Gepa

Runs the GEPA optimization loop (arXiv:2507.19457) — sample-efficient reflective Pareto search. A cheap train-minibatch pre-gate decides whether a proposal is worth an expensive val evaluation, and parents are sampled from a per-instance frontier so specialists survive instead of being averaged away. Use when rollouts are expensive and the scorer returns informative per-task feedback, and you want the most quality per evaluation. Use hill-climb instead for a first baseline run or for feedback-poor binary pass/fail tasks.

skillberry-ai Updated 69 repo stars
Play the 85-second cap-evolve demo — the CLI, four real dashboard tabs, and both benchmark results

File contents

skillberry-ai/cap-evolve commit 9674e2a161

Frequently asked questions

npx get-skill add skillberry-ai/gepa