI/MiniMax-M2.1`
- CLI: `moltbot onboard --auth-choice synthetic-api-key`
- CLI: `openclaw onboard --auth-choice synthetic-api-key`
```json5
{
@@ -300,7 +300,7 @@ Example (OpenAI‑compatible):
Notes:
- For custom providers, `reasoning`, `input`, `cost`, `contextWindow`, and `maxTokens` are optional.
When omitted, Moltbot defaults to:
When omitted, OpenClaw defaults to:
- `reasoning: false`
- `input: ["text"]`
- `cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 }`
@@ -311,9 +311,9 @@ Notes:
## CLI examples
```bash
moltbot onboard --auth-choice opencode-zen
moltbot models set opencode/claude-opus-4-5
moltbot models list
openclaw onboard --auth-choice opencode-zen
openclaw models set opencode/claude-opus-4-5
openclaw models list
```
See also: [/gateway/configuration](/gateway/configuration) for full configuration examples.

48
docs/concepts/models.md
View File

@@ -13,7 +13,7 @@ Quick provider overview + examples: [/concepts/model-providers](/concepts/model-
## How model selection works
Moltbot selects models in this order:
OpenClaw selects models in this order:
1) **Primary** model (`agents.defaults.model.primary` or `agents.defaults.model`).
2) **Fallbacks** in `agents.defaults.model.fallbacks` (in order).
@@ -21,7 +21,7 @@ Moltbot selects models in this order:
next model.
Related:
- `agents.defaults.models` is the allowlist/catalog of models Moltbot can use (plus aliases).
- `agents.defaults.models` is the allowlist/catalog of models OpenClaw can use (plus aliases).
- `agents.defaults.imageModel` is used **only when** the primary model can’t accept images.
- Per-agent defaults can override `agents.defaults.model` via `agents.list[].model` plus bindings (see [/concepts/multi-agent](/concepts/multi-agent)).
@@ -35,7 +35,7 @@ Related:
If you don’t want to hand-edit config, run the onboarding wizard:
```bash
moltbot onboard
openclaw onboard
```
It can set up model + auth for common providers, including **OpenAI Code (Codex)
@@ -59,7 +59,7 @@ Provider configuration examples (including OpenCode Zen) live in
If `agents.defaults.models` is set, it becomes the **allowlist** for `/model` and for
session overrides. When a user selects a model that isn’t in that allowlist,
Moltbot returns:
OpenClaw returns:
```
Model "provider/model" is not allowed. Use /model to list available models.
@@ -104,34 +104,34 @@ Notes:
- `/model status` is the detailed view (auth candidates and, when configured, provider endpoint `baseUrl` + `api` mode).
- Model refs are parsed by splitting on the **first** `/`. Use `provider/model` when typing `/model <ref>`.
- If the model ID itself contains `/` (OpenRouter-style), you must include the provider prefix (example: `/model openrouter/moonshotai/kimi-k2`).
- If you omit the provider, Moltbot treats the input as an alias or a model for the **default provider** (only works when there is no `/` in the model ID).
- If you omit the provider, OpenClaw treats the input as an alias or a model for the **default provider** (only works when there is no `/` in the model ID).
Full command behavior/config: [Slash commands](/tools/slash-commands).
## CLI commands
```bash
moltbot models list
moltbot models status
moltbot models set <provider/model>
moltbot models set-image <provider/model>
openclaw models list
openclaw models status
openclaw models set <provider/model>
openclaw models set-image <provider/model>
moltbot models aliases list
moltbot models aliases add <alias> <provider/model>
moltbot models aliases remove <alias>
openclaw models aliases list
openclaw models aliases add <alias> <provider/model>
openclaw models aliases remove <alias>
moltbot models fallbacks list
moltbot models fallbacks add <provider/model>
moltbot models fallbacks remove <provider/model>
moltbot models fallbacks clear
openclaw models fallbacks list
openclaw models fallbacks add <provider/model>
openclaw models fallbacks remove <provider/model>
openclaw models fallbacks clear
moltbot models image-fallbacks list
moltbot models image-fallbacks add <provider/model>
moltbot models image-fallbacks remove <provider/model>
moltbot models image-fallbacks clear
openclaw models image-fallbacks list
openclaw models image-fallbacks add <provider/model>
openclaw models image-fallbacks remove <provider/model>
openclaw models image-fallbacks clear
```
`moltbot models` (no subcommand) is a shortcut for `models status`.
