evo

by evo-hq · Codex Skill · ★ 719

About evo

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.

agent-skillsautonomous-agentsautoresearchclaude-codecode-optimizationcodexevolutionary-algorithmsllm-agents

Quick Facts

Stars719
Forks59
LanguagePython
CategoryCodex Skill
LicenseApache-2.0
Quality Score55.468/100
Open Issues6
Last Updated2026-05-21
Created2026-04-05
Platformsclaude-code, codex, python
Est. Tokens~1019k

More Codex Skill Tools

Explore other popular codex skill tools:

View all Codex Skill tools →

Popular Python Agent Tools

Frequently Asked Questions

What is evo?

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.

What programming language is evo written in?

evo is primarily written in Python. It covers topics such as agent-skills, autonomous-agents, autoresearch.

How do I install or use evo?

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.

What license does evo use?

evo is released under the Apache-2.0 license, making it free to use and modify according to the license terms.

View on GitHub → Browse Codex Skill tools