Backed by Y Combinator

End-to-End AI Scientist For
ML Researchers

Sciloop automates your end-to-end ML research workflow. Curious about an idea? Shoot it and we'll handle the rest. Built for researchers who care about results, not infrastructure.

Built by MIT undergrads · Automating scientific discovery

The Goal

At Sciloop, we're trying to automate scientific research and discovery to push science to new frontiers. Starting with ML research, we're building tools that let researchers focus on ideas while we handle the experimentation and writing code. We're designing tools we wish existed. Autonomous, and flexible tools that make it easier to do better research quickly, and in a more reproducable manner.

Introducing Sciloop Lab

We are pleased to announce that Sciloop Lab v_0 is available for early access. A cloud native research agent that autonomously conducts machine learning research. Sciloop Lab is designed to handle the entire research lifecycle, from ideation to experimentation and analysis to paper drafting. Built on top of SakanaAI's AI scientist, v_0 takes in an initial codebase and research goal in the form of a experiment template and then autonomously runs experiments, and iterates based on results. We are working on making this more flexible and easy to use.Screenshot of Sciloop Lab v_0We are currently privately onboarding researchers to try out v_0.

Get in touch

Interested in automating some aspect of your ML research?

Tell us about your research needs by booking a time below. We are based in bay area and would love to meet if you're nearby!

If you are an investor interested in learning more about Sciloop, please reach out via email at bilal@sciloop.dev.