Runs a research agent for scientists that reviews literature, writes and runs analysis code, and reproduces experiments, from a desktop app, browser workspace, or CLI.
Use it now
Keep it with up to 9 other tools you're setting up, then share them all as one link.
Try this first
Ask your coding agent:
- Literature Review
Use OpenScience to search scientific sources: ‹what you're looking for›
- Data Analysis
Use OpenScience to inspect input data: ‹what you need›
- Remote Compute
Use OpenScience to send long or GPU-bound jobs: ‹what you need›
Install the CLI
Install it as its own instructions say.
Call the API
Auth An API key from Synthetic Sciences
Compare
Press Compare to add it to the tray at the bottom of the window, then pick up to 2 others anywhere on the site.
- Access
- CLIAPI
- Auth
- API Key
- Skills
- 5
Skills
Literature Review
Searches scientific sources, compares findings, and saves cited evidence, with connectors to databases such as PubMed, arXiv, and UniProt.
Data Analysis
Inspects input data, writes and runs analysis code in shell, Python, or R kernels, and produces figures and reports in the project folder.
Experiment Reproduction
Agrees on a claim, its prerequisites, and a budget with you, then reruns the experiment and compares the measured results to the claim.
Remote Compute
Sends long or GPU-bound jobs to Modal, SSH hosts, or Slurm and PBS clusters, with each dispatch approved by you before it runs.
Headless Runs
Runs a single research turn from a script or pipeline with openscience run, and continues the same session with the --continue flag.