by proyecto26 · Claude 技能 · ★ 7
Autoresearch AI Plugin Autonomous Experiment Loops for Claude Code — Let AI optimize while you sleep Edit code → commit → run benchmark → measure metric → keep improvement or revert → repeat forever. Works for any optimization target: LLM training loss, test speed, bundle size, build time, Lighthouse scores, and more. Inspired by Karpathy's autoresearch, pi-autoresearch, and litesearch. Skills This plugin provides two skills that work together. Autoresearch is the core engine (works for any metric), and Autoresearch ML extends it with GPU-specific templates for LLM training.
| Stars | 7 |
| Forks | 0 |
| Language | Python |
| Category | Claude 技能 |
| License | MIT |
| Quality Score | 37.25/100 |
| Last Updated | 2026-04-07 |
| Created | 2026-03-21 |
| Platforms | claude-code, python |
| Est. Tokens | ~8k |
Explore other popular claude 技能 tools:
autoresearch-ai-plugin is A Claude Code plugin for Autoresearch with AI to improve anything!. It is categorized as a Claude 技能 with 7 GitHub stars.
autoresearch-ai-plugin is primarily written in Python. It covers topics such as ai-agent, autonomous-agents, autoresearch.
You can find installation instructions and usage details in the autoresearch-ai-plugin GitHub repository at github.com/proyecto26/autoresearch-ai-plugin. The project has 7 stars and 0 forks, indicating an active community.
autoresearch-ai-plugin is released under the MIT license, making it free to use and modify according to the license terms.