wanshuiyin/Auto-claude-code-research-in-sleep

Registry

Summary

ARIS (Auto-Research-In-Sleep) is a lightweight, Markdown-only skill set for autonomous machine learning research. It enables cross-model review loops, idea discovery, and experiment automation without any framework lock-in, working seamlessly with Claude Code, Codex, OpenClaw, or any LLM agent.

Key features

• Markdown-only skill design with no framework dependency
• Cross-model review loops for automated paper and idea evaluation
• Idea discovery and experiment automation for ML research
• Compatible with Claude Code, Codex, OpenClaw, and any LLM agent
• Lightweight and lock-in-free architecture

Use cases

• Automated ML paper review and idea generation
• Autonomous experiment design and execution
• Cross-model research validation and comparison
• Rapid prototyping of research workflows without framework overhead
• Integration with Claude Code for sleep-mode research automation

README excerpt

# Auto-claude-code-research-in-sleep (ARIS ⚔️🌙) <p align="center"> <a href="https://huggingface.co/papers/2605.03042"> <img src="docs/hf_daily_paper_1.svg" alt="Hugging Face Daily Paper · #1 Paper of the Day" width="360"> </a> </p> [](https://huggingface.co/papers/2605.03042) · [](https://wanshuiyin.github.io/Auto-claude-code-research-in-sleep/ARIS_INTRO.html) · [](docs/aris_intro_slides.pdf) · [](AGENT_GUIDE.md) · [](https://mp.weixin.qq.com/s/tDniVryVGjDkkkWl-5sTkQ) · [](https://github.com/VoltAgent/awesome-agent-skills) · [-orange?style=flat)](https://aidigitalcrew.com) · [](https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep/stargazers) · [💬 Join Community](#community) · [![Cite](htt

Topics