The desktop app and browser workspace give you the same research workflow: open a project, choose a model, and work through a question in a conversation.
openscience
openscience ~/research/my-project
The first command opens the current folder; the second opens the folder you specify.
Projects and conversations
A project groups related work and files. A conversation, also called a session, holds the requests and results for one task. Start a new conversation for a separate question, or reopen an existing one to continue its work.
Give files descriptive names and tell OpenScience where to save outputs. A new conversation does not automatically know every detail of another conversation; refer to the relevant saved report or handoff when continuing across sessions.
Find your way around
| Area | What it is for |
|---|---|
| Conversation | Requests, responses, tool activity, and results. |
| Model picker | Choose an available model and its options. |
| Files | Browse project documents and the current conversation's working files. |
| Terminal | Run project commands yourself. |
| Compute | Check analysis work and jobs. |
| Customize | Configure model access, skills, tools, connectors, and app settings. |
Use the command palette to find actions such as Open project files, Open project terminal, Open settings, and New session. On narrow windows, workspace actions may appear in a menu.
Add context
Mention the input files and the outcome in your request. The file picker and attachments let you provide material directly. You can also use @file references where the composer offers them.
Use data/samples.csv and methods/protocol.md. Check whether the sample
labels match the protocol, and save discrepancies in results/labels.md.
Only refer to material you have permission to use. For large files, first ask for the schema or a bounded sample.
Follow progress and steer the task
The conversation shows the agent's prose in bright text and everything it did to get there in grey beneath one header per turn: thoughts (with their text when the provider shares it), files read, searches, commands, edits, delegations and questions, in order. While the turn runs the header names the call in flight ("Reading study.json") and the list is open; when it finishes the header reads "Worked for 46m 29s" and folds the list, leaving the answer, any failed call and any question that still needs you. Open an individual row when you need a tool's inputs or output.
You can send follow-up prompts while a response is running: they join the current turn and the agent answers them in order. Use the Stop button or Escape when you need to change direction immediately. Inspect any files already written before asking it to retry or redo the work.
Use Research controls to choose planning, research effort, delegation, and when the agent asks for your input.
Review files and scientific results
Open an output link in the conversation or choose Files. Supported scientific formats can display as plots, molecules, structures, or genomic views.
Project files and Session scratch are different locations. They can contain files with the same name. Check the preview's location, especially when opening an older conversation, and save final deliverables to the project.
Ask for a text explanation alongside a visual result: what was measured, what the axes or colors mean, and where the source data came from. See Files and storage.
Undo and restore
After a response finishes, use Undo from here to return to an earlier point. Review the confirmation, which identifies affected work and file changes. A restore action is available for reverted work.
Undo is useful for trying a different analysis path. It does not reverse external payments, messages, or changes in a connected service. Use version control or backups for files you need to retain independently of conversation history.
Customize your setup
Open Customize to manage:
- Workspaces for each project's folders, read/write access, and default working location.
- Models and Local models for model access.
- Skills for reusable instructions.
- Tools for scientific capability availability.
- Connectors for external tools and services.
- Compute for local analysis and your own remote resources.
- Storage and General for app data, account selection, appearance, and updates.
Configuration covers file-based settings for repeatable setups.
Browser and terminal sessions
The CLI prints a local workspace URL. If you close the browser tab while the command is still running, reopen that URL. Stopping the CLI stops that running workspace; saved conversations remain available next time.
To choose a port:
openscience web --port 4096
For a browser-free server and a request from another terminal:
openscience serve --port 4096
openscience run --attach http://localhost:4096 "Summarize the current project"
Use the actual URL printed at startup. The workspace is for local access; it does not provide public remote hosting.
See Sessions for continuing, exporting, and importing conversations.
Explore workspace features
- Projects and source folders: create a workspace, connect material, pin, and archive.
- Tables: filter, sort, inspect schema and distributions, and export a subset.
- Scientific viewers: inspect structures, sequences, variants, alignments, and single-cell data.
- Saved Results: retain verified outputs, download, rename, and recover from Trash.
- Context and handoffs: compact long work and prepare a continuation.
- Keyboard shortcuts and Preferences: navigate and configure the interface.
Usage
Open Customize → Usage, directly below Ace, to see activity by source. Managed shows your confirmed Wallet charges in the selected funding workspace across devices. API keys, Local models, and Subscriptions show activity from saved conversations on this device, across projects. API-key costs are estimates; subscription fees and local hardware costs are not included.
Choose 7, 30, or 90 days, or enter custom From and To dates (up to 366 days, inclusive, in UTC). Filter by model and select tokens, cost, or requests in the daily chart. Export CSV at the bottom downloads daily model totals for the selected source, dates, and model, including token details and USD costs.
New requests retain the route used at the time of the call. Older saved activity without that information appears under Unclassified; it may include managed calls and is kept separate from confirmed charges. Deleted conversations are not part of device usage, and inherited fork history is not counted twice.
See Usage reports and CSV exports for reconciliation and report scope.