Autoresearch — Development skill for Claude Code
Claude Autoresearch Skill — Autonomous goal-directed iteration for Claude Code.
How to install Autoresearch
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open uditgoenka/autoresearch and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Autoresearch does
**Turn [Claude Code](https://docs.anthropic.com/en/docs/claude-code), [OpenCode](https://opencode.ai), or [OpenAI Codex](https://developers.openai.com/codex) into a relentless improvement engine.**
Alternatives in Development
- Andrej Karpathy Skills — 7404 65 1 7.5k ★
- Evo — turns your codebase into an autoresearch loop — discovers what to measure, instruments the benchmark, then run 1.4k ★
- Overnight PRs — Autonomous overnight loop — verify issues against the codebase, close stale ones, ship PRs through /ship (bug 324 ★
README
Autoresearch
**Turn [Claude Code](https://docs.anthropic.com/en/docs/claude-code), [OpenCode](https://opencode.ai), or [OpenAI Codex](https://developers.openai.com/codex) into a relentless improvement engine.**
Based on [Karpathy's autoresearch](https://github.com/karpathy/autoresearch) — constraint + mechanical metric + autonomous iteration = compounding gains.
[](https://docs.anthropic.com/en/docs/claude-code) [](https://opencode.ai) [](https://developers.openai.com/codex) [](https://github.com/uditgoenka/autoresearch/releases) [](LICENSE)
[](https://github.com/karpathy/autoresearch) [](https://x.com/intent/follow?screen_name=iuditg) [](https://paypal.me/uditgoenka)
*"Set the GOAL → The agent runs the LOOP → You wake up to results"*
*You don't need AGI. You need a goal, a metric, and a loop that never quits.*
**Now supports Claude Code, OpenCode, and OpenAI Codex.**
[How It Works](#how-it-works) · [Commands](#commands) · [Quick Start](#quick-start) · [Guides](guide/) · [FAQ](#faq)
PLAN LOOP DEBUG FIX SECURE SHIP
┌──────────┐ ┌──────────┐ ┌──────────┐ ┌──────────┐ ┌──────────┐ ┌──────────┐
│ Goal │ │ Modify │ │ Find │ │ Fix │ │ STRIDE │ │ Stage │
│ Metric │────▶│ Verify │────▶│ Bugs │────▶│ Errors │────▶│ OWASP │────▶│ Deploy │
│ Scope │ │ Keep/ │ │ Trace │ │ Repair │ │ Red │ │ Release │
└──────────┘ │ Discard │ └──────────┘ └──────────┘ │ Team │ └──────────┘
/autoresearch: └──────────┘ /autoresearch: /autoresearch: └──────────┘ /autoresearch:
plan /autoresearch debug fix /autoresearch: ship
security
┌──────────┐ ┌──────────┐ ┌──────────┐ ┌──────────┐
...
Related Skills
Auto Optimize
Self-improving agent optimization — generates challenger variants of any agent/command, benchmarks against bas
Skill Autoimprove
OpenClaw skill auto-improvement system using Karpathy autoresearch loop
Goal Tracking
Self-directed agile goal tracking system — personal kanban, driven by kaizen, 52 goals across 4 domains.
Waterbear
keep a claude remote-control session alive forever (tmux + launchd), optionally resuming the same conversation
Andrej Karpathy Skills
Karpathy-inspired Agent Skills collection
IDEA.Md
IDEA.md — A standard file for portable idea intent in agentic software work. Share the idea, not the code. You
Related Agents
Autoresearch Orchestrator
Use this agent to run an autoresearch experiment session end-to-end — setup, baseline, and a batch of edit→mea
Research Loop
Autonomous iterative research loop — hypothesis, search, ingest, evaluate, keep/discard via checkpoint. Max 3
Decision Loop
Autonomous PIVOT/REFINE/PROCEED decision agent — evaluates iteration results and autonomously decides whether