Progress will not be saved. This browser is blocking storage (often private browsing). You can still learn, but closing the tab loses your progress.
wanshuiyin/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
- 19,555
- +7 days
- —
- Forks
- 1,564
- Language
- Python
- License
- MIT
- Last push
- 19 Nov 2026
Summary
Summary written by AI from the README; it may be imprecise.This collection provides Markdown-based skills and tooling for autonomous machine learning research using Claude Code and other agent environments. It organizes multi-model workflows where an executor agent handles experiments and writing while an independent model reviews findings and code. Developers can automate iterative idea exploration, paper reviews, and implementation cycles without relying on heavy external frameworks.
Use it when
- When automating machine learning experiments and paper exploration through agent workflows
- Setting up cross-model review loops between Claude Code and external models via MCP server
- Running end-to-end autonomous research pipelines with minimal framework overhead
Install
/plugin marketplace add openai/codex-plugin-cc/plugin install codex@openai-codexclaude mcp add codex -s user -- python3 "$(pwd)/Auto-claude-code-research-in-sleep/mcp-servers/codex-exec/server.py"Commands quoted from the repo's README. Read the README before running them.
Needs a token or API key.
Stars over 90 days
Collecting: 2 of 90 days so far. The chart appears after 7 days.