ARIS: AI That Does ML Research While You Sleep
ARIS: Let AI Do Your ML Research While You Sleep
Auto-Research-In-Sleep (ARIS) is a revolutionary Claude Code skill collection that automates the entire machine learning research lifecycle. With 5.4K GitHub stars and papers accepted at AAAI 2026, this is production-proven autonomous research.
🚀 What ARIS Does (While You Sleep)
- /idea-discovery: Literature survey → 8-12 ideas → novelty check → GPU pilots → ranked report
- /auto-review-loop: GPT-5.4 reviews paper (5/10→7.5/10) → writes experiments → deploys to GPU → rewrites
- /paper-writing: Narrative → claims matrix → figures → LaTeX → submission-ready PDF
- /rebuttal: Parse reviews → strategy → safe draft → GPT stress test → PASTE_READY.txt
- /research-pipeline: Full end-to-end: idea → paper → submit
🎯 Real Results
| Paper | Score | Venue | Built With |
|---|---|---|---|
| CS Paper | 8/10 "clear accept" | CS Conference | Claude + GPT-5.4 |
| AAAI Paper | 7/10 "good paper" | AAAI 2026 | Pure Codex CLI |
🔥 Key Features
- Cross-model adversarial review: Claude executes, GPT-5.4 critiques (beats self-play)
- GPU automation: Local/remote/Vast.ai rental, auto-debug + retry
- Zero dependencies: Pure Markdown SKILL.md files
- Multi-platform: Claude Code, Codex CLI, Cursor, Trae, Antigravity, OpenClaw
- Free alternatives: GLM-5 + MiniMax-M2.7 (no Claude/OpenAI API needed)
🎮 Quick Start (5 Minutes)
git clone https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep.git
mkdir -p ~/.claude/skills/
cp -r skills/* ~/.claude/skills/
claude
Then:
/research-pipeline "factorized gap in discrete diffusion LMs"
🛠️ Workflows
Workflow 1: /idea-discovery "discrete diffusion models" → literature + 8 ideas + pilots
Workflow 2: /auto-review-loop "my paper topic" → 4-round improvement loop
Workflow 3: /paper-writing NARRATIVE_REPORT.md → ICLR/NeurIPS PDF
Workflow 4: /rebuttal "paper/ + reviews" — venue: ICML
🌙 No GPU? No Problem
- Modal serverless GPU:
gpu: modal(community contribution) - Vast.ai rental:
gpu: vastauto-rents/destroys - ModelScope free tier: 2000 calls/day
📈 Why It Works
Single-model self-review = local minima. ARIS uses adversarial collaboration:
Claude Code (fast execution) × GPT-5.4 xhigh (rigorous critique)
Real score progression (overnight run):
| Round | Score | What Happened |
|---|---|---|
| Initial | 5.0/10 | Borderline reject |
| Round 4 | 7.5/10 ✅ | 20+ GPU experiments, narrative pivot |
🎉 Community Power
- 32 contributors, 12 community skills (proof-writer, paper-poster, grant-proposal)
- Featured: PaperWeekly, awesome-agent-skills, AI Digital Crew
- Adaptations: OpenClaw, Cursor, Trae (ByteDance), Antigravity (Google)
🚀 Get Started Today
cd your-research-project
/research-pipeline "your research direction" — difficulty: nightmare
Wake up to a submission-ready paper. ARIS doesn't replace your insight - it amplifies it 10x.
⭐ GitHub Repo | 📖 Full Docs