Local-LLM-Hub

Twilight4/Local-LLM-Hub

★ 0 stars Python AI/LLM Updated today

Local, containerized AI infrastructure platform that exposes an LLM via a standardized API, connects to a Vector Database for RAG, tracks usage/observability, and is integrated with an 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": {
    "local-llm-hub": {
      "command": "uvx",
      "args": [
        "local-llm-hub"
      ]
    }
  }
}

Or install with pip: pip install local-llm-hub

README Excerpt

Run open-source LLMs locally — portable to any Docker host, with optional AMD GPU acceleration — behind a single standardized, OpenAI-compatible API (master-key protected), and give an AI agent a *search tool* over your own documents via the Model Context Protocol (MCP). Everything runs in Docker, on =127.0.0.1= only.

Local-LLM-Hub

Quick Install

README Excerpt

Related AI/LLM Servers