OpenClaw VPS Hosting
Host OpenClaw, the open-source personal AI assistant, on a VPS that never sleeps. Its gateway stays connected to your chat apps around the clock, on a server that is separate from your own computer. Full root access, DDoS protection and instant deployment.
OpenClaw VPS at a glance
- Recommended system
- Ubuntu 24.04 LTS
- Memory
- 4 GB RAM recommended; 8 GB for browser automation
- Runtime
- Node.js 24.16+ or 26 (the installer can set it up)
- Chat apps
- WhatsApp, Telegram, Discord, Slack, Signal, Teams and more
- Licence
- Open source (MIT)
- Deployment
- Ready in minutes, with full root access
Choose your OpenClaw VPS plan
Live prices. Ubuntu is selected for you on the next page, where you choose the location and pay with crypto or your balance.
Live plans are loading. You can also choose a plan on the deploy page. Deploy your OpenClaw VPS
What is OpenClaw VPS hosting?
OpenClaw is an open-source personal AI assistant. A gateway process connects a model provider of your choice, such as Anthropic or OpenAI, to the messaging apps you already use, so you can chat with your assistant and let it run tasks from anywhere.
An OpenClaw VPS is a server where that gateway runs all the time. We provide the server; you install OpenClaw, add your model API keys and decide which people and channels it answers.
Why run OpenClaw on a VPS
Always reachable
The gateway keeps its chat connections open even when your own computer is off.
Kept apart from your files
OpenClaw can run tools on the machine it lives on. On a VPS, that machine holds only what you give it.
Restarts by itself
Installed as a systemd service, the gateway starts again after a reboot or a crash.
Room for tools
Dedicated vCPU and RAM leave room for browser automation and other tools the assistant uses.
OpenClaw on a VPS or on your own computer
| What matters | Your own computer | ClientVPS server |
|---|---|---|
| Uptime | Stops when your computer sleeps, restarts or loses its connection. | Runs around the clock in a datacenter. |
| Isolation | The agent can reach your personal files, browser sessions and saved passwords. | A separate machine that holds only what you put on it. |
| Access | Tied to one device. | Reach it over SSH from your laptop, phone or another computer. |
| Network | Home connections are slower and often block incoming connections. | A fast datacenter connection, a public IP address and DDoS protection. |
| Starting over | Undoing an agent's changes to your own computer can be hard. | Reinstall the system from your client area in minutes. |
What you can do with a OpenClaw VPS
A personal assistant in your chat apps
Ask questions, draft messages and get summaries from WhatsApp or Telegram.
Scheduled check-ins and reminders
Have the assistant send you updates at set times.
A shared team assistant
Run a dedicated assistant in Slack or Discord for your team, on its own server and OS user.
Web research and automation
Let the assistant browse and collect information with its browser tools.
Experiments with models
Switch between model providers without touching your own computer.
How much VPS does OpenClaw need?
| What you run | Recommended resources |
|---|---|
| One personal assistant | 2 vCPU, 4 GB RAM |
| Browser automation or several channels | 4 vCPU, 8 GB RAM |
| Several assistants or a team | 8 vCPU, 16 GB RAM |
How to set up OpenClaw on your VPS
Commands follow the official documentation as of October 2026. Tools like this change quickly, so check the official docs linked below before you run them.
- 1
Deploy a server and connect
Choose a plan with Ubuntu 24.04. When it is ready, connect over SSH with the IP address and password from your client area, and update the system.
ssh root@YOUR_SERVER_IP apt update && apt upgrade -y - 2
Create a user for the agent
Create a normal user with sudo rights, then sign in again over SSH as that user, so the services you install run under it. Add your SSH public key to /home/agent/.ssh/authorized_keys to log in with a key.
adduser agent usermod -aG sudo agent exit ssh agent@YOUR_SERVER_IP - 3
Turn on the firewall
Allow SSH first, then enable the firewall. Dashboards stay on localhost, so no other ports are needed.
sudo ufw allow OpenSSH sudo ufw enable - 4
Install OpenClaw
Run the official installer as your agent user. It sets up a supported Node.js if needed and starts onboarding, where you choose a model provider and connect chat apps.
curl -fsSL https://openclaw.ai/install.sh | bash - 5
Run the gateway as a service
Install the systemd user service and enable lingering so it keeps running after you log out. Then check its status.
openclaw gateway install systemctl --user enable --now openclaw-gateway.service sudo loginctl enable-linger $USER openclaw gateway status - 6
Open the dashboard through SSH
The gateway listens on localhost port 18789. From your own computer, open an SSH tunnel and use the dashboard locally, without exposing it to the internet.
ssh -N -L 18789:127.0.0.1:18789 agent@YOUR_SERVER_IP - 7
Approve who can talk to it
Unknown senders in direct messages get a pairing code. Approve only the people you trust.
openclaw pairing approve <channel> <code>
Security basics for OpenClaw on a VPS
- Treat every incoming message as untrusted, and approve only people you trust.
