loci MCP Server
IvenKooLab/loci
[](https://agentrank-ai.com/tool/IvenKooLab--loci/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge) A queryable second brain over your scattered notes and docs - hybrid retrieval (vector + BM25), section-level citations, and an MCP server so AI agents can use it. ~300 lines, no LangChain.
claude mcp add agentrank -- npx -y agentrank-mcp-server Overview
IvenKooLab/loci is a Python MCP server licensed under MIT. A queryable second brain over your scattered notes and docs - hybrid retrieval (vector + BM25), section-level citations, and an MCP server so AI agents can use it. ~300 lines, no LangChain. Topics: chromadb, embeddings, knowledge-base, local-first, mcp, mcp-server, obsidian, rag, retrieval-augmented-generation, second-brain, ai-agents, bm25, cross-ide, memory-management, ollama, personal-knowledge-base, wiki, feedback-loop, incremental-indexing, query-rewriting.
Ranked #10854 out of 24846 indexed tools.
Ecosystem
Score Breakdown
100 stars → early stage
Last commit 1mo ago → moderate activity
0/1 issues closed → many open issues
1 contributor → solo project
No dependents → no downstream usage
Weights: Freshness 20% · Issue Health 20% · Dependents 22% · Stars 10% · Contributors 8% · How we score →
How to Improve
Badge all embed codes →
[](https://agentrank-ai.com/tool/IvenKooLab--loci/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge) <a href="https://agentrank-ai.com/tool/IvenKooLab--loci/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge"><img src="https://agentrank-ai.com/api/v1/badge/IvenKooLab--loci" alt="AgentRank"></a> Matched Queries
From the README
# loci 🧠 > Two thousand years ago, orators stored their speeches in the rooms of a > palace and walked through them to remember. **loci does the same for your > files.** > > *Loci* is the method behind every memory palace: place knowledge in > locations, recall it by walking the path. **A queryable "second brain" for the project docs, notes, and chat logs scattered across a dozen directories — and an MCP server so your AI agents can use it too.** Local files → heading-aware chunking → embeddings → hybrid retrieval (vector + BM25) → LLM answer with section-level citations. The index lives entirely on your machine; only embedding/chat calls go out, to any OpenAI-compatible API (Zhipu / DeepSeek / Kimi / OpenAI / …). > **The thesis** (from studying the 90k-star platforms and the graveyard of > dead lightweight tools — see > [our competitive landscape study](docs/research/competitive-landscape.md)): > don't build another chat app. Build the **memory layer that every chat app > can mouRead full README on GitHub →
Get the weekly AgentRank digest
Top movers, new tools, ecosystem insights — straight to your inbox.