MerlijnW70/mnema

A fast, secure, local-first memory layer for LLMs — contradiction-resolving writes, injection-resistant retrieval, encrypted at rest, every guarantee ratchet-proven.

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

Hacker News discussions

• Mnema: A local, encrypted memory layer for AI agents (2 points, 0 comments, by MerlijnW70, 2026-07-12)