- Tools run on the server itself unless you configure sandboxing, so read the OpenClaw security and sandboxing guides before connecting other users.
- If you bind the gateway to anything other than localhost, set a gateway token or password.
- Sign in with SSH keys and turn off password logins.
- Run the agent as a normal user, not as root.
- Turn on a firewall and open only the ports you need, usually just SSH.
- Keep dashboards on localhost and reach them through an SSH tunnel instead of opening them to the internet.
- Store API keys in the tool's own config or environment files, never in a Git repository.
- Give the agent its own API keys with spending limits, and rotate them if you suspect a leak.
- Install security updates regularly and reboot after kernel updates.
- Back up the agent's data directory before upgrades and big changes.
Troubleshooting
Gateway stops when you log out
Enable lingering with sudo loginctl enable-linger $USER so user services keep running.
Service problems after an update
Run openclaw doctor; it checks and repairs the gateway service.
Dashboard not reachable
Keep the SSH tunnel open, and check that the gateway is running with openclaw gateway status.
Processes killed for low memory
Browser tools use the most memory. Reduce concurrency or move to a plan with more RAM.
When you don't need a OpenClaw VPS
You only try it now and then
For occasional testing, running OpenClaw on your own computer is simpler.
You rely on Apple-only features
Integrations that need macOS, such as iMessage, cannot run on a Linux VPS.
You don't want to manage a Linux server
Updates, backups and security are your responsibility on a self-managed VPS.
Other AI agents you can host
Claude Code VPS guideA remote coding workspace for Anthropic's terminal coding agent.
Hermes Agent VPS guideNous Research's self-improving agent with memory, skills and scheduled tasks.
NemoClaw VPS guideNVIDIA's tool for running OpenClaw agents inside a sandbox.
Paperclip VPS guideRun a whole team of AI agents as a company, with goals, budgets and approvals.
PicoClaw VPS guideAn ultra-lightweight assistant written in Go: one small binary, many chat apps.Official OpenClaw resources
These links go to the official project sites, in English.
OpenClaw VPS FAQ
Can I run OpenClaw on a VPS?
Yes. OpenClaw documents Linux servers as a supported way to host its gateway, installed as a systemd service.
Do I need a GPU?
No, not when you use hosted model providers such as Anthropic, OpenAI or OpenRouter. Running large models locally would need a GPU, which our VPS plans do not include.
Which chat apps can I connect?
WhatsApp, Telegram, Discord, Slack, Signal, Microsoft Teams, Google Chat and more. Features that need macOS, such as iMessage, do not work on a Linux server.
How do I keep OpenClaw running?
Install the gateway as a systemd user service with openclaw gateway install, and enable lingering so it runs after you log out and starts after a reboot.
How do I reach the dashboard safely?
Keep the gateway on localhost and connect through an SSH tunnel or Tailscale, as the OpenClaw docs recommend, instead of opening port 18789 to the internet.
Which plan should I choose?
4 GB of RAM suits one personal assistant. Choose 8 GB for browser automation or several channels, and 16 GB for several assistants.
Does ClientVPS provide API keys or model access?
No. We provide the server. OpenClaw uses your own account with a model provider such as Anthropic, OpenAI or OpenRouter, and you pay the provider directly.
Do you install and run the agent for me?
No. Our VPS plans are self-managed: you install OpenClaw yourself and run its gateway as a systemd service. The setup steps above show each command.
How can I pay?
The OpenClaw VPS plans on this page start at … a month on yearly billing, which saves 15%, or … a month paid monthly. You pay in cryptocurrency, such as Bitcoin, USDT and Monero, or from your ClientVPS account balance, and you only need an email address to sign up.
Ready to run OpenClaw around the clock?
Pick a plan, deploy Ubuntu in minutes and follow the guide above. Pay with crypto or your account balance.
OpenClaw is an independent open-source project. ClientVPS is not affiliated with or endorsed by the OpenClaw project.