Memantoclaw Deploy Remote

Memantoclaw Deploy Remote

Provision a remote GPU VM with MemantoClaw using Brev deployment.

Prerequisites

• The Brev CLI installed and authenticated.
• An NVIDIA API key from build.nvidia.com.
• MemantoClaw installed locally. Follow the Quickstart (see the memantoclaw-get-started skill) install steps.
• A running MemantoClaw sandbox, either local or remote.
• A Telegram bot token from BotFather.

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

Step 1: Deploy the Instance

Warning: The memantoclaw deploy command is experimental and may not work as expected.

Create a Brev instance and run the MemantoClaw setup:

$ memantoclaw 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 memantoclaw setup to create the gateway, register providers, and launch the sandbox.
4. Starts auxiliary services, such as the Telegram bridge and cloudflared tunnel.

Step 2: 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:

$ memantoclaw deploy <instance-name>

Step 3: 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/memantoclaw && set -a && . .env && set +a && openshell term'

Step 4: 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

Step 5: GPU Configuration

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

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

Forward messages between a Telegram bot and the OpenClaw agent running inside the sandbox. The Telegram bridge is an auxiliary service managed by memantoclaw start.

Step 6: Create a Telegram Bot

Open Telegram and send /newbot to @BotFather. Follow the prompts to create a bot and receive a bot token.

Step 7: Set the Environment Variable

Export the bot token as an environment variable:

$ export TELEGRAM_BOT_TOKEN=<your-bot-token>

Step 8: Start Auxiliary Services

Start the Telegram bridge and other auxiliary services:

$ memantoclaw start

The start command launches the following services:

• The Telegram bridge forwards messages between Telegram and the agent.
• The cloudflared tunnel provides external access to the sandbox.

The Telegram bridge starts only when the TELEGRAM_BOT_TOKEN environment variable is set.

Step 9: Verify the Services

Check that the Telegram bridge is running:

$ memantoclaw status

The output shows the status of all auxiliary services.

Step 10: Send a Message

Open Telegram, find your bot, and send a message. The bridge forwards the message to the OpenClaw agent inside the sandbox and returns the agent response.

Step 11: Restrict Access by Chat ID

To restrict which Telegram chats can interact with the agent, set the ALLOWED_CHAT_IDS environment variable to a comma-separated list of Telegram chat IDs:

$ export ALLOWED_CHAT_IDS="123456789,987654321"
$ memantoclaw start

Step 12: Stop the Services

To stop the Telegram bridge and all other auxiliary services:

$ memantoclaw stop

Related Skills

• memantoclaw-monitor-sandbox — Monitor Sandbox Activity for sandbox monitoring tools
• memantoclaw-reference — Commands for the full deploy command reference