AI Agents MCP Servers Workflows Blog Submit
T

tomohiro-owada/devrag

Database Free Open Source

🏎️ 🏠 🍎 🪟 🐧 - Lightweight local RAG MCP server for semantic vector search over markdown documents. Reduces token consumption by 40x with sqlite-vec and multilingual-e5-small embeddings. Supports filtered search by directory and filename patterns.

<p><strong>tomohiro-owada/devrag</strong> is a database MCP server that 🏎️ 🏠 🍎 🪟 🐧 - Lightweight local RAG MCP server for semantic vector search over markdown documents. Reduces token consumption by 40x with sqlite-vec and multilingual-e5-small embeddings. Supports filtered search by directory and filename patterns..</p> <h2>How to Use tomohiro-owada/devrag</h2> <p>To use tomohiro-owada/devrag, you need an MCP-compatible client such as Claude Desktop, Cursor, or VS Code with an MCP extension. Once configured, the AI model can automatically use the tools provided by this server.</p>

Key Features

  • Open source with community contributions
  • Data querying and manipulation
  • Multiple database support