mcp-server

ARIS: Automate ML Research

Get autonomous ML research with ARIS.
intermediate30 minutes💵 Free (self-hosted)
15,251 stars1,338 forksPythonGuide quality 8/10Updated 8/26/2026100% free · open source
What it is

Use ARIS to automatically discover and validate machine learning (ML) ideas.

Real use case example

"A founder named Alex wants to explore building a chatbot that understands user intent. They create an ARIS automation to cross-review ML models, identify patterns, and set up experiments with Codex. After a few days, ARIS provides Alex with potential chatbot architectures and code snippets, saving them weeks of research time."

Best insideClaude CodeClaude DesktopCodex CLI
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
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
Use with Claude
New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

⚡ Runs out of the box

A prompt/skill package — nothing to install beyond adding it to your AI tool.

Try it instantly — no install
Claude Code
mkdir -p ~/.claude/skills/auto-claude-code-research-in-sleep && curl -fsSL https://workflowstacks.com/api/skills/auto-claude-code-research-in-sleep/claude-skill -o ~/.claude/skills/auto-claude-code-research-in-sleep/SKILL.md
Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)
claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How ARIS: Automate ML Research works
Codeflow
Free to inspect

ARIS: Automate ML Research is mostly documents (409 doc files, 81 small scripts) — something you read, not something you run. You install it into your AI tool with one command; there is nothing to run yourself. Last commit this month, MIT license.

Size
Mostly documents
409 documents · 81 small scripts · days to read — use, don't read
Setup
Install as a skill / plugin
Add it to Claude Code (or your AI tool) with one command — 187 skills inside. Nothing to run yourself.
Runs on
Inside your AI tool
Nothing to install on your machine · needs API keys
Python 75%Shell 13%HTML 8%PowerShell 3%
Where to start reading
  1. 1
    README.md
    Start here — what it does and how to install it
  2. 2
    .env.example
    The API keys and settings you must provide
  3. 3
    skills/ablation-planner/SKILL.md
    Inside skills/ — an example of what the AI is told to do
What's in each folder
skills/Prompts, skills & agent definitions345 files
docs/Documentation178 files
templates/Templates21 files
tools/Helper scripts47 files
mcp-servers/Folder16 files
aris-monitor/Folder8 files
community_papers/Folder1 files
tests/Tests — proof it works61 files
READMEHas testsDocumentedCI checksMIT licenseUpdated this month
Quick Actions
Details
Creator
wanshuiyin
Language
Python
Category
mcp-server
Published
3/10/2026

Are you the creator of this tool? Claim your listing → and earn 85% of every sale.

Ready-to-run pack · one-time $29

Review Watchdog

Catch every bad review the day it lands — with a reply ready.

Includes the tested workflow and a written setup playbook. Needs: Google Places API key (free tier).

See what you get