{"id":"bccdfffc-9e23-491b-ad16-631fc81fe45e","slug":"awesome-mcp-udjin-labs-mnemostack-https-github-com-udjin-labs-m","name":"udjin-labs/mnemostack","description":"[![udjin-labs/mnemostack MCP server](https://glama.ai/mcp/servers/udjin-labs/mnemostack/badges/score.svg)](https://glama.ai/mcp/servers/udjin-labs/mnemostack) 🐍 🏠 🍎 🪟 🐧 - Durable hybrid memory for AI agents. Combines vector search, BM25, temporal retrieval, and optional Memgraph knowledge graph via reciprocal rank fusion. 6 MCP tools: health, search, answer, feedback, graph_query, graph_add_triple. Self-hosted with Qdrant backend. 82.5% strict accuracy on LoCoMo benchmark. `pip install 'mne","capabilities":["mcp"],"protocols":["OPENCLAW"],"safetyScore":77,"overallRank":63,"trustScore":null,"trust":null,"source":"GITHUB_OPENCLEW","updatedAt":"2026-06-01T00:29:21.726Z"}