Run AI Agents in Remote Sandboxes

[srosenbauer]

Run AI Agents in Remote Sandboxes

Problem

Local execution of AI agents still ties agent workloads to a developer's machine, limiting concurrency and requiring the developer to remain online for the duration of long-running tasks.

What we're releasing

Remote workspaces that run AI agents in isolated cloud sandboxes instead of on a developer’s local machine, allowing agent tasks to execute independently in a secure environment.

Expected outcome

Teams can run AI agents in the background at scale without relying on a developer’s machine, enabling long-running tasks and fully autonomous workflows.

[github-actions]

This issue has been automatically marked as stale because it has not had recent activity. It will be closed in 14 days if no further activity occurs.