cablate/memory-lancedb-mcp
MCP server for LanceDB-backed long-term memory with hybrid retrieval (Vector + BM25), cross-encoder rerank, multi-scope isolation, and memory lifecycle management
Platform-specific configuration:
{
"mcpServers": {
"memory-lancedb-mcp": {
"command": "npx",
"args": [
"-y",
"memory-lancedb-mcp"
]
}
}
}Add the config above to .claude/settings.json under the mcpServers key.
<div align="center">
> Built on [CortexReach/memory-lancedb-pro](https://github.com/CortexReach/memory-lancedb-pro) — original work by win4r and contributors. Refactored from OpenClaw plugin into a standalone MCP server.
[](https://www.npmjs.com/package/@cablate/memory-lancedb-mcp) [](https://lancedb.com) [](LICENSE)
English | 繁體中文
</div>
---
Most AI agents forget everything the moment you start a new session. This MCP server gives any MCP-compatible client persistent, intelligent long-term memory — without manual management.
| | What you get | | -------------------------- | ------------------------------------------------------------------------------ | | Hybrid Retrieval | Vector + BM25 full-text search, fused with cross-encoder reranking | | Smart Extraction | LLM-powered 6-category memory extraction | | Memory Lifecycle | Weibull decay + 3-tier promotion — important memories surface, stale ones fade | | Multi-Scope Isolation | Per-agent, per-user, per-project memory boundaries | | Any Embedding Provider | OpenAI, Jina, Gemini, DeepInfra, Ollama, or any OpenAI-compatible API | | Self-Improvement Tools | Structured learning/error logging with skill extraction |
---
npm install -g @cablate/memory-lancedb-mcpAdd to your MCP client settings (e.g. Claude Desktop `claude_desktop_config.
Loading reviews...