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

# Choose Between NemoClaw and OpenShell CLIs

> Choose between the NemoClaw CLI and the OpenShell CLI for common sandbox operations.

NemoClaw uses two host-side CLIs.
Use `nemohermes` for NemoClaw-managed workflows.
Use `openshell` when you need a lower-level OpenShell operation that NemoClaw intentionally leaves available.

## Rule of Thumb

If the task changes how NemoClaw creates, rebuilds, preserves, or configures a sandbox, start with `nemohermes`.

If the task inspects or changes the live OpenShell gateway, TUI, raw policy, port forwarding, inference route, or sandbox file transfer, use `openshell`.

Do not create or recreate NemoClaw-managed sandboxes directly with `openshell sandbox create` unless you intend to manage OpenShell yourself.
Run `nemohermes onboard` afterward if you need to return to a NemoClaw-managed environment.

## Use `nemohermes` For NemoClaw Workflows

Use `nemohermes` for operations where NemoClaw adds product-specific state, safety checks, backup behavior, credential handling, or agent configuration.

* Install, onboard, or recreate a NemoClaw sandbox:

  ```bash
  nemohermes onboard
  nemohermes onboard --fresh --name <sandbox-name> --recreate-sandbox
  ```

Use `--resume` only when you are recovering an interrupted onboarding session.
For a completed sandbox, use `--fresh --name <sandbox-name> --recreate-sandbox` when you need NemoClaw to recreate it.

* List, connect to, check, or delete NemoClaw-managed sandboxes:

  ```bash
  nemohermes list
  nemohermes my-assistant connect
  nemohermes my-assistant status
  nemohermes my-assistant logs --follow
  nemohermes my-assistant destroy
  ```

* Rebuild or upgrade while preserving workspace state:

  ```bash
  nemohermes my-assistant rebuild
  nemohermes upgrade-sandboxes --check
  ```

* Snapshot, restore, or mount sandbox state:

  ```bash
  nemohermes my-assistant snapshot create --name before-change
  nemohermes my-assistant snapshot restore before-change
  nemohermes my-assistant share mount
  ```

* Add or remove NemoClaw policy presets:

  ```bash
  nemohermes my-assistant policy add pypi --yes
  nemohermes my-assistant policy list
  nemohermes my-assistant policy remove pypi --yes
  ```

* Manage NemoClaw credentials, diagnostics, and cleanup:

  ```bash
  nemohermes credentials list
  nemohermes credentials reset nvidia-prod
  nemohermes debug --sandbox my-assistant
  nemohermes gc --dry-run
  ```

* Manage NemoClaw messaging channels:

  ```bash
  nemohermes my-assistant channels add slack
  ```

## Use `openshell` For OpenShell Operations

Use `openshell` when the docs explicitly call for a live OpenShell gateway operation or when you need a lower-level view beneath the NemoClaw wrapper.

* Open the OpenShell TUI for network approvals and live activity:

  ```bash
  openshell term
  ```

* Manage service port forwards:

  ```bash
  openshell forward start --background <port> <sandbox-name>
  openshell forward list
  ```

* Inspect the underlying sandbox state:

  ```bash
  openshell sandbox list
  openshell sandbox get <sandbox-name>
  openshell logs <sandbox-name> -n 20
  openshell doctor check
  ```

* Move files or run raw one-off commands when you intentionally want to bypass NemoClaw's sandbox registry and wrappers:

  ```bash
  openshell sandbox upload <sandbox-name> ./local-file /sandbox/
  openshell sandbox download <sandbox-name> /sandbox/output ./output
  openshell sandbox exec -n <sandbox-name> -- env | grep '^HOME='
  ```

* Merge a single endpoint into the live OpenShell policy:

  ```bash
  openshell policy update <sandbox-name> --add-endpoint api.example.com:443:read-only:rest:enforce
  ```

* Export the round-trippable OpenShell base policy through NemoClaw, then replace it through OpenShell:

  Requires OpenShell 0.0.72+ for the round-trippable `policy get --base` and `policy set --wait` syntax.

  ```bash
  nemohermes <sandbox-name> policy get > current-policy.yaml
  ```

  NemoClaw strips the OpenShell metadata header and exits non-zero if it cannot validate the base policy.
  Do not use `--raw` for a file that you plan to reapply.

  Edit or review `current-policy.yaml`, then apply it:

  ```bash
  openshell policy set --policy current-policy.yaml --wait <sandbox-name>
  ```

`openshell policy update` merges specific endpoint and rule changes into the live sandbox policy.
`openshell policy set` replaces the live policy with the file you provide.
For normal NemoClaw network access changes, prefer `nemohermes <name> policy add` so NemoClaw preserves presets and records the change for rebuilds.

