CortexReach/memory-lancedb-pro

Enhanced LanceDB memory plugin for OpenClaw — Hybrid Retrieval (Vector + BM25), Cross-Encoder Rerank, Multi-Scope Isolation, Management CLI

62
/ 100
Established

Implements OpenClaw agent memory through LanceDB, leveraging a Weibull decay model where agents auto-extract conversation context into six semantic categories (profiles, preferences, entities, events, cases, patterns), then retrieve via fused vector+BM25 search with cross-encoder reranking. Operates with granular scope isolation (per-agent, per-user, per-project) and includes production tooling: CLI management, backup/migration utilities, and OpenAI-compatible provider flexibility across embedding and reranking endpoints.

2,280 stars. Actively maintained with 250 commits in the last 30 days.

No License No Package No Dependents
Maintenance 25 / 25
Adoption 10 / 25
Maturity 3 / 25
Community 24 / 25

How are scores calculated?

Stars

2,280

Forks

392

Language

TypeScript

License

Last pushed

Mar 13, 2026

Commits (30d)

250

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/vector-db/CortexReach/memory-lancedb-pro"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.