This guide explains how to install and run an OpenClaw agent on a Virtual Private Server (VPS). Running OpenClaw on a VPS allows your AI assistant to operate 24/7 and execute automated tasks remotely.
What is OpenClaw?
OpenClaw is an open-source AI agent that runs locally on a server and can interact with files, APIs, terminals, and external services. It can automate workflows and execute commands based on natural language instructions.
Because the agent can execute system commands, it is recommended to run it inside a container to isolate it from the rest of your server environment.
Requirements
- A VPS running Linux (Ubuntu 22.04 or newer recommended)
- Root or sudo access
- Docker and Docker Compose installed
- Minimum recommended resources:
- 2 CPU cores
- 4 GB RAM
- 40 GB disk space
- An SSH client
Step 1: Connect to your VPS
Use SSH to connect to your server.
ssh root@YOUR_SERVER_IP
Step 2: Install Docker
If Docker is not installed, install it using the following commands:
apt update apt install docker.io docker-compose -y systemctl enable docker systemctl start docker
Step 3: Create a working directory
mkdir openclaw cd openclaw
Step 4: Create the Docker Compose configuration
Create a docker-compose.yml file:
nano docker-compose.yml
Example configuration:
version: '3'
services:
openclaw:
image: openclaw/openclaw:latest
container_name: openclaw
restart: always
ports:
- "3000:3000"
volumes:
- ./data:/app/data
Step 5: Start the OpenClaw agent
Run the following command:
docker compose up -d
This command downloads the OpenClaw container and starts the agent.
Step 6: Access the OpenClaw dashboard
Once the container is running, open your browser and go to:
http://YOUR_SERVER_IP:3000
You can now configure your AI agent and connect external services.
Security recommendations
- Run OpenClaw inside Docker for isolation.
- Restrict access with a firewall.
- Use SSH keys instead of passwords.
- Avoid exposing the dashboard publicly without authentication.
Conclusion
You have successfully installed an OpenClaw agent on your VPS. Your AI assistant can now run continuously and automate tasks directly from your server.