Read papers and work with code
Reads scientific papers and writes and runs code as part of a research workflow.
Loading page…
Research / product dossier
Open-source research agent that reads papers, runs code and tracks experiments.
Product brief
OpenScience is an open-source AI agent for scientific research. It reads papers, writes and runs code, works in notebooks and a terminal, and sends long jobs to Modal, your own servers, or a Slurm/PBS cluster. Give it a metric and Autoresearch runs experiments, logs every one, and keeps hill-climbing. Use 30+ models through one wallet, sign in with ChatGPT, or run a local model. It ranks #1 on agentic scientific research benchmarks. Free and open source.
Why we selected it
An open-source research agent with concrete capabilities for running and tracking experiments. Its support for Modal connects directly to recent infrastructure news.
Product preview saved with our daily selection
Capability scan
Only capabilities supported by the product information we collected are listed here.
Reads scientific papers and writes and runs code as part of a research workflow.
Operates in notebooks and a terminal.
Sends long jobs to Modal, your own servers, or a Slurm/PBS cluster.
Autoresearch takes a metric, runs experiments, logs each one, and continues iterating.
Supports 30+ models through one wallet, ChatGPT sign-in, or a local model.
Best-fit use cases
FAQ
It is an open-source AI agent for scientific research that reads papers, works with code, and runs experiments.
Yes. Its Autoresearch feature accepts a metric, runs experiments, logs each one, and continues iterating.
The description lists Modal, your own servers, and Slurm/PBS clusters.
Yes. The description lists a local model as an option, alongside 30+ models through one wallet and ChatGPT sign-in.