mcp-server

ARIS: Automate ML Research

Name: ARIS: Automate ML Research
Author: wanshuiyin

Get autonomous ML research with ARIS, for founders. 13k+ GitHub stars.

13,281 stars1,200 forksPythonQuality 8/10Updated 7/12/2026100% free · open source

What it does

Auto-claude-code-research-in-sleep enables autonomous ML research using ARIS, allowing founders to automate cross-model review loops, idea discovery, and experiment automation with lightweight Markdown-only skills

Install / run

git clone https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep.git

When to use it

•When you need to automate ML research tasks without being locked into a specific framework
•When you want to leverage the capabilities of Claude Code, Codex, OpenClaw, or other LLM agents for research
•When you require a lightweight solution for experiment automation and idea discovery

Quick start

1Navigate to the cloned repository: cd Auto-claude-code-research-in-sleep
2Review the README for configuration options and parameters
3Create a Markdown file for your research task, following the guidelines in the README
4Use the ARIS tool to automate your research task, referencing the provided examples and documentation
5Monitor and refine your research task as needed, using the output and insights generated by ARIS

Ready-to-paste prompt

Create a Markdown file named `research_task.md` with the following content: `# Research Task: Automate cross-model review loops for CLIP model comparison`, then run ARIS to automate the research task

Heads up: Ensure you have a compatible LLM agent (such as Claude Code, Codex, or OpenClaw) set up and configured, as ARIS relies on these agents to function

Saves to your device