HN Showcase
Back to browse
GitHub Repository

Cognitive Memory OS for AI Agents — persistent, self-improving, multi-agent memory

80 starsTypeScript

Mnemosyne – Cognitive memory OS for AI agents (zero LLM calls)

by mnemosy·Feb 24, 2026·5 points·1 comment
Visit ProjectView on HN

AI Analysis

●MidBig BrainBold Bet

Claims brain-like cognition with zero LLM calls, but zero evidence of actual learning.

Strengths
  • •Frames memory problem clearly: agents today are stateless and fail in production.
  • •10 named cognitive features suggest thoughtful architectural approach.
Weaknesses
  • •No working demo, no benchmarks, no code showing how 'zero LLM calls' is possible.
  • •'Self-improving' is promised but unexplained; 'Theory of Mind' is hype without implementation details.
Category
AI/ML
Target Audience

AI agent developers, autonomous system builders

Similar To

LangChain memory modules · MemGPT · Mem0

Similar Projects

AI/ML●●Solid

AgentKeeper – cognitive persistence layer for AI agents

Cross-provider agent memory is clever, but LLM context windows keep growing and RAG is already standard.

Solve My ProblemShip ItBig Brain
thinklanceai
303mo ago
AI/ML●●Solid

AgentKeeper – Cross-model memory for AI agents

Recovers 95% critical facts when switching GPT-4 ↔ Claude with real benchmarks.

Solve My ProblemBig Brain
thinklanceai
103mo ago
AI/ML●●●Banger

YantrikDB – persistent memory for AI agents

Bundled 7MB embedder means zero network calls or model downloads for agent memory.

Zero to OneWizardrySolve My Problem
pranabsarkar
111mo ago