## Common Decisions

This section covers common decisions when using the NemoClaw CLI and the OpenShell CLI.

### First Setup or Full Recreate

Use `nemohermes onboard`.
It starts the OpenShell gateway when needed, registers providers, builds the selected agent sandbox image, applies NemoClaw policy choices, and creates the sandbox.

The OpenShell CLI does not provide a command that starts a gateway.
Avoid running `openshell sandbox create` directly for NemoClaw-managed sandboxes because it does not update NemoClaw's registry, session metadata, workspace-preservation flow, or agent-specific configuration.

### Connect to the Sandbox

Use `nemohermes <name> connect` for an interactive NemoClaw sandbox shell.
It waits for readiness, handles stale SSH host keys after gateway restarts, and prints agent-specific hints.

Use `openshell sandbox connect <name>` only when you intentionally want the raw OpenShell connection path.

For a one-off command in a NemoClaw-managed sandbox, use `nemohermes <name> exec` instead of opening an interactive shell.
It resolves the sandbox by its NemoClaw registry name and runs through the standard NemoClaw CLI surface.
The command executes as the sandbox user with `HOME=/sandbox` inside the provisioned sandbox, where the agent configuration, inference routing, and policy state are already in place.

```bash
nemohermes my-assistant exec -- cat /tmp/gateway.log
```

Use `openshell sandbox exec` for the raw OpenShell execution path, such as when you address a sandbox by its gateway name or intentionally bypass the NemoClaw CLI and registry.

```bash
openshell sandbox exec -n my-assistant -- cat /tmp/gateway.log
```

### Check Health or Logs

Use `nemohermes <name> status` and `nemohermes <name> logs` first.
They combine NemoClaw registry data, OpenShell state, selected agent process health, inference health, policy details, and messaging-channel warnings for that sandbox.
Use `nemohermes status` only for the global all-sandbox and host-service overview.

Use `openshell sandbox list`, `openshell sandbox get`, `openshell logs <name> -n 20`, or `openshell doctor check` when debugging lower-level OpenShell behavior.
When using `openshell logs` directly, `-n <lines>` controls the line count; use `--tail` only when you want live OpenShell log streaming.

### Approve Blocked Network Requests

Use `openshell term`.
The OpenShell TUI owns live network activity and operator approval prompts.

Approved endpoints are session-scoped unless you also add them to the policy through a NemoClaw preset or raw OpenShell policy update.

### Change Models or Providers

Use the NemoClaw commands for model or provider inspection and switches so the OpenShell route and the running agent config stay consistent:

```bash
nemohermes inference get
nemohermes inference set --provider nvidia-prod --model nvidia/nemotron-3-super-120b-a12b
```

For Hermes sandboxes, use the alias; it updates the route and `/sandbox/.hermes/config.yaml` without a rebuild or restart:

```bash
nemohermes inference set --provider hermes-provider --model openai/gpt-5.4-mini
```

For a build-time agent setting change, rerun onboarding so the sandbox configuration is recreated consistently:

```bash
nemohermes onboard --fresh --name <sandbox-name> --recreate-sandbox
```

Verify either path with:

```bash
nemohermes <name> status
```

### Update Network Policy

Use `nemohermes <name> policy add` or `policy remove` for NemoClaw presets and custom preset files.
NemoClaw merges the new policy with the live policy and reapplies presets during rebuilds.

Use `openshell policy update` for precise live endpoint or REST rule changes.
Use `nemohermes <name> policy get` and `openshell policy set --policy <file> --wait <name>` only when you need to edit and replace the round-trippable base policy.
Use `openshell policy get --full <name>` only to inspect the effective policy, including provider-composed rules.

### Move Workspace Files

Use `nemohermes <name> snapshot create`, `snapshot restore`, or `share mount` for normal workspace preservation and editing.

Use `openshell sandbox upload` and `openshell sandbox download` for manual file copies when you need exact control over source and destination paths.

## Related Topics

* [Commands](commands) for the full NemoClaw command reference.
* [Recover and Rebuild Sandboxes](../manage-sandboxes/operate-sandboxes/recover-and-rebuild-sandboxes) for day-two recovery.
* [Switch Inference Models](../inference/manage-inference/switch-models) for inference route examples.
* [Customize the Network Policy](../network-policy/customize-network-policy) for persistent network access changes.
* [Approve or Deny Network Requests](../network-policy/approve-network-requests) for the OpenShell TUI approval flow.