velocirag

Lightning-fast RAG for AI agents. 4-layer fusion, ONNX Runtime, sub-200ms search.

GitHub · PyPI · Registry

Search & knowledge Dev tools & GitHub AI models & media

Install

Run it directly:

uvx velocirag

Or add it to your client config (Claude Desktop claude_desktop_config.json, Cursor .cursor/mcp.json):

{
  "mcpServers": {
    "velocirag": {
      "command": "uvx",
      "args": [
        "velocirag"
      ]
    }
  }
}

Generated from the package metadata in the official MCP Registry. MCP Morning does not run or test servers; check required environment variables in the project README.

Alternatives