Tarun Sukhani e7ac300b7e memory-neo4j: add Pareto-based memory ecosystem with retrieval tracking ...

Implement retrieval tracking and Pareto-based memory consolidation:

- Track retrievalCount and lastRetrievedAt on every search
- Effective importance formula: importance × freq_boost × recency_factor
- Seven-phase sleep cycle: dedup, pareto scoring, promotion, demotion,
  decay/pruning, extraction, cleanup
- Bidirectional mobility between core (≤20%) and regular memory tiers
- Core memories ranked by pure usage (no importance multiplier)

Based on ACT-R memory model and Ebbinghaus forgetting curve research.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

2026-02-16 17:56:38 +08:00

..

config.ts

…

embeddings.ts

…

extractor.ts

memory-neo4j: add Pareto-based memory ecosystem with retrieval tracking

2026-02-16 17:56:38 +08:00

index.ts

memory-neo4j: add Pareto-based memory ecosystem with retrieval tracking

2026-02-16 17:56:38 +08:00

neo4j-client.ts

memory-neo4j: add Pareto-based memory ecosystem with retrieval tracking

2026-02-16 17:56:38 +08:00

openclaw.plugin.json

…

package.json

…

schema.ts

…

search.ts

memory-neo4j: add Pareto-based memory ecosystem with retrieval tracking

2026-02-16 17:56:38 +08:00

tsconfig.json

…