llm-wiki-rag

wuharlem/llm-wiki-rag

★ 0 stars Python AI/LLM Updated today

LLM Wiki RAG: hybrid retrieval (BM25 + dense + rerank) over a curated markdown vault, exposed as CLI + MCP server.

View on GitHub → 🔍 Audit Wallet Slippage →

Quick Install

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

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "llm-wiki-rag": {
      "command": "uvx",
      "args": [
        "llm-wiki-rag"
      ]
    }
  }
}

Or install with pip: pip install llm-wiki-rag

README Excerpt

<div align="center"> **Build-and-maintenance pipeline for an LLM-maintained wiki** — ingest sources into a Markdown (Obsidian-compatible) vault, build a chunked hybrid-retrieval index (BM25 + dense + rerank), and serve it to agents over MCP. Topic-agnostic: everything domain-specific lives in one file, `wiki_schema.yml`.

llm-wiki-rag

Quick Install

README Excerpt

Related AI/LLM Servers