DEDUPED Hot AI repos, turned into use cases Get the Monday 5

How to run an open AI Scientist system on a test question with Awesome AI Scientist

Pick a linked end-to-end system and run it on one small research question.

  • Top pick
  • Research
  • Advanced
  • 3 hours
  • From the README
  • Any agent

Authorization notice. Awesome AI Scientist is dual-use. Only use it on software, sites and systems you own or have explicit permission to test.

Remote script. Linked research systems run code and may call external services, so review each project's code before running it on your machine.

Who it is forA graduate student or ML engineer who wants to see how an end-to-end AI Scientist behaves before using one in their own lab.

The problemThere are many AI Scientist systems, and it is hard to tell which ones have public code you can run.

The outcomeYou have one working end-to-end system, a short note on its setup effort, and a sample output from a test question.

What you need first

  • A web browser to read the README and follow GitHub links
  • A GitHub account if you plan to clone or fork a linked repository
  • A Python environment for running any linked project (the list is tagged Python)
  • Time to read each linked project's own README, since this list does not contain install instructions

Steps

  1. Open the End-to-End AI Scientists section of the README.
  2. Pick an entry whose badge links to a GitHub repository, such as The AI Scientist or data-to-paper.
  3. Open that repository and read its own README, because this list does not give setup steps.
  4. Clone the chosen repository with git and create a Python environment for it. (inferred, check the README)
  5. Run the project on one small test research question and save the output for review.

Prompt for your agent

Using the README of Omni-Scientist/Awesome-AI-Scientist, list the End-to-End AI Scientists entries that link to a GitHub repository and fit the research question <research question>. Return each system name, its paper link and its repository link, and confirm each repository link appears in the README before reporting it.

Caveat. This list links to projects but does not include their setup steps, so each project's own README decides what you need to install.

Use this in your AI agent

Ask your agent

Using the Deduped MCP, get the setup steps for Omni-Scientist/Awesome-AI-Scientist and "Run an open AI Scientist system on a test question"

Add Deduped to Claude Code once

claude mcp add --transport http deduped https://dedupedai.com/mcp

Cursor, ChatGPT, others

Share: X LinkedIn Hacker News Email Copy link

Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer