* Removed network access docs * Simplified docs for sandboxes and inference * Fixed build * docs(inference): clarify local inference routing * docs(inference): update provider and model examples * docs: add Docker prerequisite warning for connection-refused error Made-with: Cursor * Minor edits to quickstart safety and privacy * Doc restructured * removed tutorials * Added tutorial * Inference section reformatting * Updated CLI ref * removed troubleshooting * Updated inference * Updated pip install command for bug bash * Updated arch diagram * Updated tutorial * Updated install commands * Updated getting started * Updated brev link --------- Co-authored-by: Piotr Mlocek <pmlocek@nvidia.com>
3.9 KiB
title, description, keywords, topics, tags, content
| title | description | keywords | topics | tags | content | ||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
|
Install the OpenShell CLI and create your first sandboxed AI agent in two commands. |
|
|
|
|
Quickstart
This page gets you from zero to a running, policy-enforced sandbox in two commands.
Prerequisites
Before you begin, make sure you have:
- Python 3.12 or later
- uv installed
- Docker Desktop running on your machine
Install the OpenShell CLI
Activate your virtual environment:
uv venv && source .venv/bin/activate
Install the CLI:
uv pip install nemoclaw
Connect to a Remote Gateway (Optional)
If you're running locally, skip this step — the CLI creates a gateway automatically when you create your first sandbox.
:::::{tab-set}
::::{tab-item} Brev
:::{note} Deploy an OpenShell gateway on Brev by hitting Deploy on the OpenShell Launchable. :::
Once the instance is running, find the gateway URL in the Brev console under Using Secure Links. Copy the shareable URL for port 8080 — this is the gateway endpoint.
$ nemoclaw gateway add https://<your-port-8080-url>.brevlab.com
$ nemoclaw status
::::
::::{tab-item} DGX Spark
:::{note} Set up your Spark with NVIDIA Sync first, or make sure SSH access is configured (e.g., SSH keys added to the host). :::
Deploy to a DGX Spark machine over SSH:
$ nemoclaw gateway start --remote <username>@<spark-ssid>.local
$ nemoclaw status
Once nemoclaw status shows the gateway as healthy, all subsequent commands route through the SSH tunnel.
::::
:::::
Create Your First OpenShell Sandbox
Choose the tab that matches your agent:
::::{tab-set}
:::{tab-item} Claude Code
$ nemoclaw sandbox create -- claude
The CLI prompts you to create a provider from local credentials — type yes to continue. If ANTHROPIC_API_KEY is set in your environment, it is picked up automatically. If not, you can configure it from inside the sandbox after it launches.
:::
:::{tab-item} OpenCode
$ nemoclaw sandbox create -- opencode
The CLI prompts you to create a provider from local credentials — type yes to continue. If OPENAI_API_KEY or OPENROUTER_API_KEY is set in your environment, it is picked up automatically. If not, you can configure it from inside the sandbox after it launches.
:::
:::{tab-item} Codex
$ nemoclaw sandbox create -- codex
The CLI prompts you to create a provider from local credentials — type yes to continue. If OPENAI_API_KEY is set in your environment, it is picked up automatically. If not, you can configure it from inside the sandbox after it launches.
:::
:::{tab-item} Community Sandbox
$ nemoclaw sandbox create --from openclaw
The --from flag pulls a pre-built sandbox definition from the NemoClaw Community catalog. Each definition bundles a container image, a tailored policy, and optional skills into a single package.
:::
::::
Next Steps
You now have a working sandbox! From here, you can:
- Follow a guided tutorial — set up scoped GitHub repo access in {doc}
/tutorials/github-sandbox. - Learn how sandboxes work — see {doc}
/sandboxes/create-and-managefor the full lifecycle. - Write your own policies — see {doc}
/sandboxes/policiesfor custom access rules.