autoresearch

autoresearch is an open-source productivity skill for Claude Code and compatible agents, published by github. Its author describes it as: “Autonomous iterative experimentation loop for any programming task. Guides the user through defining goals, measurable metrics, and scope constraints, then runs an autonomous loop of code changes, testing, measuring,…”. The project has 38k stars on GitHub and is available under the MIT license. Add it to your setup with `git clone https://github.com/github/awesome-copilot ~/.claude/skills/autoresearch`.

What autoresearch does

An autonomous experimentation loop for any programming task. You define the goal and how to measure it; the agent iterates autonomously -- modifying code, running experiments, measuring results, and keeping or discarding changes -- until interrupted.

Installation

Add autoresearch to your agent with:

git clone https://github.com/github/awesome-copilot ~/.claude/skills/autoresearch

Always review a skill's source before installing it. This command comes from the skill's public repository; the linked repo is the source of truth for exact setup steps.

What's inside

The SKILL.md for autoresearch is organised into these sections:

• Agent Behavior Rules
• Phase 1: Setup (Interactive)
• 1.1 Define the Goal
• 1.2 Define the Metric
• 1.3 Define the Scope
• 1.4 Define Constraints
• 1.5 Define the Experiment Budget (Optional)
• 1.6 Simplicity Criterion
• 1.7 Confirm Setup
• Phase 2: Branch & Baseline
• Phase 3: Experiment Loop
• For each experiment:

When to use it

Reach for autoresearch when you want productivity help from your agent without writing the same instructions every session. Load the skill and the agent picks it up automatically for relevant tasks.

Strengths

• Clear MIT license — safe to read and adapt
• Ships in github/awesome-copilot, an established project with 37,982 GitHub stars
• Actively maintained (recent commits)

Topics

Frequently asked questions

What does autoresearch do?

Autonomous iterative experimentation loop for any programming task. Guides the user through defining goals, measurable metrics, and scope constraints, then runs an autonomous loop of code changes, testing, measuring, and keeping/discarding results. Inspired by Karpathy's autoresearch. USE FOR: autonomous improvement, iterative optimization, experiment loop, auto research, performance tuning, automated experimentation, hill climbing, try things automatically, optimize code, run experiments, autonomous coding loop. DO NOT USE FOR: one-shot tasks, simple bug fixes, code review, or tasks without a measurable metric.

How do I install autoresearch?

Run git clone https://github.com/github/awesome-copilot ~/.claude/skills/autoresearch in your agent, then reload your skills. Review the source at https://github.com/github/awesome-copilot before installing.

Is autoresearch free to use?

Yes. autoresearch is free and open source under the MIT license, so you can read, run, and adapt it within that license's terms.

Where does autoresearch come from?

autoresearch ships inside github/awesome-copilot, a repository that contains 41 catalogued skills in total. The repository's 37,982 GitHub stars apply to that whole collection, not to this skill on its own.