Nova Admin Docs
Concepts

Sandboxes

Sandboxes are isolated execution environments where agents can browse, run shell commands, or drive a virtual desktop without risking the host.

A sandbox is a short-lived, isolated environment that an agent can drive through tool calls. Nova Admin uses E2B for both code-only sandboxes and full desktop sandboxes, with the @e2b/desktop package for GUI workflows.

When to use a sandbox

  • The agent needs to execute code with arbitrary dependencies.
  • The agent needs a browser to scrape, log in, or click through a flow that has no API.
  • The agent needs to run a shell command that should not touch production credentials.
  • You want a clean, reproducible environment per run.

How sandboxes plug in

Sandboxes show up to agents as integration actions on the sandbox provider. Typical actions:

ActionWhat it does
sandbox_createSpins up a new E2B environment, returns an ID.
sandbox_execRuns a shell command inside the sandbox.
sandbox_read_file / sandbox_write_fileMove files in and out.
sandbox_browser_navigateDrive the headless browser.
sandbox_desktop_screenshotCapture the virtual desktop.

A sandbox auto-destroys on a timeout or when the run completes. Files you want to keep must be uploaded to a durable store (Cloud Storage, Firestore) before teardown.

Limits

  • Lifetimes are bounded, so long-running tasks need to checkpoint state.
  • Outbound network is open, but the agent's credentials never enter the sandbox unless you explicitly pass them through.
  • Each sandbox costs money. The platform tracks spend per agent in the Costs tab.

See also

  • Observability — every sandbox action shows up in the run timeline.

On this page