`openclaw models` (no subcommand) is a shortcut for `models status`.
### `models list`
@@ -159,12 +159,12 @@ Preferred Anthropic auth is the Claude Code CLI setup-token (run anywhere; paste
```bash
claude setup-token
moltbot models status
openclaw models status
```
## Scanning (OpenRouter free models)
`moltbot models scan` inspects OpenRouter’s **free model catalog** and can
`openclaw models scan` inspects OpenRouter’s **free model catalog** and can
optionally probe models for tool and image support.
Key flags:
@@ -198,5 +198,5 @@ mode, pass `--yes` to accept defaults.
## Models registry (`models.json`)
Custom providers in `models.providers` are written into `models.json` under the
agent directory (default `~/.clawdbot/agents/<agentId>/models.json`). This file
agent directory (default `~/.openclaw/agents/<agentId>/models.json`). This file
is merged by default unless `models.mode` is set to `replace`.

62
docs/concepts/multi-agent.md
View File

@@ -15,12 +15,12 @@ An **agent** is a fully scoped brain with its own:
- **Workspace** (files, AGENTS.md/SOUL.md/USER.md, local notes, persona rules).
- **State directory** (`agentDir`) for auth profiles, model registry, and per-agent config.
- **Session store** (chat history + routing state) under `~/.clawdbot/agents/<agentId>/sessions`.
- **Session store** (chat history + routing state) under `~/.openclaw/agents/<agentId>/sessions`.
Auth profiles are **per-agent**. Each agent reads from its own:
```
~/.clawdbot/agents/<agentId>/agent/auth-profiles.json
~/.openclaw/agents/<agentId>/agent/auth-profiles.json
```
Main agent credentials are **not** shared automatically. Never reuse `agentDir`
@@ -28,7 +28,7 @@ across agents (it causes auth/session collisions). If you want to share creds,
copy `auth-profiles.json` into the other agent's `agentDir`.
Skills are per-agent via each workspace’s `skills/` folder, with shared skills
available from `~/.clawdbot/skills`. See [Skills: per-agent vs shared](/tools/skills#per-agent-vs-shared-skills).
available from `~/.openclaw/skills`. See [Skills: per-agent vs shared](/tools/skills#per-agent-vs-shared-skills).
The Gateway can host **one agent** (default) or **many agents** side-by-side.
@@ -39,27 +39,27 @@ reach other host locations unless sandboxing is enabled. See
## Paths (quick map)
- Config: `~/.clawdbot/moltbot.json` (or `CLAWDBOT_CONFIG_PATH`)
- State dir: `~/.clawdbot` (or `CLAWDBOT_STATE_DIR`)
- Workspace: `~/clawd` (or `~/clawd-<agentId>`)
- Agent dir: `~/.clawdbot/agents/<agentId>/agent` (or `agents.list[].agentDir`)
- Sessions: `~/.clawdbot/agents/<agentId>/sessions`
- Config: `~/.openclaw/openclaw.json` (or `OPENCLAW_CONFIG_PATH`)
- State dir: `~/.openclaw` (or `OPENCLAW_STATE_DIR`)
- Workspace: `~/.openclaw/workspace` (or `~/.openclaw/workspace-<agentId>`)
- Agent dir: `~/.openclaw/agents/<agentId>/agent` (or `agents.list[].agentDir`)
- Sessions: `~/.openclaw/agents/<agentId>/sessions`
### Single-agent mode (default)
If you do nothing, Moltbot runs a single agent:
If you do nothing, OpenClaw runs a single agent:
- `agentId` defaults to **`main`**.
- Sessions are keyed as `agent:main:<mainKey>`.
- Workspace defaults to `~/clawd` (or `~/clawd-<profile>` when `CLAWDBOT_PROFILE` is set).
- State defaults to `~/.clawdbot/agents/main/agent`.
- Workspace defaults to `~/.openclaw/workspace` (or `~/.openclaw/workspace-<profile>` when `OPENCLAW_PROFILE` is set).
- State defaults to `~/.openclaw/agents/main/agent`.
## Agent helper
Use the agent wizard to add a new isolated agent:
```bash
moltbot agents add work
openclaw agents add work
```
Then add `bindings` (or let the wizard do it) to route inbound messages.
