tomohiro-owada/devrag
Markdown vector search MCP server for Claude Code. Natural language search for markdown files using multilingual-e5-small embeddings.
This tool helps software developers efficiently find specific information within their project's documentation when using Claude Code. It takes your Markdown files as input and creates a searchable index. When you ask Claude Code a question in natural language, it quickly retrieves only the most relevant sections from your documents, saving time and reducing the cost of using the AI.
Use this if you are a developer frequently using Claude Code and need to quickly find specific code examples, API details, or process explanations within your extensive Markdown-based project documentation without manually sifting through files or wasting AI tokens.
Not ideal if you don't use Claude Code for development or if your project's documentation is not primarily in Markdown files.
Stars
36
Forks
10
Language
Go
License
—
Category
Last pushed
Mar 12, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/vector-db/tomohiro-owada/devrag"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
cocoindex-io/cocoindex
Data transformation framework for AI. Ultra performant, with incremental processing. 🌟 Star if...
infinilabs/coco-server
🥥 Coco AI Server - Search, Connect, Collaborate, AI-powered Enterprise Search, all in one space.
REASY/k8s-ariadne-rs
Query Kubernetes with natural language by compiling English to Cypher. No context window bloat....
lemoal-t/oriongraphdb
🚀 Optimize AI context retrieval with OrionGraphDB, a powerful engine that respects token budgets...
karmaniverous/jeeves-watcher
Filesystem watcher that keeps a Qdrant vector store in sync with document changes. Config-driven...