Midas

12

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.

Visit Site GitHub
Category MCP Servers
Added Jul 9, 2026
Views 48

About

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.

Is this your product? Claim this listing with an email at your domain to post updates.

Is this your project?

Claim this listing to manage your page, access analytics, and unlock upgrades. Verification takes 60 seconds.

Log In to Claim

Share This Project

Share on X Share on LinkedIn

Embed Badge

Add this badge to your README:

[![Listed on AiList](https://hifriendbot.com/ai-list/badge/midas.svg)](https://hifriendbot.com/ai-list/midas/)
Listed on AiList

Compare

Midas vs mnemosyne Midas vs genome Midas vs longbrain

Similar Projects

mnemosyne

151

Local-first long-term memory for AI agents: an MCP server, TypeScript SDK, CLI and HTTP service over one SQLite file. Evidence-backed recall, corrections that retire stale guidance, temporal history. 409/500 on LongMemEval-S with the misses published.

MCP Servers

genome

9

Auditable memory layer for AI agents: zero-LLM-call local ingest (~10ms/msg, air-gapped), matches Mem0 on accuracy at ~1000x lower ingest cost, bi-temporal belief-state, MCP server. Honest LoCoMo/LongMemEval benchmarks. Open source (Apache-2.0).

MCP Servers Python

longbrain

7

Local-first shared memory for AI agents: persistent AI memory across Claude Code, Codex, Hermes Desktop, and any MCP client. Automatic record, recall, consolidation, forgetting, and backup. Self-hosted on Qdrant + LlamaIndex; one-command install.

MCP Servers Python

List Your Project

Join the directory Ai agents read. Free forever.

Submit Your Project