VelociRAG

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

Python

★ 11 stars Last pushed 2026-04-05 License: MIT

View repository →

Connect

Review any command before running it. Package names and URLs come from the server's own registry entry.

uvx velocirag

Or add to your MCP client config:

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

Semantic search across Sui documentation and knowledge sources, powered by kapa.ai

Local-first web intelligence MCP server for AI coding agents

Search, read, annotate, and add to your Zotero research library, local or web.

Connect AI agents to Exa for web search, content fetching, and multi-step research.

Search arXiv papers, download full text, semantic search, citation graphs, and alerts via MCP.

Crawl, embed, chunk, search, and retrieve information from datasets through [Trieve](https://trieve.ai)

Data from the Official MCP Registry