Auto-claude-code-research-in-sleep
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.
- stars
- 16,250
- 30-day movement
- +18261/day
- Related entries
- 120
- Connections
- 1
ARIS (Auto-Research-In-Sleep) is a collection of Markdown-only skills for automating ML research tasks with LLM agents. It provides cross-model review loops, idea discovery, and experiment automation without requiring any framework, and is packaged as an MCP server usable from Claude Code, Codex, OpenClaw, or other agents.
It lets you run research workflows like reviewing and idea generation autonomously through any LLM agent you already use, with no lock-in.
Use it to
- Set up cross-model review loops for papers
- Automate ML experiment pipelines
- Generate research ideas with agents
- Run research tasks unattended in Claude Code or Codex
- Integrate research skills via MCP
For ML researchers using Claude Code, Codex, or similar agents
- Role
- mcp-server
- Language
- Python
- Licence
- MIT
- Forks
- 1,384
- Open issues
- 54
- Last push
- 2026-09-17
- Latest release
- v0.1.0 · 2026-04-02
- Skills shipped
- 82