@@ -67,7 +67,7 @@ Then add `bindings` (or let the wizard do it) to route inbound messages.
Verify with:
```bash
moltbot agents list --bindings
openclaw agents list --bindings
```
## Multiple agents = multiple people, multiple personalities
@@ -92,8 +92,8 @@ Example:
{
agents: {
list: [
{ id: "alex", workspace: "~/clawd-alex" },
{ id: "mia", workspace: "~/clawd-mia" }
{ id: "alex", workspace: "~/.openclaw/workspace-alex" },
{ id: "mia", workspace: "~/.openclaw/workspace-mia" }
]
},
bindings: [
@@ -139,7 +139,7 @@ multiple phone numbers without mixing sessions.
## Example: two WhatsApps → two agents
`~/.clawdbot/moltbot.json` (JSON5):
`~/.openclaw/openclaw.json` (JSON5):
```js
{
@@ -149,14 +149,14 @@ multiple phone numbers without mixing sessions.
id: "home",
default: true,
name: "Home",
workspace: "~/clawd-home",
agentDir: "~/.clawdbot/agents/home/agent",
workspace: "~/.openclaw/workspace-home",
agentDir: "~/.openclaw/agents/home/agent",
},
{
id: "work",
name: "Work",
workspace: "~/clawd-work",
agentDir: "~/.clawdbot/agents/work/agent",
workspace: "~/.openclaw/workspace-work",
agentDir: "~/.openclaw/agents/work/agent",
},
],
},
@@ -189,12 +189,12 @@ multiple phone numbers without mixing sessions.
whatsapp: {
accounts: {
personal: {
// Optional override. Default: ~/.clawdbot/credentials/whatsapp/personal
// authDir: "~/.clawdbot/credentials/whatsapp/personal",
// Optional override. Default: ~/.openclaw/credentials/whatsapp/personal
// authDir: "~/.openclaw/credentials/whatsapp/personal",
},
biz: {
// Optional override. Default: ~/.clawdbot/credentials/whatsapp/biz
// authDir: "~/.clawdbot/credentials/whatsapp/biz",
// Optional override. Default: ~/.openclaw/credentials/whatsapp/biz
// authDir: "~/.openclaw/credentials/whatsapp/biz",
},
},
},
@@ -213,13 +213,13 @@ Split by channel: route WhatsApp to a fast everyday agent and Telegram to an Opu
{
id: "chat",
name: "Everyday",
workspace: "~/clawd-chat",
workspace: "~/.openclaw/workspace-chat",
model: "anthropic/claude-sonnet-4-5"
},
{
id: "opus",
name: "Deep Work",
workspace: "~/clawd-opus",
workspace: "~/.openclaw/workspace-opus",
model: "anthropic/claude-opus-4-5"
}
]
@@ -243,8 +243,8 @@ Keep WhatsApp on the fast agent, but route one DM to Opus:
{
agents: {
list: [
{ id: "chat", name: "Everyday", workspace: "~/clawd-chat", model: "anthropic/claude-sonnet-4-5" },
{ id: "opus", name: "Deep Work", workspace: "~/clawd-opus", model: "anthropic/claude-opus-4-5" }
{ id: "chat", name: "Everyday", workspace: "~/.openclaw/workspace-chat", model: "anthropic/claude-sonnet-4-5" },
{ id: "opus", name: "Deep Work", workspace: "~/.openclaw/workspace-opus", model: "anthropic/claude-opus-4-5" }
]
},
bindings: [
@@ -268,7 +268,7 @@ and a tighter tool policy:
{
id: "family",
name: "Family",
workspace: "~/clawd-family",
workspace: "~/.openclaw/workspace-family",
identity: { name: "Family Bot" },
groupChat: {
mentionPatterns: ["@family", "@familybot", "@Family Bot"]
@@ -312,7 +312,7 @@ Starting with v2026.1.6, each agent can have its own sandbox and tool restrictio
list: [
{
id: "personal",
workspace: "~/clawd-personal",
workspace: "~/.openclaw/workspace-personal",
sandbox: {
mode: "off", // No sandbox for personal agent
},
@@ -320,7 +320,7 @@ Starting with v2026.1.6, each agent can have its own sandbox and tool restrictio
},
{
id: "family",
workspace: "~/clawd-family",
workspace: "~/.openclaw/workspace-family",
sandbox: {
mode: "all", // Always sandboxed
scope: "agent", // One container per agent

44
docs/concepts/oauth.md
View File

@@ -1,24 +1,24 @@
---
summary: "OAuth in Moltbot: token exchange, storage, and multi-account patterns"
summary: "OAuth in OpenClaw: token exchange, storage, and multi-account patterns"
read_when:
- You want to understand Moltbot OAuth end-to-end
- You want to understand OpenClaw OAuth end-to-end
- You hit token invalidation / logout issues
