Sandbox Runtime

The sandbox runtime is the execution layer for autonomous work. It provisions isolated environments, manages session execution, and streams events so workflows can run safely at scale. Today, workloads are triggered through the workbench and managed platform services. External runtime APIs are not yet public.

What It Provides

• Isolation and containment for untrusted or semi-trusted workloads.
• Policy enforcement for tools, data access, and budgets.
• Execution control with queueing, timeouts, and retry-aware failures.
• Streaming observability with real-time events, file updates, and execution metadata.
• Capacity management with host health, pooling, and optional autoscaling.

Who This Is For

• Workbench users who need secure, repeatable execution. Start in the workbench.
• Operators who host runtimes and earn for reliable execution. Operator onboarding.
• Platform teams who manage execution reliability and safety. Review architecture.

Start Here (By Role)

• Operators: Begin with operator onboarding.
• Platform engineers: Review architecture and orchestration.
• Security teams: Start with sandboxing and safety.

The runtime is available via partnership or early access.