evo-hq/evo
480 stars · Last commit 2026-04-16
A plugin for Claude Code and Codex that turns your codebase into an autoresearch loop — discovers what to measure, instruments the benchmark, then runs tree search with parallel subagents.
README preview
<p align="center"> <img src="assets/banner.png" alt="evo banner" width="100%" /> </p> # evo A plugin for [Claude Code](https://docs.anthropic.com/en/docs/claude-code) and [Codex](https://developers.openai.com/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](https://github.com/karpathy/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.** Multiple directions can fork from any committed node, so exploration doesn't collapse to one path. - **Parallel semi-autonomous agents.** Spawn multiple subagents and run them simultaneously, each in its own git worktree. Each subagent reads traces, formulates hypotheses, and can run multiple iterations within its branch. - **Shared state.** Failure traces, annotations, and discarded hypotheses are accessible to every agent before it decides what to try next. - **Gating.** Regression tests or safety checks can be wired up as a gate. Experiments that don't pass get discarded. - **Observability.** A dashboard to monitor your experiments. - **Benchmark discovery.** `evo:discover` explores the repo, figures out what to measure, and instruments the evaluation. ## Install Common requirements: Python 3.12+, git, [uv](https://docs.astral.sh/uv/).