Sohamp2809/mnemos

Open-source memory layer for multi-agent LLM systems. Typed conflict resolution ensures agents share accurate, up-to-date knowledge stale facts are detected and resolved at ingestion, not left for the LLM to guess.

2 best points · 0 comments · 1 Hacker News post · 9 GitHub stars · View on GitHub

Hacker News discussions

• Mnemos – Open-source memory layer with typed conflict resolution for AI agents (2 points, 0 comments, by Soham2809, 2026-03-19)