OpenWorkerDeveloper
DocumentationHarness SDK

Deployment options

Start inside your app, then choose a shared service when you need one.

Desktop packaging and a Node container on Railway use the managed SDK runtime. The ows CLI installs and operates a separate OpenWorker service cluster; it is not needed to deploy every SDK app.

Choose a platform

PlatformStatus and starting point
RailwayApplication hosting; single-service recipe tested live
Private Kubernetes clusterBring an existing cluster; local qualification does not cover every remote environment
AWSExperimental EKS service deployment
GCPExperimental; complete live qualification pending
AzureExperimental AKS service deployment; fresh-install qualification ongoing

The application-facing service API stays the same. Cloud identity, networking, storage and lifecycle setup are provider-specific. NVIDIA OpenShell is the sandbox integration across these reference deployments.

Choose execution placement

PlacementUse it when
Managed local harnessA desktop app or one container owns a workspace
Service with nearby executionSeveral API nodes need durable sessions and shared worker capacity
Service with separate executionSandboxes need different hardware, capacity or lifecycle from the agent workers

SQLite serves local applications. PostgreSQL supports service deployments and can also be selected through the Rust SDK. Database choice does not remove team/session capabilities. Bind an execution environment explicitly when agents must share it; sharing does not resolve conflicting file edits or ports automatically.

OpenShell runs tool execution in a sandbox while the current harness remains in the trusted service domain. RuntimeProfiles select the provider and allowed resources. A profile is configuration; a provisioned environment is an instance.

Start with the local service setup and service CLI. Cloud credentials, budgets and cluster identity are operator-owned. Cloud deployment paths are experimental; validate the configuration in the target environment before production use.

Before upgrading, read versions and compatibility and the storage migration instructions.

Search guides, examples and deployment instructions.