by evo-hq · Codex Skill · ★ 719
evo A plugin for Claude Code and Codex that optimizes code through experiments. You give it a codebase. It discovers metrics to optimize, sets up the evaluation, and starts running experiments in a loop -- trying things, keeping what improves the score, throwing away what doesn't. Inspired by Karpathy's autoresearch -- where an LLM runs training experiments autonomously to beat its own best score. Autoresearch is a pure hill climb: try something, keep or revert, repeat on a single branch. Evo adds structure on top of that idea: Tree search over greedy hill climb.
| Stars | 719 |
| Forks | 59 |
| Language | Python |
| Category | Codex Skill |
| License | Apache-2.0 |
| Quality Score | 55.468/100 |
| Open Issues | 6 |
| Last Updated | 2026-05-21 |
| Created | 2026-04-05 |
| Platforms | claude-code, codex, python |
| Est. Tokens | ~1019k |
Explore other popular codex skill tools:
evo is turns your codebase into an autoresearch loop — discovers what to measure, instruments the benchmark, then runs tree search with parallel subagents.. It is categorized as a Codex Skill with 719 GitHub stars.
evo is primarily written in Python. It covers topics such as agent-skills, autonomous-agents, autoresearch.
You can find installation instructions and usage details in the evo GitHub repository at github.com/evo-hq/evo. The project has 719 stars and 59 forks, indicating an active community.
evo is released under the Apache-2.0 license, making it free to use and modify according to the license terms.