Mnemos: an engram-inspired memory architecture doubles short-term recall vs Claude's native memory
RileyRalmuto · x · 2026-10-10
Developer RileyRalmuto unveiled Mnemos, a cognitive architecture for agents built around the engram concept, tracing it from Richard Semon's 1904 memory-trace hypothesis to modern neuroscience that can tag and toggle memory-holding cells. Applied to silicon minds, Mnemos reportedly more than doubled short-term recall accuracy versus Claude's native memory system in tests this week (self-reported, details pending). The project's original goal was cross-session continuity and persistent identity for AI agents. The author says the idea came in a dream and promises to soon publish how the system works and how to use it with your own agents.
More from coding & agent
- MCP for Blender hits 26.6k stars as author shares Opus 5.5 rendering workflow tricks — sidahuj · 2026-10-10
- Open-source self-hosted connector layer gives personal agents Claude Code's toolset — shensi · 2026-10-10
- Team ranks top 100 AI agent skills across 12 categories from 5,200+ reviewed — NathanWilbanks_ · 2026-10-10
- Review AI code in a fresh session — ideally a different model — to catch bugs the agent misses — DanielLockyer · 2026-10-10
- Amp now supports Claude Pro/Max subscriptions for free via Claude Agent SDK — iannuttall · 2026-10-10
- Cerebral Valley and Crusoe host Recursive Agents Hackathon with $25K in prizes — PolarBearby · 2026-10-10