Skip to main content
Agents often need to keep going after one request ends. They install packages, edit files, clone repositories, generate artifacts, and build up context over time. Celesto computers are designed for that kind of stateful work. Both the root disk and the workspace are durable across normal stop and start operations. They serve different jobs.

Two durable storage surfaces

StorageBest forHow to size it
Root diskOperating system, runtime, package manager internals, and system-level state.Increase disk_size_mb when system tools need more room.
CelestoFS workspaceRepositories, generated files, datasets, build artifacts, and agent project state.Use it for large workspace data.
In Celesto Linux sandboxes, the sandbox user’s home directory is /home/ohm. That is the default place for agent workspace files.

Stop, start, delete

1

Stop when work should continue later

Stopping turns the computer off while keeping saved state available for a later start.
2

Start when the same agent job resumes

Starting the same computer brings back its saved root disk and workspace state.
3

Delete when the work is done

Deleting removes the computer and its saved state. Use it when you no longer need the files or resources.

Learn more

Petabyte-scale storage

See how a 10 GB sandbox can write a 20 GB workspace file with CelestoFS.

Persistent state

Learn the stop/start/delete model for saved computer state.
Last modified on July 1, 2026