> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.nvidia.com/openshell/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/openshell/_mcp/server.

# Tutorials

> Step-by-step walkthroughs for OpenShell, from first sandbox to production-ready policies.

Hands-on walkthroughs that teach OpenShell concepts by building real configurations. Each tutorial builds on the previous one, starting with core sandbox mechanics and progressing to production workflows.

#### [First Network Policy](/get-started/tutorials/first-network-policy)

Create a sandbox, observe default-deny networking, apply a read-only L7 policy, and inspect audit logs. No AI agent required.

#### [GitHub Push Access](/get-started/tutorials/github-sandbox)

Launch Claude Code in a sandbox, diagnose a policy denial, and iterate on a custom GitHub policy from outside the sandbox.

#### [Microsoft Graph Provider Refresh](/get-started/tutorials/microsoft-graph-provider-refresh)

Configure a Microsoft Graph provider profile with gateway-managed OAuth2 refresh-token rotation.

#### [Inference with Ollama](/get-started/tutorials/inference-ollama)

Run Ollama models in a community sandbox or attach a profile for a host-level service.

#### [Local Inference with LM Studio](/get-started/tutorials/local-inference-lmstudio)

Attach an endpoint-bearing profile and call a local LM Studio server directly.

#### [Docker Compose Setup](/get-started/tutorials/docker-compose)

Run the OpenShell gateway as a Docker Compose service and create agent sandboxes including OpenClaw.