Auto-claude-code-research-in-sleep
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.
Install
- Stars
- ★ 18k
- License
- MIT
- Language
- Python
- Last push
- Oct 24, 2026
- Topics
- ai-research · ai-tools · aris · autonomous-agent · codex
Good for
- Automate ML research with cross-model review loops: one model executes, an independent model reviews
- Discover and screen research ideas
- Automate experiments
- Draw method diagrams with /method-figure
Getting started
- Install with npx skills add wanshuiyin/Auto-claude-code-research-in-sleep
- Follow Quick Start step 2 to register the codex MCP server used as reviewer (Codex by default), or choose another model combination
- Run the research workflow from Claude Code, Codex or another supported agent
Before you install
Markdown-only skills with no framework lock-in. codex-cli 0.154.0 removed codex mcp-server, so existing installs need one re-registration (Quick Start step 2b); alternative combinations such as ModelScope-hosted models need no Claude or OpenAI API.
Summarized by AI from the project docs; check the official docs before relying on it.
Similar tools
- AI-Research-SKILLsCommunity skills · ★ 13.9k
Comprehensive open-source library of AI research and engineering skills for any AI model. Package the skills and your claude code/codex/gemini agent will be an AI research agent with full horsepower. Maintained by Orchestra Research.
- reaCommunity skills · ★ 380k
Reverse engineer anything with agents, from app behavior down to native binaries.
- agent-skillsCommunity skills · ★ 110k
Production-grade engineering skills for AI coding agents.
- paperclipCommunity skills · ★ 107k
The open-source app everyone uses to manage agents at work
- taste-skillCommunity skills · ★ 102k
Agent skills that give coding agents taste: art direction, reference images and a browser check instead of generic AI pages
Source GitHub · All rights belong to the original creators