Toolbox/ML experiment agents/wanshuiyin/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.

View on GitHub →
PythonMITai-researchautonomous-agentclaude-codecodexmcp
Stars
17.8k
Δ 7d
+378
Δ 30d
+1,381
Age
7 mo
Last push
4h ago
18k17k16k15k13kJul 24Sep 6Oct 21
90-day star history

Where this sits in the catalog

Most-wanted open issues

Ranked by 👍 reactions. 58 open issues total, checked 2026-10-15.

Head to head with its peers

The same six axes and the same star history, two projects at a time.

Alternatives in ML experiment agents

The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery 🧑‍🔬

⭐14.8k
+547d
Jupyter Notebook
2 yrs

Open-source implementation of AlphaEvolve

⭐7.6k
+647d
Python
1 yr

The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search

⭐7.4k
+467d
Python
1 yr

🔬 Harness Vibe Research with Self-evolving AI Scientists

⭐5.0k
+207d
Python
8 mo

Now, Stronger AI Pushes Frontiers, Stronger Our Shared Future.

⭐3.4k
+117d
TypeScript
1 yr

AIDE: an LLM agent for machine learning engineering - the research Weco grew out of. Referenced in OpenAI MLE-…

⭐1.6k
+147d
Python
2 yrs