# Alpha evolve

> Alpha evolve is an open-source agent skill. Use when the user wants to evolve an ML model/program through population-based search rather than a single sequential refine loop — a genera. It is available on Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, Windsurf and Goose.

- **Kind:** Skill
- **Pricing:** Open source
- **Platforms:** Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, Windsurf, Goose
- **Website:** https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/alpha-evolve
- **Repository:** https://github.com/gaasher/agent-loop-skills
- **GitHub stars:** 183
- **License:** MIT
- **Skill name:** alpha-evolve
- **Collection:** https://github.com/gaasher/Agent-Loop-Skills
- **Listing updated:** 2026-11-17

## About

Use when the user wants to evolve an ML model/program through population-based search rather than a single sequential refine loop — a generational evolution where parallel proposers each apply one small SEARCH/REPLACE diff to a parent, scored by a cascade-evaluated training run, and children are kept in a MAP-Elites archive across islands (with migration + checkpointing) so diverse high performers survive. A finite, bounded-parallelism re-creation of AlphaEvolve/OpenEvolve, bent for ML autoresearch. Runs to a fixed compute budget or until interrupted. Not for the sequential single-thread autoresearch loops (one change → measure → keep/revert), and not for verifying a known bug or external claim — this is parallel, diversity-preserving search over a program.

## When your agent uses it

> Use when the user wants to evolve an ML model/program through population-based search rather than a single sequential refine loop — a generational evolution where parallel proposers each apply one small SEARCH/REPLACE diff to a parent, scored by a cascade-evaluated training run, and children are kept in a MAP-Elites archive across islands (with migration + checkpointing) so diverse high performers survive. A finite, bounded-parallelism re-creation of AlphaEvolve/OpenEvolve, bent for ML autoresearch. Runs to a fixed compute budget or until interrupted. Not for the sequential single-thread autoresearch loops (one change → measure → keep/revert), and not for verifying a known bug or external claim — this is parallel, diversity-preserving search over a program.

## What it can access

From a static check of the files on GitHub; nothing was run.

- [Instructions only, no scripts](https://github.com/gaasher/Agent-Loop-Skills/tree/HEAD/loops/alpha-evolve)
- [License: MIT](https://github.com/gaasher/Agent-Loop-Skills/tree/HEAD/loops/alpha-evolve)

## Install

### Claude Code

This skill ships in the `agent-loops` plugin. In Claude Code, add the marketplace and install the plugin (it may include other skills too):

```sh
/plugin marketplace add gaasher/Agent-Loop-Skills
/plugin install agent-loops@agent-loop-skills
```

Or copy only this skill to `~/.claude/skills/alpha-evolve`:

```sh
tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/gaasher/Agent-Loop-Skills.git "$tmp" &&
mkdir -p ~/.claude/skills &&
rm -rf ~/.claude/skills/alpha-evolve &&
cp -R "$tmp/loops/alpha-evolve" ~/.claude/skills/alpha-evolve &&
rm -rf "$tmp"
```

For one project only, put the folder in `.claude/skills/alpha-evolve` inside it instead.

### Codex

Copy the skill folder to `~/.agents/skills/alpha-evolve` to use it in every repository:

```sh
tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/gaasher/Agent-Loop-Skills.git "$tmp" &&
mkdir -p ~/.agents/skills &&
rm -rf ~/.agents/skills/alpha-evolve &&
cp -R "$tmp/loops/alpha-evolve" ~/.agents/skills/alpha-evolve &&
rm -rf "$tmp"
```

For one repository only, put the folder in `.agents/skills/alpha-evolve` inside it instead.

### Cursor

Copy the skill folder to `~/.cursor/skills/alpha-evolve` to use it in every project:

```sh
tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/gaasher/Agent-Loop-Skills.git "$tmp" &&
mkdir -p ~/.cursor/skills &&
rm -rf ~/.cursor/skills/alpha-evolve &&
cp -R "$tmp/loops/alpha-evolve" ~/.cursor/skills/alpha-evolve &&
rm -rf "$tmp"
```

For one project only, put the folder in `.cursor/skills/alpha-evolve` inside it instead.

### Gemini CLI

Run in a terminal (add `--scope workspace` to install it for the current workspace only):

```sh
gemini skills install https://github.com/gaasher/Agent-Loop-Skills.git --path loops/alpha-evolve
```

Or copy the folder to `~/.gemini/skills/alpha-evolve` yourself.

### VS Code

For GitHub Copilot in VS Code, copy the skill folder to `~/.copilot/skills/alpha-evolve`:

```sh
tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/gaasher/Agent-Loop-Skills.git "$tmp" &&
mkdir -p ~/.copilot/skills &&
rm -rf ~/.copilot/skills/alpha-evolve &&
cp -R "$tmp/loops/alpha-evolve" ~/.copilot/skills/alpha-evolve &&
rm -rf "$tmp"
```

For one project only, put the folder in `.github/skills/alpha-evolve` inside it instead.

### Other agents

Get the folder:

```sh
git clone --depth 1 https://github.com/gaasher/Agent-Loop-Skills.git
```

Then copy `Agent-Loop-Skills/loops/alpha-evolve` into your agent's skills folder as `alpha-evolve`. Agents that support SKILL.md read one folder per skill.

## FAQ

### How do I install Alpha evolve in Claude Code?

Copy the skill folder from GitHub to ~/.claude/skills/alpha-evolve to use it in all your projects, or to .claude/skills/alpha-evolve in one project. Or install the agent-loops plugin, which includes it: /plugin marketplace add gaasher/Agent-Loop-Skills, then /plugin install agent-loops@agent-loop-skills.

### Does Alpha evolve run scripts?

No. It is instructions only, with no scripts. This comes from a static check of the files on GitHub; nothing was run. Read the files before you install it.

### Which AI agents can use Alpha evolve?

Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, Windsurf and Goose. Each reads skills in the SKILL.md format from its own folder; the install steps on this page list them.

---
Source: https://ai-powered.com/skills/alpha-evolve
