#91 · Primary category: Education & Research

Auto-claude-code-research-in-sleep

ai-research ai-tools aris autonomous-agent claude claude-code claude-code-skills codex deep-learning gpt idea-generation llm machine-learning mcp mcp-server ml-research openai paper-review paper-writing research-automation

ARIS ⚔️ (Auto-Research-In-Sleep) — Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation. No framework, no lock-in — works with Claude Code, Codex, OpenClaw, or any LLM agent.

Project last updated:08/26/26

GitHub Stars

15.4K

Forks

1.3K

Contributors

89

License

MIT

Why we included this project

ARIS (Auto-Research-In-Sleep) automates the repetitive parts of ML research so an agent can keep working while you sleep. It ships as plain-Markdown skills that hand a coding agent like Claude Code or Codex a job: score a draft paper against several model reviewers, flag its weaknesses, propose the next experiment, and save the findings to a research wiki so a long project keeps its thread. Everything is Markdown with no framework and no vendor lock-in, so the skills drop into whichever agent you already run, and the standalone ARIS-Code CLI offers the same workflow for anyone who wants the fuller setup. The agent guide and adapters for Cursor, Copilot CLI, and similar tools keep the initial setup cheap. If your bottleneck is the grunt work around the actual thinking, this is a practical way to hand that loop to a machine while you stay in charge of the direction.

Articles for this project

No articles for this project yet.

To suggest a topic or contribute an article, contact us.

Related projects in this category