Self Improving Agent Builder

Encodes a continuous improvement loop for goal-seeking agents: EVAL, ANALYZE, RESEARCH (hypothesis + evidence + counter-arguments), IMPROVE, RE-EVAL, DECIDE. Auto-commits improvements (+2% net, no regression >5%) and reverts failures. Works with all 4 SDK implementations. Auto-activates on "improve agent", "self-improving loop", "agent eval loop", "benchmark agents", "run improvement cycle".

rysweet Updated 76 repo stars

File contents

rysweet/amplihack commit b333152903

Frequently asked questions

npx get-skill add rysweet/self-improving-agent-builder