- You want setup-token or OAuth auth flows
- You want multiple accounts or profile routing
---
# OAuth
Moltbot supports “subscription auth” via OAuth for providers that offer it (notably **OpenAI Codex (ChatGPT OAuth)**). For Anthropic subscriptions, use the **setup-token** flow. This page explains:
OpenClaw supports “subscription auth” via OAuth for providers that offer it (notably **OpenAI Codex (ChatGPT OAuth)**). For Anthropic subscriptions, use the **setup-token** flow. This page explains:
- how the OAuth **token exchange** works (PKCE)
- where tokens are **stored** (and why)
- how to handle **multiple accounts** (profiles + per-session overrides)
Moltbot also supports **provider plugins** that ship their own OAuth or API‑key
OpenClaw also supports **provider plugins** that ship their own OAuth or API‑key
flows. Run them via:
```bash
moltbot models auth login --provider <id>
openclaw models auth login --provider <id>
```
## The token sink (why it exists)
@@ -26,9 +26,9 @@ moltbot models auth login --provider <id>
OAuth providers commonly mint a **new refresh token** during login/refresh flows. Some providers (or OAuth clients) can invalidate older refresh tokens when a new one is issued for the same user/app.
Practical symptom:
- you log in via Moltbot *and* via Claude Code / Codex CLI → one of them randomly gets “logged out” later
- you log in via OpenClaw *and* via Claude Code / Codex CLI → one of them randomly gets “logged out” later
To reduce that, Moltbot treats `auth-profiles.json` as a **token sink**:
To reduce that, OpenClaw treats `auth-profiles.json` as a **token sink**:
- the runtime reads credentials from **one place**
- we can keep multiple profiles and route them deterministically
@@ -36,47 +36,47 @@ To reduce that, Moltbot treats `auth-profiles.json` as a **token sink**:
Secrets are stored **per-agent**:
- Auth profiles (OAuth + API keys): `~/.clawdbot/agents/<agentId>/agent/auth-profiles.json`
- Runtime cache (managed automatically; don’t edit): `~/.clawdbot/agents/<agentId>/agent/auth.json`
- Auth profiles (OAuth + API keys): `~/.openclaw/agents/<agentId>/agent/auth-profiles.json`
- Runtime cache (managed automatically; don’t edit): `~/.openclaw/agents/<agentId>/agent/auth.json`
Legacy import-only file (still supported, but not the main store):
- `~/.clawdbot/credentials/oauth.json` (imported into `auth-profiles.json` on first use)
- `~/.openclaw/credentials/oauth.json` (imported into `auth-profiles.json` on first use)
All of the above also respect `$CLAWDBOT_STATE_DIR` (state dir override). Full reference: [/gateway/configuration](/gateway/configuration#auth-storage-oauth--api-keys)
All of the above also respect `$OPENCLAW_STATE_DIR` (state dir override). Full reference: [/gateway/configuration](/gateway/configuration#auth-storage-oauth--api-keys)
## Anthropic setup-token (subscription auth)
Run `claude setup-token` on any machine, then paste it into Moltbot:
Run `claude setup-token` on any machine, then paste it into OpenClaw:
```bash
moltbot models auth setup-token --provider anthropic
openclaw models auth setup-token --provider anthropic
```
If you generated the token elsewhere, paste it manually:
```bash
moltbot models auth paste-token --provider anthropic
openclaw models auth paste-token --provider anthropic
```
Verify:
```bash
moltbot models status
openclaw models status
```
## OAuth exchange (how login works)
Moltbot’s interactive login flows are implemented in `@mariozechner/pi-ai` and wired into the wizards/commands.
OpenClaw’s interactive login flows are implemented in `@mariozechner/pi-ai` and wired into the wizards/commands.
### Anthropic (Claude Pro/Max) setup-token
Flow shape:
1) run `claude setup-token`
2) paste the token into Moltbot
2) paste the token into OpenClaw
3) store as a token auth profile (no refresh)
The wizard path is `moltbot onboard` → auth choice `setup-token` (Anthropic).
