</>MCP Agents Market
Plugin

memory-lancedb-pro

by CortexReach4.5kJavaScriptUpdated 2026-08-29

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

OpenClaw

memory-lancedb-pro is an advanced memory plugin for OpenClaw AI agents that provides persistent, semantic long-term memory using LanceDB vector storage. It enables agents to automatically capture preferences, decisions, and context from conversations, then intelligently recall relevant memories in future sessions across users, projects, and agents. The plugin combines vector search with BM25 full-text retrieval, cross-encoder reranking, and intelligent forgetting mechanisms to surface the most relevant memories at the right time. It eliminates the need for users to repeat preferences and allows agents to maintain continuity across sessions with minimal configuration.

Key Features

Hybrid retrieval combining vector similarity search and BM25 full-text search with configurable fusion weights
Cross-encoder reranking with support for Jina, SiliconFlow, Voyage AI, and Pinecone providers
LLM-powered smart extraction that classifies memories into 6 categories (profile, preferences, entities, events, cases, patterns) with automatic deduplication
Weibull decay model with three-tier memory management (Core → Working → Peripheral) and access-based reinforcement
Multi-scope isolation for per-agent, per-user, and per-project memory boundaries with granular access control
Auto-capture from conversations and auto-recall injection into prompts with noise filtering
Comprehensive CLI for memory management, export/import, re-embedding, and migration
Compatible with any OpenAI-compatible embedding API (OpenAI, Jina, Gemini, Voyage, Ollama) with task-aware embeddings support

Use Cases

  • 01Maintaining coding style preferences across sessions so agents automatically apply formatting rules without reminders
  • 02Recalling past technical decisions and their rationale when revisiting old projects
  • 03Building personalized agent responses based on accumulated user preferences and interaction history
  • 04Isolating memory contexts for different projects or team members in multi-user environments
  • 05Automatically learning from user corrections and applying those lessons to future interactions
  • 06Preserving domain knowledge and project context for AI assistants that work on long-running tasks

Related Plugins

View more

andrej-karpathy-skills

A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.

Plugin216.2k

claude-mem

Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More

Plugin95.1k

Understand-Anything

Graphs that teach > graphs that impress. Turn any code into an interactive knowledge graph you can explore, search, and ask questions about. Works with Claude Code, Codex, Cursor, Copilot, Gemini CLI, and more.

Plugin85k

rtk

CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies

Plugin82.2k

memory-lancedb-pro — FAQ

What is memory-lancedb-pro?+

memory-lancedb-pro is a production-grade long-term memory plugin for OpenClaw that gives AI agents persistent semantic memory using LanceDB vector storage. It automatically captures and recalls preferences, decisions, and context across sessions without manual intervention.

How do I install memory-lancedb-pro?+

Install via OpenClaw CLI with 'openclaw plugins install memory-lancedb-pro@beta' or use npm with 'npm i memory-lancedb-pro@beta'. You must configure it in openclaw.json with embedding provider credentials and bind it to the memory slot.

Which AI clients work with this plugin?+

This plugin is specifically designed for OpenClaw (version 2026.3+). It uses OpenClaw's plugin architecture and lifecycle hooks, so it requires an OpenClaw agent installation to function.

Do I need API keys to use memory-lancedb-pro?+

Yes, you need an API key for an embedding provider (OpenAI, Jina, Gemini, Voyage, or a compatible service). For cross-encoder reranking, you also need a reranker API key (Jina, SiliconFlow, etc.). Alternatively, you can run fully local with Ollama.

Is memory-lancedb-pro free to use?+

The plugin itself is MIT-licensed and free. However, you'll incur costs from your chosen embedding and reranking API providers based on their pricing. Free tiers are available from providers like SiliconFlow, or you can run cost-free with Ollama locally.

Does my CPU need special requirements?+

Your CPU must support AVX instructions. LanceDB may require AVX2 on some Linux builds and can crash AVX-only CPUs. If you encounter crashes, set 'disableNativeCosine: true' to use JavaScript-based cosine ranking instead.

How do I install memory-lancedb-pro?+

Open the source repository on GitHub and follow its README. memory-lancedb-pro is a plugin — MCP Agents Market links you directly to the official repo.

Is memory-lancedb-pro free?+

memory-lancedb-pro is an open-source project hosted on GitHub. Check the repository for its license and any usage requirements.

Related searches

Knowledge & Memory PluginsDeveloper Tools PluginsBest MCP ServersBest SkillsBest AgentsTop rated listingsClaude Code toolsBrowse all categories