memory-mcp

vladmesh/memory-mcp

★ 0 stars Python AI/LLM Updated 13d ago

Shared semantic-memory server over MCP (SQLite + sqlite-vec + fastembed)

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": {
    "memory-mcp": {
      "command": "uvx",
      "args": [
        "memory-mcp"
      ]
    }
  }
}

Or install with pip: pip install memory-mcp

README Excerpt

A small semantic-memory server exposed over MCP, so any MCP-speaking agent (Claude Code, Codex, Gemini CLI, Hermes, ...) shares one warm memory store. - **Storage / ANN:** SQLite + [`sqlite-vec`](https://github.com/asg017/sqlite-vec) (vectors live in the same file). - **Embeddings:** [`fastembed`](https://github.com/qdrant/fastembed) on CPU, multilingual model (`intfloat/multilingual-e5-large`, 1024-dim). No GPU, no local LLM.

Tools (5)

MEMORY_DBMEMORY_DIMMEMORY_MODELMEMORY_PORTmemory

memory-mcp

Quick Install

README Excerpt

Tools (5)

Related AI/LLM Servers