The wizard path is `openclaw onboard` → auth choice `setup-token` (Anthropic).
### OpenAI Codex (ChatGPT OAuth)
@@ -89,7 +89,7 @@ Flow shape (PKCE):
5) exchange at `https://auth.openai.com/oauth/token`
6) extract `accountId` from the access token and store `{ access, refresh, expires, accountId }`
Wizard path is `moltbot onboard` → auth choice `openai-codex`.
Wizard path is `openclaw onboard` → auth choice `openai-codex`.
## Refresh + expiry
@@ -110,8 +110,8 @@ Two patterns:
If you want “personal” and “work” to never interact, use isolated agents (separate sessions + credentials + workspace):
```bash
moltbot agents add work
moltbot agents add personal
openclaw agents add work
openclaw agents add personal
```
Then configure auth per-agent (wizard) and route chats to the right agent.
@@ -128,7 +128,7 @@ Example (session override):
- `/model Opus@anthropic:work`
How to see what profile IDs exist:
- `moltbot channels list --json` (shows `auth[]`)
- `openclaw channels list --json` (shows `auth[]`)
Related docs:
- [/concepts/model-failover](/concepts/model-failover) (rotation + cooldown rules)

4
docs/concepts/presence.md
View File

@@ -1,5 +1,5 @@
---
summary: "How Moltbot presence entries are produced, merged, and displayed"
summary: "How OpenClaw presence entries are produced, merged, and displayed"
read_when:
- Debugging the Instances tab
- Investigating duplicate or stale instance rows
@@ -7,7 +7,7 @@ read_when:
---
# Presence
Moltbot “presence” is a lightweight, best‑effort view of:
OpenClaw “presence” is a lightweight, best‑effort view of:
- the **Gateway** itself, and
- **clients connected to the Gateway** (mac app, WebChat, CLI, etc.)

2
docs/concepts/retry.md
View File

@@ -30,7 +30,7 @@ read_when:
- Markdown parse errors are not retried; they fall back to plain text.
## Configuration
Set retry policy per provider in `~/.clawdbot/moltbot.json`:
Set retry policy per provider in `~/.openclaw/openclaw.json`:
```json5
{

2
docs/concepts/session-pruning.md
View File

@@ -18,7 +18,7 @@ Session pruning trims **old tool results** from the in-memory context right befo
## Smart defaults (Anthropic)
- **OAuth or setup-token** profiles: enable `cache-ttl` pruning and set heartbeat to `1h`.
- **API key** profiles: enable `cache-ttl` pruning, set heartbeat to `30m`, and default `cacheControlTtl` to `1h` on Anthropic models.
- If you set any of these values explicitly, Moltbot does **not** override them.
- If you set any of these values explicitly, OpenClaw does **not** override them.
## What this improves (cost + cache behavior)
- **Why prune:** Anthropic prompt caching only applies within the TTL. If a session goes idle past the TTL, the next request re-caches the full prompt unless you trim it first.

8
docs/concepts/session-tool.md
View File

@@ -63,7 +63,7 @@ Parameters:
Behavior:
- `includeTools=false` filters `role: "toolResult"` messages.
- Returns messages array in the raw transcript format.
- When given a `sessionId`, Moltbot resolves it to the corresponding session key (missing ids error).
- When given a `sessionId`, OpenClaw resolves it to the corresponding session key (missing ids error).
## sessions_send
Send a message into another session.
@@ -81,11 +81,11 @@ Behavior:
- Announce delivery runs after the primary run completes and is best-effort; `status: "ok"` does not guarantee the announce was delivered.
- Waits via gateway `agent.wait` (server-side) so reconnects don't drop the wait.
- Agent-to-agent message context is injected for the primary run.
- After the primary run completes, Moltbot runs a **reply-back loop**:
- After the primary run completes, OpenClaw runs a **reply-back loop**:
- Round 2+ alternates between requester and target agents.
- Reply exactly `REPLY_SKIP` to stop the ping‑pong.
- Max turns is `session.agentToAgent.maxPingPongTurns` (0–5, default 5).
- Once the loop ends, Moltbot runs the **agent‑to‑agent announce step** (target agent only):
- Once the loop ends, OpenClaw runs the **agent‑to‑agent announce step** (target agent only):
- Reply exactly `ANNOUNCE_SKIP` to stay silent.
