krapcys1-maker/adaptive-agent-memory-research

Open research on long-term memory for LLM agents: local-first, model-agnostic, preregistered where possible, negative results kept. Current work: a writer-memory benchmark, a one-file memory module and a synthetic-life generator (in progress). Newcomers welcome: start with the issue "Status and where help is wanted".

4 best points · 0 comments · 1 Hacker News post · 7 GitHub stars · View on GitHub

Hacker News discussions

• Show HN: Offline project memory for coding agents – no API key, no vector DB (4 points, 0 comments, by krapcys, 2026-11-01)