Deploy NemoClaw to a Remote GPU Instance#

Run NemoClaw on a remote GPU instance through Brev. The deploy command provisions the VM, installs dependencies, and connects you to a running sandbox.

Prerequisites#

  • The Brev CLI installed and authenticated.

  • An NVIDIA API key from build.nvidia.com.

  • NemoClaw installed locally. Install with npm install -g nemoclaw.

Deploy the Instance#

Create a Brev instance and run the NemoClaw setup:

$ nemoclaw deploy <instance-name>

Replace <instance-name> with a name for your remote instance, for example my-gpu-box.

The deploy script performs the following steps on the VM:

  1. Installs Docker and the NVIDIA Container Toolkit if a GPU is present.

  2. Installs the OpenShell CLI.

  3. Runs nemoclaw setup to create the gateway, register providers, and launch the sandbox.

  4. Starts auxiliary services, such as the Telegram bridge and cloudflared tunnel.

Connect to the Remote Sandbox#

After deployment finishes, connect to the sandbox on the remote instance:

$ nemoclaw deploy <instance-name>

This opens an interactive shell inside the remote sandbox.

Monitor the Remote Sandbox#

Open the OpenShell TUI on the remote instance to monitor activity and approve network requests:

$ nemoclaw term <instance-name>

Verify Inference#

Run a test agent prompt inside the remote sandbox:

$ openclaw agent --agent main --local -m "Hello from the remote sandbox" --session-id test

GPU Configuration#

The deploy script uses the NEMOCLAW_GPU environment variable to select the GPU type. The default value is a2-highgpu-1g:nvidia-tesla-a100:1. Set this variable before running nemoclaw deploy to use a different GPU configuration:

$ export NEMOCLAW_GPU="a2-highgpu-1g:nvidia-tesla-a100:2"
$ nemoclaw deploy <instance-name>