OpenClaw on a VPS
Run OpenClaw on a virtual private server — provider comparison and setup
Run OpenClaw on a virtual private server — provider comparison and setup
Running OpenClaw on a VPS gives you 24/7 availability without keeping a home machine on. The good news: OpenClaw is lightweight on the server side. The AI computation happens on your LLM provider (OpenAI, Anthropic, Ollama cloud, etc.), so your VPS mainly runs Node.js, channel connections, and the gateway. That means a modest VPS—1–2GB RAM, single vCPU—is usually enough for personal or small-team use.
This guide covers minimum requirements, recommended providers, and step-by-step setup. We've focused on Hetzner and DigitalOcean as the most popular choices for OpenClaw self-hosters, with notes on Vultr, Hostinger, Oracle Cloud, and others.
OpenClaw needs:
Important: If you use cloud LLMs (Anthropic, OpenAI, etc.), the VPS doesn't run the models. Heavy lifting happens on their servers. Your VPS only handles the Gateway, channel connections, and tool execution. That's why a small VPS works.
Here are the top providers for OpenClaw, with real-world pricing and notes:
EU-based, GDPR-friendly, and 2–3x more compute per dollar than AWS/GCP. CX11 (~$4/mo, 2GB RAM) works; CX22 ($4/mo, 2 vCPU, 4GB) or CX32 ($10/mo, 4 vCPU, 8GB) are more comfortable. German and Finnish data centers.
1-Click Deploy from the marketplace, excellent docs, $200 free credit for new users. Basic Droplet $6/mo (1GB) or $12/mo (2GB) recommended. Simple UI, predictable pricing.
32 datacenters worldwide. Cloud Compute $6/mo (1 vCPU, 1GB) comparable to DigitalOcean. Good if you need a specific region (Asia, South America, etc.).
$5.99/mo intro (1 vCPU, 4GB RAM, 50GB NVMe). One-click OpenClaw template, sometimes bundled AI credits. Limited US datacenter coverage.
Always Free tier: 4 ARM CPUs, 24GB RAM, 200GB storage. Enough to run OpenClaw + Ollama with local models. ARM architecture, slightly more complex setup.
One-click deploy, web setup wizard. $5/mo Hobby plan. Best for testing and development—cheapest way to try OpenClaw in the cloud.
~€5/mo, 9 regions, unlimited traffic, dedicated OpenClaw hosting page. Good for EU users.
Cheapest OpenClaw VPS option. Docker template, Ubuntu 24.04. 1GB RAM entry; upgrade for production.
Simple Application Server, Model Studio. Qwen Max, Plus, Flash, 3.5. Low latency for APAC users.
33 datacenters, 99.99% uptime. Optional full server management. EU-focused.
Dedicated OpenClaw page. VPS from ~$9/mo, dedicated from ~$70/mo. DDoS protection.
Once you have a VPS with Ubuntu or Debian:
curl -fsSL https://openclaw.ai/install.sh | bash
npm install -g pm2
openclaw init
pm2 start 'openclaw gateway start' --name openclaw
pm2 save
pm2 startup
Enable UFW firewall for ports 22 (SSH), 80 (HTTP), and 443 (HTTPS). For full setup including reverse proxy and SSL, see our Deployment tutorial and the provider-specific guides below.
For reproducible deployments, use Docker. The Docker guide covers building and running OpenClaw in containers. Many providers (DigitalOcean, Hetzner) support Docker out of the box. Benefits: consistent environment, easy updates, isolation.
Running OpenClaw on a local device (your Mac, Linux box, or Windows machine) often improves day-to-day productivity: you can airdrop files, use local paths, and get lower latency. Workflows like "drop a video, get transcript and thumbnails" are much easier when the Gateway and workspace live on a machine you use daily.
Use a VPS when you need 24/7 reachability (e.g. WhatsApp always online), don't have suitable local hardware, or want to isolate the assistant from your main machine. Prefer no servers at all? See Managed hosting—Clawi, xCloud, MyClaw.ai let you get WhatsApp and Telegram connected without running any infrastructure. More in Tips & best practices.