LLM-second-brain

philadelfic/LLM-second-brain

★ 2 stars Python AI/LLM Updated 1d ago

Self-hosted MCP server for LLM long-term memory (Open WebUI). Models search, read, write and delete notes via MCP (hybrid vector + full-text search). Single non-root Docker container, no UI. SQLite + sqlite-vec + FTS5, RRF hybrid search, embeddings and summarization via Ollama. 6 memory_* tools, Bearer token.

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-second-brain": {
      "command": "uvx",
      "args": [
        "llm-second-brain"
      ]
    }
  }
}

Or install with pip: pip install llm-second-brain

README Excerpt

A self-hosted **long-term memory server** for LLMs running in harnesses (primarily Open WebUI). Models get MCP access to a shared note store: they can search it (hybrid vector + full-text), read, write, update and delete notes. - **One Docker container**, self-hosted, non-root. - **MCP Streamable HTTP** (`/mcp`, natively supported by Open WebUI) with a

LLM-second-brain

Quick Install

README Excerpt

Related AI/LLM Servers