Recursive Self-Improvement for AI agents and models, helping your agents self-improve with every run
Latest release v0.2.0 — v0.2.0 — Continual Learning Infrastructure · 29 May 2026
1 file for Claude Code: amfs CLAUDE.md — 3,099 tokens loaded in every session.
CLAUDE.md A 3,099 tok These files are raia-live/amfs's own configuration — they tell Claude Code how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.