docs/deployment/deploy-to-remote-gpu.md

metadata

title:
  page: Deploy IniClaw to a Remote GPU Instance with Brev
  nav: Deploy to Remote GPU
description: Provision a remote GPU VM with IniClaw using Brev deployment.
keywords:
  - deploy iniclaw remote gpu
  - iniclaw brev cloud deployment
topics:
  - generative_ai
  - ai_agents
tags:
  - openclaw
  - openshell
  - deployment
  - gpu
  - iniclaw
content:
  type: how_to
  difficulty: intermediate
  audience:
    - developer
    - engineer
status: published

Deploy IniClaw to a Remote GPU Instance

Run IniClaw 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.
• IniClaw installed locally. Install with npm install -g iniclaw.

Deploy the Instance

Create a Brev instance and run the IniClaw setup:

$ iniclaw 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 the iniclaw 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, the deploy command opens an interactive shell inside the remote sandbox. To reconnect after closing the session, run the deploy command again:

$ iniclaw deploy <instance-name>

Monitor the Remote Sandbox

SSH to the instance and run the OpenShell TUI to monitor activity and approve network requests:

$ ssh <instance-name> 'cd /home/ubuntu/iniclaw && set -a && . .env && set +a && openshell term'

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

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

Related Topics

• Set Up the Telegram Bridge to interact with the remote agent through Telegram.
• Monitor Sandbox Activity for sandbox monitoring tools.
• Commands for the full deploy command reference.