- Any other reply is sent to the target channel.
- Announce step includes the original request + round‑1 reply + latest ping‑pong reply.
@@ -145,7 +145,7 @@ Behavior:
- Sub-agents default to the full tool set **minus session tools** (configurable via `tools.subagents.tools`).
- Sub-agents are not allowed to call `sessions_spawn` (no sub-agent → sub-agent spawning).
- Always non-blocking: returns `{ status: "accepted", runId, childSessionKey }` immediately.
- After completion, Moltbot runs a sub-agent **announce step** and posts the result to the requester chat channel.
- After completion, OpenClaw runs a sub-agent **announce step** and posts the result to the requester chat channel.
- Reply exactly `ANNOUNCE_SKIP` during the announce step to stay silent.
- Announce replies are normalized to `Status`/`Result`/`Notes`; `Status` comes from runtime outcome (not model text).
- Sub-agent sessions are auto-archived after `agents.defaults.subagents.archiveAfterMinutes` (default: 60).

28
docs/concepts/session.md
View File

@@ -5,7 +5,7 @@ read_when:
---
# Session Management
Moltbot treats **one direct-chat session per agent** as primary. Direct chats collapse to `agent:<agentId>:<mainKey>` (default `main`), while group/channel chats get their own keys. `session.mainKey` is honored.
OpenClaw treats **one direct-chat session per agent** as primary. Direct chats collapse to `agent:<agentId>:<mainKey>` (default `main`), while group/channel chats get their own keys. `session.mainKey` is honored.
Use `session.dmScope` to control how **direct messages** are grouped:
- `main` (default): all DMs share the main session for continuity.
@@ -15,26 +15,26 @@ Use `session.dmScope` to control how **direct messages** are grouped:
Use `session.identityLinks` to map provider-prefixed peer ids to a canonical identity so the same person shares a DM session across channels when using `per-peer`, `per-channel-peer`, or `per-account-channel-peer`.
## Gateway is the source of truth
All session state is **owned by the gateway** (the “master” Moltbot). UI clients (macOS app, WebChat, etc.) must query the gateway for session lists and token counts instead of reading local files.
All session state is **owned by the gateway** (the “master” OpenClaw). UI clients (macOS app, WebChat, etc.) must query the gateway for session lists and token counts instead of reading local files.
- In **remote mode**, the session store you care about lives on the remote gateway host, not your Mac.
- Token counts shown in UIs come from the gateway’s store fields (`inputTokens`, `outputTokens`, `totalTokens`, `contextTokens`). Clients do not parse JSONL transcripts to “fix up” totals.
## Where state lives
- On the **gateway host**:
- Store file: `~/.clawdbot/agents/<agentId>/sessions/sessions.json` (per agent).
- Transcripts: `~/.clawdbot/agents/<agentId>/sessions/<SessionId>.jsonl` (Telegram topic sessions use `.../<SessionId>-topic-<threadId>.jsonl`).
- Store file: `~/.openclaw/agents/<agentId>/sessions/sessions.json` (per agent).
- Transcripts: `~/.openclaw/agents/<agentId>/sessions/<SessionId>.jsonl` (Telegram topic sessions use `.../<SessionId>-topic-<threadId>.jsonl`).
- The store is a map `sessionKey -> { sessionId, updatedAt, ... }`. Deleting entries is safe; they are recreated on demand.
- Group entries may include `displayName`, `channel`, `subject`, `room`, and `space` to label sessions in UIs.
- Session entries include `origin` metadata (label + routing hints) so UIs can explain where a session came from.
- Moltbot does **not** read legacy Pi/Tau session folders.
- OpenClaw does **not** read legacy Pi/Tau session folders.
## Session pruning
Moltbot trims **old tool results** from the in-memory context right before LLM calls by default.
OpenClaw trims **old tool results** from the in-memory context right before LLM calls by default.
This does **not** rewrite JSONL history. See [/concepts/session-pruning](/concepts/session-pruning).
## Pre-compaction memory flush
When a session nears auto-compaction, Moltbot can run a **silent memory flush**
When a session nears auto-compaction, OpenClaw can run a **silent memory flush**
turn that reminds the model to write durable notes to disk. This only runs when
the workspace is writable. See [Memory](/concepts/memory) and
[Compaction](/concepts/compaction).
