Local-first, eval-first memory for long-horizon AI agents — no LLM at ingest. Python SDK + MCP server with source-traceable recall, belief revision, selective forgetting, and reproducible benchmarks.
<h1 align="center">Midas</h1> <p align="center"><b>The local memory layer for long-horizon AI agents — remembers across sessions, keeps what's current, and won't act on stale memory.</b><br/>No LLM at ingest · $0 per message · fully local · every recall traces to its source.</p> <p align="center"> <a href="https://github.com/vornicx/Midas/actions/workflows/ci.yml"><img src="https://github.com/vornicx/Midas/actions/workflows/ci.yml/badge.svg" alt="tests"></a>