autoresearch
by uditgoenka (personal account)
Claude Autoresearch Skill — Autonomous goal-directed iteration for Claude Code. Inspired by Karpathy's autoresearch. Modify → Verify → Keep/Discard → Repeat forever. (description from the project’s GitHub page)
Repository facts
- Stars
- 6,578
- Forks
- 483
- Open issues and pull requests
- 8
- Primary language
- Shell
- License
- MIT License (MIT)
- Owner
- uditgoenka · Personal account
- Created
- Mar 13, 2026
- Last push
- Aug 12, 2026
Topics
Add this badge to your README
Shows this repository’s rank in AI on GitHub and links back to this page. Ranks are by stars and change when the list is refreshed. The badge is not an endorsement or a rating. About the badges
Markdown (for a README)
[](https://unitedstatesofamericasuperintelligence.com/github/uditgoenka--autoresearch/)
HTML
<a href="https://unitedstatesofamericasuperintelligence.com/github/uditgoenka--autoresearch/"><img src="https://unitedstatesofamericasuperintelligence.com/badges/github/uditgoenka--autoresearch.svg" alt="Ranked #1,223 in AI on GitHub" height="20"></a>
Related projects
Projects that share this one’s GitHub topics.
Rank 2,663: leo-lilinxiao/codex-autoresearch
Codex Autoresearch Skill — A self-directed iterative system for Codex that continuously cycles through: modify, verify, retain or discard, and repeat indefinitely. Inspired by Kar…
2,957 starsPythonMITLast push Sep 12, 2026
Rank 1,986: Leonxlnx/unlazy
Anti-laziness skill for AI agents. Core: the Depth Tree method, which splits a task N layers deep and gives every leaf the full time budget of the whole task, so effort multiplies…
3,983 starsJavaScriptMITLast push Sep 3, 2026
Rank 5,061: greyhaven-ai/autocontext
a recursive self-improving harness designed to help your agents (and future iterations of those agents) succeed on any task
1,309 starsPythonApache-2.0Last push Oct 14, 2026
Rank 8,937: tzachbon/smart-ralph
Spec-driven development with smart compaction. Claude Code plugin combining Ralph Wiggum loop with structured specification workflow.
559 starsShellMITLast push Sep 16, 2026
Rank 32: JuliusBrussee/caveman
🪨 why use many token when few token do trick. Viral skill + proxy for coding agents that cuts 65% of tokens by talking like a caveman.
113,414 starsGoApache-2.0Last push Oct 18, 2026
Rank 1,303: ZSeven-W/openpencil
The world's first open-source AI-native vector design tool and the first to feature concurrent Agent Teams. Design-as-Code. Turn prompts into UI directly on the live canvas. A mod…
6,217 starsRustMITLast push Oct 18, 2026