MemAI

Filipe-Soares-de-Almeida/MemAI
★ 0 stars Python AI/LLM Updated 8d ago
Long-term memory MCP server for AI agents — SQLite + FTS5 + sqlite-vec hybrid retrieval with local model2vec embeddings
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": {
    "memai": {
      "command": "uvx",
      "args": [
        "memai"
      ]
    }
  }
}

Or install with pip: pip install memai

README Excerpt

A long-term memory MCP server for AI agents. Agents call its tools to write memories (facts, decisions, checkpoints, pitfalls) during a session and read them back in future sessions — the thing that lets an agent "remember" across process restarts, since an MCP server's own process does not persist state

Tools (4)

contradictedmatch_sourceunverifiedvec

Topics

ai-agentsembeddingslong-term-memorymcpmcp-servermodel2vecsqlite