# CortexReach/memory-lancedb-pro

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

Repository: https://github.com/CortexReach/memory-lancedb-pro
Canonical: https://ross.abutalabs.com/products/memory-lancedb-pro
Homepage: https://youtu.be/bhuGrjuCM_g
Language: JavaScript
License Family: other
Topics: lancedb, memory, openclaw, openclaw-agent, openclaw-plugin, rag
Last push: 2026-08-25T08:16:31+00:00

## Health v2 (maintenance only)
Score: 74/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 76, longevity 13
- inputs: {"age_days": 190, "days_push": 8, "days_rel": 163, "gap_med": 0.0, "n_releases_24m": 33}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 4463, forks 730 (observed 2026-08-28T04:08:50.766084+00:00)

## What it is
A LanceDB-backed long-term memory plugin for OpenClaw agents that stores preferences, decisions, and project context, then automatically recalls them in future sessions. It provides hybrid retrieval (vector + BM25), cross-encoder reranking, multi-scope isolation, and a management CLI.

## Use cases
- give my AI agent persistent memory across chat sessions
- store user preferences and recall them automatically in future conversations
- hybrid vector and BM25 retrieval for agent memory
- remember past decisions and project context across agents
- add long-term memory to an OpenClaw agent
- auto-capture important facts from conversations without manual tagging

## When to choose
- you use OpenClaw and want persistent, auto-recalled memory across sessions
- you need hybrid retrieval with reranking for high-quality memory recall
- you want multi-scope memory isolation across projects or agents
- you prefer an embedded LanceDB store with a management CLI

## When to avoid
- you use a different agent framework than OpenClaw
- you need a fully supported license — the repo currently has no license file
- you need a battle-tested stable release — current versions are beta
- you want a hosted or shared memory service rather than a local plugin

## Facets
- artifact type: plugin
- maturity: active
- function: rag, vector-database, search-engine, cli, plugin-system
- domain: large-language-models, databases, developer-tools
- platform: cli, cross-platform
- tags: lancedb, long-term-memory, agent-memory, hybrid-retrieval, bm25, reranking, openclaw, memory-persistence, ai-agents, retrieval-augmented-generation, nodejs

## Member repositories
- CortexReach/memory-lancedb-pro (main) score 74

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:50.766084+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:20:40.255049+00:00, confidence not recorded.
  - readme: https://github.com/CortexReach/memory-lancedb-pro (fetched 2026-08-28T04:08:50.766084+00:00, sha 9cfc7a57c9a8)
  - homepage: https://youtu.be/bhuGrjuCM_g (fetched 2026-08-29T09:07:37.442891+00:00, sha a100e322c58d)
- Data as of 2026-08-30T08:39:29.467469+00:00.