Start with a small dataset or a few papers you know. This makes it easier to check the first result before giving OpenScience a larger task.
1. Install and open OpenScience
Download the desktop app for your operating system and open it. You can also install the command-line app with npm:
npm install -g @synsci/openscience@latest
openscience
openscience opens the browser workspace. To use an existing project folder:
openscience ~/research/my-project
npx synsci@latest is an alternative launcher that installs and opens OpenScience. It requires Node.js and npm.
2. Set up your account, Ace, and connections
The first launch walks through four short steps. The desktop app shows them as
cards; openscience in a terminal asks the same questions inline before it opens
the workspace. Every install sees the setup once.
- Account. Select Continue with Synthetic Sciences. Your browser opens app.syntheticsciences.ai, where you sign up or sign in and choose a workspace you belong to. An account is required; on a machine without a browser, paste a sign-in key instead.
- Ace (recommended, optional). Turn on Ace opens your billing page. Ace access costs $0 to enable, with pay-as-you-go usage and separate consent for automatic reload: managed frontier models, literature search through Firecrawl, scientific schematics and image generation, and one team wallet. OpenScience notices when Ace is on and continues. Skip for now keeps your own keys as the model source.
- Connect your own models (optional). Connect a ChatGPT / Codex subscription, add Anthropic, OpenAI, OpenRouter, Google, or Firecrawl keys, or detect a Modal compute profile. A provider key is checked with its provider before it is saved: a key the provider refuses is not stored, and a provider that cannot be reached saves the key and says it could not be checked. A provider OpenScience already reaches, such as a key in your environment, shows as connected. Keys are stored in an owner-only file on this device.
- Done. Open workspace shows the Projects page. Select New project, open a folder or start blank, and send your first message.
You can change any of these later in Customize.
3. Choose model access
Open Customize → Models and choose the option that fits your setup:
| Option | What to do | What you pay for |
|---|---|---|
| Ace | Sign in, select your funding workspace, and add Wallet funds or enable automatic reloads. | Usage charged to that workspace's Wallet. |
| Your provider | Select Keys & subscriptions, then connect an API key or a supported provider sign-in. | Your provider's usage or subscription terms. |
| Local model | Open Customize → Local models, connect a running endpoint, and select its model. | Your hardware; no Ace model charge. |
First-run setup requires a Synthetic Sciences account. Ace remains optional, and your own provider access or local models remain direct after setup. See Account and workspaces for device access and workspace selection. See Models, Local models, and Pricing for the details.
For terminal setup, run openscience keys add to connect a provider, or openscience local add to connect a local endpoint.
4. Open a project and add your inputs
Create a project or open an existing folder in the workspace. Add the files the task needs and mention them in your request. Keep the original data and ask OpenScience to write results to a separate folder.
Try this request with your own CSV:
Inspect data/measurements.csv and explain each column. Check missing
values, units, and duplicate rows. Save a data-quality report in results/.
Do not change the original dataset.
Without a dataset, try:
Help me plan a literature review on protein language models. Ask about
my research question and inclusion criteria before searching.
5. Review and continue
Read the response and open the files it produced. Check the cited sources, assumptions, and any reported limitations. Continue in the same conversation to refine the result:
Make a plot of the missing-value counts. Explain which columns need
attention before we compare treatment groups.
Use a new conversation for a separate question. Your previous conversations remain available in the project history.
Try a terminal run
openscience run "Summarize the files in this project and suggest a first analysis"
openscience run --continue "Write the analysis plan to results/plan.md"
See Sessions for attachments, continuing a specific conversation, and exporting your work.
Check your setup
openscience --version
openscience doctor
openscience models
If no model is available, finish connecting your provider or local endpoint, then select a model. If Ace is selected, check the funding workspace and Wallet in Customize → Models.