kglite-docs

kkollsga/kglite-docs

★ 0 stars Python 🤖 AI/LLM Updated today

Agent-first knowledge base for documents. Built on kglite + BAAI/bge-m3. Multi-format ingest, cross-checked summaries, review kanban, grounding checks, and an MCP server.

View on GitHub → Try with Claude — $10 free →

Quick Install

Copy the config for your editor. Some servers may need additional setup — check the README.

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "kglite-docs": {
      "command": "uvx",
      "args": [
        "kglite-docs"
      ]
    }
  }
}

Or install with pip: pip install kglite-docs

README Excerpt

> **Agent-first knowledge base for documents.** Ingest PDFs, Office files, Markdown, HTML, or images; chunk + embed them with [BAAI/bge-m3](https://huggingface.co/BAAI/bge-m3); cluster, tag, summarise, fact-check, translate, and review them — and serve the whole thing to AI agents over MCP. Built on [`kglite`](https://github.com/kkollsga/kglite) (storage + vector search + clustering) and [`mcp-methods`](https://github.com/kkollsga/mcp-methods) (MCP framework).

Topics

anthropicbge-m3claude-codeembeddingskgliteknowledge-graphmcppdfrag

kglite-docs

Quick Install

README Excerpt

Topics

Related AI/LLM Servers