evo

Transform your codebase into an automated research loop to discover optimization metrics and run tree search.

Agent SkillDevOpen sourceautoresearchcode optimizationparallel agents

Type: Agent Skill
Open source: Yes
GitHub Stars: ★ 1.2k
Source: skill-github
Repository: github.com/evo-hq/evo

Overview

evo is a plugin for agent frameworks that optimizes code through experiments. It identifies metrics needing optimization, sets up evaluation, and begins running experiments in a loop—trying different approaches, keeping improvements, and discarding ineffective ones. evo supports multiple LLMs and remote backends, making it ideal for researchers and developers aiming to automate code optimization.

Capabilities

▪Automatically discover optimization metrics
▪Set up benchmarking
▪Run tree search
▪Multi-directional parallel exploration
▪Shared state management
▪Regression testing and safety checks

Use cases

Code performance optimizationAutomated code researchMulti-agent parallel experimentationContinuous integration and deployment

Setup

Requires: API KeyNode 环境

1. Install evo CLI: `uv tool install evo-hq-cli`
2. Install host CLI (e.g., Claude Code, Codex, Cursor, etc.)
3. Install plugin and host hooks: `evo install <host>`

This information was compiled by AI from public sources and may contain inaccuracies — please refer to the source.

FAQ

Which LLMs does evo support?

Supports Claude Code, Codex, Cursor, OpenClaw, Hermes, Opencode, Pi, and more.

How do I get started with evo?

Run `/evo:discover` to identify benchmarks, then run `/evo:optimize` to begin optimization.

Related skills

gemini-cli

Gemini CLI is an open-source AI agent that brings Gemini's powerful capabilities directly into the terminal.

MCP

private-gpt

Provides a complete API layer for local models, supporting RAG, skills, tools, and more.

MCP

planning-with-files

File-based persistent planning skill, ideal for AI coding agents and long-running tasks.

Agent Skill

scientific-agent-skills

Transform any AI agent into a scientific assistant with 147 ready-to-use research skills.

Agent Skill

susi_alexa_skill

A skill that enables question-and-answer interactions between Alexa and Susi AI.

Agent Skill

claude-context

Provides code search capabilities for Claude Code, turning the entire codebase into context.

MCP