Local Rag MCP Server

@TheWinci

リポジトリ

基本情報

カテゴリ

メモリとナレッジ

トランスポート

stdio

作者

TheWinci

投稿者

TheWinci

Local Rag MCP Server について

Semantic code search for AI agents — hybrid vector + BM25 with cross-encoder reranking, AST-aware chunking for 14 languages, conversation memory, code annotations, and search analytics. Zero config, zero API keys. Just bunx.

#rag #local #knowledge #memory

Local Rag MCP Server の設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "local-rag": {
      "command": "bunx",
      "args": [
        "@winci/local-rag@latest",
        "serve"
      ],
      "env": {
        "RAG_PROJECT_DIR": "/path/to/your/project"
      }
    }
  }
}

Local Rag MCP Server のツール

ツール一覧はまだありません

この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。

上のボタンで一時的なサンドボックスでこのサーバーを実行し、ツール一覧を取得できます。

概要

What is Local Rag?

Local Rag is a persistent project memory tool for AI coding agents. It provides semantic code search, cross-session conversation memory, auto-generated project wikis, and dependency graph analysis—all running fully locally using SQLite and in-process embeddings.

How to use Local Rag?

Install with bunx mimirs init --ide <ide> (e.g., claude, cursor, windsurf, copilot, jetbrains). Ensure SQLite with extension support is installed (brew install sqlite on macOS). No API keys, cloud, or Docker required—just Bun and SQLite.

Key features of Local Rag

Hybrid vector + BM25 search boosted by dependency graph centrality
Cross-session conversation indexing and checkpoints
Auto-generated structured markdown wiki with Mermaid diagrams
Annotations attached to files or symbols surfacing in results
Dependency graph and reverse-dependency lookup for blast radius
Local analytics logging zero-result and low-relevance queries

Use cases of Local Rag

Quickly find code by meaning instead of filename or keyword search
Recover context from past sessions—discussions, decisions, and blockers
Understand codebase structure and impact before refactoring
Expose documentation gaps through query analytics
Mark milestones and direction changes with searchable checkpoints

よくある質問

What does Local Rag do that alternatives don’t?

It combines AST-aware chunking (24 languages), local embeddings, cross-session memory, and checkpoints—all in one local tool with no API keys. The table in the README shows it reduces token cost from ~380K to ~91K per prompt with 93–98% recall.

Where does my data live?

All data is stored in a `.mimirs/` directory inside your project. Nothing leaves your machine—the tool is fully local and privacy-preserving.

What languages and file formats does it support?

AST-aware chunking covers 24 languages via tree-sitter (TypeScript, Python, Go, Rust, Java, C, C++, C#, Ruby, PHP, Scala, Kotlin, Lua, Zig, Elixir, Haskell, OCaml, Dart, Bash/Zsh, TOML, YAML, HTML, CSS/SCSS/LESS). Many other formats fall back to paragraph splitting.

Does Local Rag require an embedding API or cloud service?

No. Embeddings are computed in-process using Transformers.js + ONNX with the all-MiniLM-L6-v2 model. The vector store is sqlite-vec—a single `.db` file.

What transport and authentication does it use?

Local Rag uses stdio transport via the MCP SDK. There is no network service; authentication is not required because everything runs locally.

「メモリとナレッジ」の他のコンテンツ

Agimem

Persistent memory for AI agents. Hosted MCP server with capsule-scoped key/value storage, tags, TTL expiration, bulk ops, and RBAC.

ctxfile

Local-first MCP server that snapshots your project's working state into one context object. Open-core, privacy-first.

OpenLore

aakarim

Serve your docs to AI agents over SSH and MCP. Agents use ls, cat, grep, find, and pipes against a virtual filesystem backed by your documentation. Identity-scoped access, governed writing with human approval, and portab

agentleFS

One permissioned folder your team and your AI agents both log into.

Tempreon

Person-owned, portable AI memory served over MCP. Your knowledge, preferences, and decisions — captured in one assistant, available in all of them.