evo-hq

Evo — Development skill for Claude Code

Development community

turns your codebase into an autoresearch loop — discovers what to measure, instruments the benchmark, then runs tree search with parallel subagents.

How to install Evo

This entry records only its repository, not the path inside it, so there is no exact command to give. Open evo-hq/evo and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Evo does

turns your codebase into an autoresearch loop — discovers what to measure, instruments the benchmark, then runs tree search with parallel subagents.

Alternatives in Development

Research Codebase — You are tasked with conducting comprehensive research across the codebase to answer user questions by spawning 10k ★
Tentacle Planner — You are the Tentacle Planner — a meta-agent that analyzes this codebase and creates department tentacles to or 1.4k ★
Agent Skill — A Claude Code plugin marketplace containing the ast-grep skill for powerful structural code search using Abstr 851 ★

README

evo

[![PyPI](https://img.shields.io/pypi/v/evo-hq-cli)](https://pypi.org/project/evo-hq-cli/) [![License](https://img.shields.io/badge/license-Apache--2.0-blue.svg)](LICENSE) [![Tests](https://github.com/evo-hq/evo/actions/workflows/ci.yml/badge.svg)](https://github.com/evo-hq/evo/actions/workflows/ci.yml) [![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.20447923.svg)](https://doi.org/10.5281/zenodo.20447923)

**Get started with autoresearch on any codebase - with two simple commands.**

Do you want to do more with autoresearch or need a custom, hands-on deployment? [Request access to evo platform](https://evo-hq.com/beta) or email [hello@evo-hq.com](mailto:hello@evo-hq.com).

**[Try it](#try-it)** · **[Install](#install)** · **[How it works](#how-it-works)** · **[Dashboard](#dashboard)** · **[Upgrading](#upgrading)**

A plugin for your agentic framework 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 disc