> This page is for NeMo Fabric, version v0.7.0.
> For other versions, use one of these documentation indexes:
> - Latest (v0.7.0) (default): https://docs.nvidia.com/nemo/fabric/latest/llms.txt
> - dev: https://docs.nvidia.com/nemo/fabric/dev/llms.txt
> - v0.7.0: https://docs.nvidia.com/nemo/fabric/v0.7.0/llms.txt
> - v0.6.1: https://docs.nvidia.com/nemo/fabric/v0.6.1/llms.txt
> - v0.6.0: https://docs.nvidia.com/nemo/fabric/v0.6.0/llms.txt
> - v0.5.0: https://docs.nvidia.com/nemo/fabric/v0.5.0/llms.txt
> - v0.4.0: https://docs.nvidia.com/nemo/fabric/v0.4.0/llms.txt
> - v0.3.0: https://docs.nvidia.com/nemo/fabric/v0.3.0/llms.txt
> - v0.2.0: https://docs.nvidia.com/nemo/fabric/v0.2.0/llms.txt
> - v0.1.1: https://docs.nvidia.com/nemo/fabric/v0.1.1/llms.txt
> - v0.1.0: https://docs.nvidia.com/nemo/fabric/v0.1.0/llms.txt

> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.nvidia.com/nemo/fabric/llms.txt.

# 4. Run in OpenShell (Optional)

> Run the source-checkout Hermes code-review example in an OpenShell sandbox.

Run a Hermes code-review agent inside an [OpenShell](https://github.com/NVIDIA/OpenShell) sandbox, controlled by the NVIDIA NeMo Fabric Python SDK on the host. OpenShell supplies isolation and policy; the adapter and harness execute the task inside the sandbox.

This optional continuation uses the repository's [Hermes code-review example](https://github.com/NVIDIA/NeMo-Fabric/tree/v0.7.0/examples/code_review_agent#run-hermes-in-openshell). It requires a source checkout and a Linux host. It packages a sample repository and skill in a task image rather than automatically moving the scripts or MCP server from the preceding guides into a sandbox.

#### Prepare a Linux Host

Use a NeMo Fabric source checkout with its Python SDK and native extension installed, following [Development Setup](/nemo/fabric/contributing/setup). The shared launcher requires Docker with Linux containers, Rust/Cargo, `uv`, Python 3, `curl`, `openssl`, and `tar`. The Docker daemon must be running. The launcher currently supports Linux x86_64 and arm64 hosts; this procedure does not run directly on macOS or Windows.

From the repository root, select your installed host SDK environment and provide the NVIDIA API key used for model access:

```bash
export UV_PROJECT_ENVIRONMENT="$PWD/.venv"
export NVIDIA_API_KEY='<your-key>'
```

The image contains its own Hermes installation and adapter. You do not need to reuse the local Hermes interpreter from quickstart two. Refer to the [shared launcher requirements](https://github.com/NVIDIA/NeMo-Fabric/blob/v0.7.0/examples/openshell/README.md#requirements) if your host environment is elsewhere.

#### Run the Sandboxed Code Review

Run from the repository root:

```bash
OPENSHELL_EXAMPLE_MODE=fabric_owned \
  bash examples/openshell/run-demo.sh \
  examples/code_review_agent/demo-openshell-hermes-sdk.sh
```

The launcher builds the provider and task images, downloads its pinned OpenShell release, starts a local gateway, and configures model access. The host consumer prepares a sandbox, runs two review turns on one runtime, then stops the runtime and releases the sandbox. NeMo Relay is off by default.

The example uses its own configured NVIDIA model. To select another model available to your key, set `OPENSHELL_CODE_REVIEW_MODEL` before launching. Alternate endpoints also need a matching OpenShell provider policy, as described in the [example's model-access instructions](https://github.com/NVIDIA/NeMo-Fabric/tree/v0.7.0/examples/code_review_agent#run-hermes-in-openshell).

#### Inspect the Result

Open `.tmp/code-review-hermes/fabric_owned-report.json`. A completed run has top-level `status: "succeeded"` and two entries in `reviews`, each with status `succeeded`. Inspect each review's `output.response` for the finding and follow-up explanation. The second review should recall the example's `cedar-4827` review tag. Collected runtime artifacts appear under `.tmp/code-review-hermes/artifacts/`.

The consumer attempts runtime shutdown and environment release even after a failure. The launcher checks sandbox removal in this ownership mode and cleans up its gateway resources. If the command fails, inspect the report's `error` field and launcher output; the [OpenShell example guide](https://github.com/NVIDIA/NeMo-Fabric/blob/v0.7.0/examples/openshell/README.md) explains setup, networking, and ownership modes.

## Next Steps

Use [Environments and Sandboxes](/nemo/fabric/sdk/environments-and-shared-services#explicit-environment-lifecycle) to integrate sandbox preparation and release into your application. The [custom LangGraph example](https://github.com/NVIDIA/NeMo-Fabric/tree/v0.7.0/examples/langgraph_custom_agent#run-the-custom-agent-in-openshell) demonstrates the same deployment path with an application-owned agent and adapter.