@@ -60,10 +60,10 @@ the workspace is writable. See [Memory](/concepts/memory) and
- Reset policy: sessions are reused until they expire, and expiry is evaluated on the next inbound message.
- Daily reset: defaults to **4:00 AM local time on the gateway host**. A session is stale once its last update is earlier than the most recent daily reset time.
- Idle reset (optional): `idleMinutes` adds a sliding idle window. When both daily and idle resets are configured, **whichever expires first** forces a new session.
- Legacy idle-only: if you set `session.idleMinutes` without any `session.reset`/`resetByType` config, Moltbot stays in idle-only mode for backward compatibility.
- Legacy idle-only: if you set `session.idleMinutes` without any `session.reset`/`resetByType` config, OpenClaw stays in idle-only mode for backward compatibility.
- Per-type overrides (optional): `resetByType` lets you override the policy for `dm`, `group`, and `thread` sessions (thread = Slack/Discord threads, Telegram topics, Matrix threads when provided by the connector).
- Per-channel overrides (optional): `resetByChannel` overrides the reset policy for a channel (applies to all session types for that channel and takes precedence over `reset`/`resetByType`).
- Reset triggers: exact `/new` or `/reset` (plus any extras in `resetTriggers`) start a fresh session id and pass the remainder of the message through. `/new <model>` accepts a model alias, `provider/model`, or provider name (fuzzy match) to set the new session model. If `/new` or `/reset` is sent alone, Moltbot runs a short “hello” greeting turn to confirm the reset.
- Reset triggers: exact `/new` or `/reset` (plus any extras in `resetTriggers`) start a fresh session id and pass the remainder of the message through. `/new <model>` accepts a model alias, `provider/model`, or provider name (fuzzy match) to set the new session model. If `/new` or `/reset` is sent alone, OpenClaw runs a short “hello” greeting turn to confirm the reset.
- Manual reset: delete specific keys from the store or remove the JSONL transcript; the next message recreates them.
- Isolated cron jobs always mint a fresh `sessionId` per run (no idle reuse).
@@ -92,7 +92,7 @@ Send these as standalone messages so they register.
## Configuration (optional rename example)
```json5
// ~/.clawdbot/moltbot.json
// ~/.openclaw/openclaw.json
{
session: {
scope: "per-sender", // keep group keys separate
@@ -116,16 +116,16 @@ Send these as standalone messages so they register.
discord: { mode: "idle", idleMinutes: 10080 }
},
resetTriggers: ["/new", "/reset"],
store: "~/.clawdbot/agents/{agentId}/sessions/sessions.json",
store: "~/.openclaw/agents/{agentId}/sessions/sessions.json",
mainKey: "main",
}
}
```
## Inspecting
- `moltbot status` — shows store path and recent sessions.
- `moltbot sessions --json` — dumps every entry (filter with `--active <minutes>`).
- `moltbot gateway call sessions.list --params '{}'` — fetch sessions from the running gateway (use `--url`/`--token` for remote gateway access).
- `openclaw status` — shows store path and recent sessions.
- `openclaw sessions --json` — dumps every entry (filter with `--active <minutes>`).
- `openclaw gateway call sessions.list --params '{}'` — fetch sessions from the running gateway (use `--url`/`--token` for remote gateway access).
- Send `/status` as a standalone message in chat to see whether the agent is reachable, how much of the session context is used, current thinking/verbose toggles, and when your WhatsApp web creds were last refreshed (helps spot relink needs).
- Send `/context list` or `/context detail` to see what’s in the system prompt and injected workspace files (and the biggest context contributors).
- Send `/stop` as a standalone message to abort the current run, clear queued followups for that session, and stop any sub-agent runs spawned from it (the reply includes the stopped count).

6
docs/concepts/streaming.md
View File

@@ -7,7 +7,7 @@ read_when:
---
# Streaming + chunking
Moltbot has two separate “streaming” layers:
OpenClaw has two separate “streaming” layers:
- **Block streaming (channels):** emit completed **blocks** as the assistant writes. These are normal channel messages (not token deltas).
- **Token-ish streaming (Telegram only):** update a **draft bubble** with partial text while generating; final message is sent at the end.
