autoresearch
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.
Best for Autonomous coding loopsWorks with GitHub
⌘source
- author
@github- language
- Python
★30kstars
3.6kforks
Apr 18, 2026
✦overview.md
Key Features
- ·Autonomous iterative experimentation loop
- ·Defines goals, metrics, and constraints
- ·Modifies code, runs tests, measures results
- ·Keeps or discards changes based on outcomes
- ·Requires git repository and terminal access
Use Cases
- →Autonomous improvement of code performance
- →Iterative optimization of algorithms or functions
- →Running automated experiments to test hypotheses
- →Hill climbing or parameter tuning for code
Best for
- ✓Autonomous coding loops
- ✓Performance tuning tasks
- ✓Automated experimentation
Not ideal for
- !One-shot tasks
- !Simple bug fixes
- !Code review
FAQs
name
autoresearch
description
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.
license
MIT
compatibility:Requires git. The project must be a git repository. Requires terminal access to run commands.
metadata:{"author":"luiscantero","inspired-by":"https://github.com/karpathy/autoresearch"}
Autoresearch: Autonomous Iterative Experimentation
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.
This skill is inspired by Karpathy's autoresearch, generalized from ML training to any programming task with a measurable outcome.
Agent Behavior Rules
- DO guide the user through the Setup phase interactively before starting the loop.
- DO establish a baseline measurement before making any changes.
- DO commit every experiment attempt before running it (so it can be reverted cleanly).
- DO keep a results log (TSV) tracking every experiment.
- DO revert changes that do not improve the metric (git reset to last known good).
- DO run autonomously once the loop starts -- never pause to ask "should I continue?".
- DO NOT modify files the user marked as out-of-scope.
- DO NOT skip the measurement step -- every experiment must be measured.
$install
1-click copynpx skills add github/awesome-copilot --skill autoresearchSafety assessment
★
Clarity score
How clear and easy to understand the SKILL.md instructions are, rated from 1 to 5.
3/ 5
goodMostly clear, but there are still a few confusing or poorly structured parts.
◎
Actionability score
How directly an agent can act on the SKILL.md instructions, rated from 1 to 5.
3/ 5
mediumPartially actionable with several concrete steps, but still missing important details.