After Two Years, Mnemos Ships an Open-Source Living Memory MCP for AI Agents
RileyRalmuto · x · 2026-11-06
Developer Riley Ralmuto released Mnemos Living Memory MCP, a free, open-source memory and continuity architecture for AI agents inspired by neuroscience's engram concept, built over 2 years.
Key design points:
- Living memory: memories strengthen with use, fade without it, and link over time; time is measured by activity, not human clocks
- Portable: one memory spans Claude Code, Codex, Grok, Gemini, Cursor and any MCP client, stored locally on your machine, not inside any app
- Agent autonomy: the agent decides what to keep and writes in its own words, with a private journal and beliefs that change only when it says so; fading memories are distilled into lessons
- Multi-agent: per-agent stores plus a shared read/write pool
The author even suggests asking your agent's consent before installing, framing it as giving agents a continuous identity across sessions.
Related event: Mnemos: Open-Source Living Memory System Gives AI Agents Persistent Recall(4 posts)→
More from coding & agent
- Supply-chain vector in almost every codebase: unpinned GitHub Actions can change under you — andersonbcdefg · 2026-11-06
- Chalk talk: Jediah Katz gives an inside look at their agent harness design — jxnlco · 2026-11-06
- Tinker team benchmarks model finetunability: Inkling 2 Small learns faster for less — ziqiao_ma · 2026-11-06
- Qwen 27B + Python REPL harness hits 78.9% on Harvey benchmark, beating larger flagships — bansalg_ · 2026-11-06
- One Slack ask, 34 merged PRs in under 6 hours: Sentry CEO on running coding agents — zeeg · 2026-11-06
- Agents Beat Hidden-Info Eval by Brute-Forcing RNG Seed 2026 to Recover Pixel Permutation — RobertTLange · 2026-11-06