Introducing Atlas: infrastructure for autonomous, open science. Research is about to change more in the next two years than it has in the last fifty, and the infrastructure underneath isn't ready. We’re building Atlas to be that layer. First piece is live today: Atlas Graph.

(2/7) Science still runs on a format built for people, not agents: the paper. A paper compresses months of work into something you can read in 30 minutes. That's the point of it, and also the problem: you keep the result and lose the work behind it. The runs that failed, the setup it actually took to get to the result, the directions you ruled out. That was a fair trade back when experiments were slow and expensive and run by hand.

(3/7) That stopped being the world we live in. Today, you hand a problem to a coding agent or an autoresearch loop and it comes back with hundreds of runs, each one tuned off the last. Automated research doesn't stop at a result — it reproduces, verifies, branches, and extends, at the speed of compute. The paper adds friction to each of those steps: - Reproducing a single result, even one with public code, can eat days: a hyperparameter nobody saved, an environment that won't build, a dataset version nobody wrote down. - Once everyone on a team is running hundreds of experiments a day, collaboration falls apart. - And the field can't keep up with itself: ICML went from ~12k submissions to ~24k in a year. No reviewer pool can check that, and plenty of it is slop.

(4/7) So we rebuilt the unit. In an Atlas Graph the unit is the research step, not the paper. Every step is a node: a hypothesis, an experiment, a decision on what's next. Each node carries its own provenance, where it came from and what it ruled out, and your agents write to the graph as they work, so none of it has to be reconstructed later. That's what makes the work easy to check and to build on. Fork a public graph and start where someone else called things off. Verify a result in peer review with the exact code and environment behind it. Share one with your lab so a hundred experiments a day don't turn into chaos.

(5/7) Reproduction shouldn't be a project. Give Atlas an arXiv id and the reproduce skill rebuilds the result as a graph, stripped to what runs, and asks you for what the PDF left out instead of guessing. That graph becomes your starting point. Point autoresearch at any node and extend it: take an experiment further, optimize for a metric, push in directions the authors ruled out. Your runs join the same graph, and someone else forks it from there.

(6/7) Atlas Graphs are the first piece. Atlas is the full stack for agent-native research: the graph the work lives in, a library that grounds agents in live sources instead of stale training data, managed compute to run experiments at scale, and an SOTA agent harness.

(7/7) And it runs on whatever you're already using. Atlas is a CLI. Bring Claude Code, Codex, Cursor, or your own agent. Get 1 month free with a .edu email. npm i -g @synsci/atlas

congrats on launching!

Congrats on the launch!!

crazy team! Installing right now. What’s the first thing I should try to research @ishaangangwanii ?

Curious how many hours this saves for teams doing reproduction-heavy research.

only works with papers on arXiv ?

congrats team!

Very interesting

Hi! Glad this popped up today. Nice one.

Hello! Really pleasant to read this one.

Many many congratulations on launching aayu beta Great going 👍👍👍

The hidden bottleneck for autonomous science isn't generating new graphs; it's deterministic validation. If AI agents dynamically expand knowledge graphs without real-time, verifiable logic constraints, we just accelerate the replication crisis at scale.

Will change the way research is done and presented

Hey 👋 Let’s grow your project 🚀 DM me 📥

Exciting vision. Building the infrastructure for autonomous science could have a lasting impact on research.

Are you working to integrate Lean, CoQ, Agda, and LaTeX into this workflow? ...because I am.

Glad it resonated, thank you!