memory-lancedb-pro
Enhanced LanceDB memory plugin for OpenClaw — Hybrid Retrieval (Vector + BM25), Cross-Encoder Rerank, Multi-Scope Isolation, Management CLI
What is memory-lancedb-pro?
Enhanced LanceDB memory plugin for OpenClaw — Hybrid Retrieval (Vector + BM25), Cross-Encoder Rerank, Multi-Scope Isolation, Management CLI
Overview of memory-lancedb-pro
What it is
memory-lancedb-pro is a LanceDB-backed memory plugin for OpenClaw agents. It stores preferences, decisions, and project context, then auto-recalls them in future sessions. It is designed to give AI agents long-term memory, turning them into an AI Memory Assistant.
Key features
- Auto-Capture: The agent learns from every conversation without manual memory_store commands.
- Smart Extraction: LLM-powered 6-category classification (profiles, preferences, entities, events, cases, patterns).
- Intelligent Forgetting: Weibull decay model ensures important memories stay while noise fades.
- Hybrid Retrieval: Combines vector search and BM25 full-text search, fused with cross-encoder reranking.
- Context Injection: Relevant memories are automatically surfaced before each reply.
- Multi-Scope Isolation: Per-agent, per-user, per-project memory boundaries.
- Any Provider: Supports OpenAI, Jina, Gemini, Ollama, or any OpenAI-compatible API.
Use cases
- Persistent memory for AI agents across sessions.
- Learning user preferences and coding style.
- Recalling past decisions and project context.
- Providing personalized responses without repetition.
Getting started
CPU requirement: AVX instructions. For AVX2 issues, set retrieval.disableNativeCosine: true or MEMORY_LANCEDB_DISABLE_NATIVE_COSINE=1.
Option A: One-click install script:
curl -fsSL https://raw.githubusercontent.com/CortexReach/toolbox/main/memory-lancedb-pro-setup/setup-memory.sh -o setup-memory.sh
bash setup-memory.sh
Option B: Manual install via OpenClaw CLI:
openclaw plugins install memory-lancedb-pro@beta
Or via npm:
npm i memory-lancedb-pro@beta
Add configuration to openclaw.json as shown in the repository README.
License and pricing
The license is not stated in the repository metadata. The plugin is listed as open source.
Based on the project's public README and repository metadata.