What is an artifact in Grain?
It is the useful output an agent made, such as a page, report, walkthrough, app, dashboard or scheduled job.
Grain / Docs / Artifacts, workspaces and sandboxes
Docs
Artifacts, workspaces and sandboxes
Grain separates the useful thing your agent makes from the place it stays and the compute that may run it. An artifact is the output, a workspace is its durable home, and a sandbox is a runtime rather than the final destination.
The three nouns
| Concept | What it is | What it is not |
|---|---|---|
| Artifact | A page, report, walkthrough, internal app, dashboard or scheduled job made by an agent | The chat transcript or agent itself |
| Workspace | The durable place with a URL, files and optional Postgres, logins and scheduled jobs | A code editor or one-time execution |
| Sandbox | Compute where code runs once; hosted cloud workspaces use E2B microVM sandboxes | A guarantee that the output remains published |
Artifact
Treat the artifact as the result another person opens. A static explanation may be one HTML page. An app may include files, a database-backed interface, login and a scheduled job. The useful boundary is the audience's job, not the framework or file count.
Workspace
A workspace gives the artifact continuity. Its files can be read again, linked to later work and exported. Its URL gives readers a stable address. If the artifact is an app, the same workspace may also hold its Postgres data, login boundary and scheduled jobs. Published artifacts remain published on the free tier after a session ends.
Sandbox
A sandbox supplies execution. It can install dependencies, run a build or serve an app, but compute alone does not define what should remain available to readers. Grain's hosted cloud workspaces use E2B microVM sandboxes. Grain is not a bare sandbox provider; it keeps the output produced there.
How the pieces fit
- You give a coding agent a concrete task, such as producing a release walkthrough from a changed codebase.
- The agent writes the artifact files in a connected folder. Those files are the authored result.
- The workspace keeps the files and gives the published result an address. If the result needs state, the workspace can include Postgres and login.
- A sandbox supplies runtime compute when the artifact needs to build, execute or run continuously.
- Readers open the share, leave comments and return later. The agent can read those comments and revise the existing artifact instead of beginning from an empty session.
Static pages and full apps
| Need | Static artifact | App artifact |
|---|---|---|
| Good fit | Write-ups, reports and walkthroughs | Dashboards, internal tools and automations |
| State | Files are enough | Can use Postgres |
| Access | Can use public, password or invited-person sharing | Can also include app login |
| Background work | Usually none | Can include scheduled jobs |
Boundaries
- Grain is not an agent. You bring the coding agent and model plan you already use.
- Grain is not an IDE. Humans continue editing in their chosen editor while agents publish through the supported interface.
- Grain is not a general deployment platform. Production services with their own repository pipelines may belong on a dedicated deployment platform.
- The self-hostable core is not described as open source because no public license claim is part of the product contract.
Frequently asked questions
Is a workspace the same as a sandbox?
No. The workspace is where the artifact stays. The sandbox is compute used to run code.
Does every artifact need a database?
No. Static pages can be files only. Apps can add Postgres when they need durable data.
Does Grain include a coding agent?
No. Grain is agent-agnostic and does not sell or mark up model tokens. You bring your own CLI coding agent.
Turn a folder into an artifact
Start with the first-artifact guide to connect a folder and create its share URL.
Free forever. No card. Bring your own agent.
Sources · facts verified 2026-09-04
- E2B pricing and sandbox limits · 2026-09-04