@@ -59,7 +59,7 @@ Block chunking is implemented by `EmbeddedBlockChunker`:
## Coalescing (merge streamed blocks)
When block streaming is enabled, Moltbot can **merge consecutive block chunks**
When block streaming is enabled, OpenClaw can **merge consecutive block chunks**
before sending them out. This reduces “single-line spam” while still providing
progressive output.
@@ -109,7 +109,7 @@ Telegram is the only channel with draft streaming:
- Final reply is still a normal message.
- `/reasoning stream` writes reasoning into the draft bubble (Telegram only).
When draft streaming is active, Moltbot disables block streaming for that reply to avoid double-streaming.
When draft streaming is active, OpenClaw disables block streaming for that reply to avoid double-streaming.
```
Telegram (private + topics)

22
docs/concepts/system-prompt.md
View File

@@ -1,14 +1,14 @@
---
summary: "What the Moltbot system prompt contains and how it is assembled"
summary: "What the OpenClaw system prompt contains and how it is assembled"
read_when:
- Editing system prompt text, tools list, or time/heartbeat sections
- Changing workspace bootstrap or skills injection behavior
---
# System Prompt
Moltbot builds a custom system prompt for every agent run. The prompt is **Moltbot-owned** and does not use the p-coding-agent default prompt.
OpenClaw builds a custom system prompt for every agent run. The prompt is **OpenClaw-owned** and does not use the p-coding-agent default prompt.
The prompt is assembled by Moltbot and injected into each agent run.
The prompt is assembled by OpenClaw and injected into each agent run.
## Structure
@@ -16,9 +16,9 @@ The prompt is intentionally compact and uses fixed sections:
- **Tooling**: current tool list + short descriptions.
- **Skills** (when available): tells the model how to load skill instructions on demand.
- **Moltbot Self-Update**: how to run `config.apply` and `update.run`.
- **OpenClaw Self-Update**: how to run `config.apply` and `update.run`.
- **Workspace**: working directory (`agents.defaults.workspace`).
- **Documentation**: local path to Moltbot docs (repo or npm package) and when to read them.
- **Documentation**: local path to OpenClaw docs (repo or npm package) and when to read them.
- **Workspace Files (injected)**: indicates bootstrap files are included below.
- **Sandbox** (when enabled): indicates sandboxed runtime, sandbox paths, and whether elevated exec is available.
- **Current Date & Time**: user-local time, timezone, and time format.
@@ -29,11 +29,11 @@ The prompt is intentionally compact and uses fixed sections:
## Prompt modes
Moltbot can render smaller system prompts for sub-agents. The runtime sets a
OpenClaw can render smaller system prompts for sub-agents. The runtime sets a
`promptMode` for each run (not a user-facing config):
- `full` (default): includes all sections above.
- `minimal`: used for sub-agents; omits **Skills**, **Memory Recall**, **Moltbot
- `minimal`: used for sub-agents; omits **Skills**, **Memory Recall**, **OpenClaw
Self-Update**, **Model Aliases**, **User Identity**, **Reply Tags**,
**Messaging**, **Silent Replies**, and **Heartbeats**. Tooling, Workspace,
Sandbox, Current Date & Time (when known), Runtime, and injected context stay
@@ -82,7 +82,7 @@ See [Date & Time](/date-time) for full behavior details.
## Skills
When eligible skills exist, Moltbot injects a compact **available skills list**
When eligible skills exist, OpenClaw injects a compact **available skills list**
(`formatSkillsForPrompt`) that includes the **file path** for each skill. The
prompt instructs the model to use `read` to load the SKILL.md at the listed
location (workspace, managed, or bundled). If no skills are eligible, the
@@ -103,8 +103,8 @@ This keeps the base prompt small while still enabling targeted skill usage.
## Documentation
When available, the system prompt includes a **Documentation** section that points to the
local Moltbot docs directory (either `docs/` in the repo workspace or the bundled npm
local OpenClaw docs directory (either `docs/` in the repo workspace or the bundled npm
package docs) and also notes the public mirror, source repo, community Discord, and
ClawdHub (https://clawdhub.com) for skills discovery. The prompt instructs the model to consult local docs first
for Moltbot behavior, commands, configuration, or architecture, and to run
`moltbot status` itself when possible (asking the user only when it lacks access).
for OpenClaw behavior, commands, configuration, or architecture, and to run
`openclaw status` itself when possible (asking the user only when it lacks access).

Some files were not shown because too many files have changed in this diff Show More