{"id":33111,"date":"2026-08-05T17:59:22","date_gmt":"2026-08-05T15:59:22","guid":{"rendered":"https:\/\/contabo.com\/blog\/?p=33111"},"modified":"2026-08-05T17:59:26","modified_gmt":"2026-08-05T15:59:26","slug":"how-to-install-openclaw-on-a-vps-complete-setup-guide","status":"publish","type":"post","link":"https:\/\/contabo.com\/blog\/how-to-install-openclaw-on-a-vps-complete-setup-guide\/","title":{"rendered":"How to Install OpenClaw on a VPS: Complete Setup Guide"},"content":{"rendered":"\n

Installing OpenClaw on a VPS <\/a>requires a Linux server (Ubuntu 22.04 or 24.04 LTS recommended), SSH access, an AI model API key or Ollama for local inference, and credentials for at least one messaging platform. The official page documents a three-step process: choose plan, SSH into the onboarding wizard, and launch via terminal or the Control UI over an SSH tunnel. Manual install from the OpenClaw GitHub repository follows a similar flow \u2014 verify all commands from the repository README before running.<\/p>\n\n\n\n

The Pre-Installed Option: Contabo OpenClaw Hosting<\/h2>\n\n\n\n

The fastest path to a running OpenClaw instance is a Contabo VPS plan with OpenClaw pre-installed. The official page confirms the three-step process:<\/p>\n\n\n\n

    \n
  1. Choose a plan at contabo.com\/en\/openclaw-hosting\/<\/a> \u2014 plans are labelled by use case (Personal Use, Power User, Team Deployment, Enterprise Scale). See the page for current pricing.<\/li>\n\n\n\n
  2. Once the server is deployed, connect via SSH and run the onboarding wizard. Add your AI provider API keys (they are encrypted on setup), connect your messaging apps, and configure your preferences.<\/li>\n\n\n\n
  3. Launch the terminal interface to interact with your assistant directly, or access the Control UI securely via SSH tunnel.<\/li>\n<\/ol>\n\n\n\n

    Contabo provides full technical support for the VPS infrastructure and the initial 1-click installation. Configuring, maintaining, and troubleshooting OpenClaw itself is the user’s responsibility. For app-level questions, refer to the OpenClaw documentation and GitHub community.<\/p>\n\n\n\n

    Manual Install: Prerequisites<\/h2>\n\n\n\n

    If you prefer to install from the OpenClaw GitHub repository, gather these before starting:<\/p>\n\n\n\n

      \n
    • A Linux VPS \u2014 Ubuntu 22.04 LTS or 24.04 LTS recommended. Verify supported distributions from the OpenClaw GitHub README.<\/li>\n\n\n\n
    • SSH root or sudo access.<\/li>\n\n\n\n
    • Sufficient RAM for your planned AI model (see the RAM requirements section below).<\/li>\n\n\n\n
    • An AI model API key \u2014 OpenAI, Anthropic, or Google \u2014 or plan to use Ollama for local inference at no API cost.<\/li>\n\n\n\n
    • Messaging platform credentials: bot token or webhook URL for your chosen app.<\/li>\n\n\n\n
    • Optionally: a domain name to point at your VPS for a clean gateway URL.<\/li>\n<\/ul>\n\n\n\n

      Step 1: Prepare Your VPS<\/h2>\n\n\n\n
        \n
      • Update the system:
        \u00a0\u00a0\u00a0 sudo apt update && sudo apt upgrade -y<\/li>\n\n\n\n
      • Create a non-root user for running OpenClaw:
        \u00a0\u00a0\u00a0 adduser openclaw-user
        \u00a0\u00a0\u00a0 usermod -aG sudo openclaw-user
        \u00a0 Switch to this user \u2014 never run OpenClaw as root.<\/li>\n\n\n\n
      • Configure UFW firewall:
        \u00a0\u00a0\u00a0 sudo ufw default deny incoming
        \u00a0\u00a0\u00a0 sudo ufw allow OpenSSH
        \u00a0\u00a0\u00a0 sudo ufw enable<\/li>\n\n\n\n
      • Activate the Contabo network-level Firewall before opening any other ports: new.contabo.com \u2192 Network Services \u2192 Firewall \u2192 block all inbound by default.<\/li>\n<\/ul>\n\n\n\n

        Step 2: Install OpenClaw<\/h2>\n\n\n\n

        Verify the exact commands from the OpenClaw GitHub repository before running \u2014 the project is actively developed and install steps change between releases. General flow:<\/p>\n\n\n\n

          \n
        • Clone the repository (verify current URL from official OpenClaw documentation):
          \u00a0\u00a0\u00a0 git clone https:\/\/github.com\/[openclaw-repo] openclaw
          \u00a0\u00a0\u00a0 cd openclaw<\/li>\n\n\n\n
        • Install the required runtime \u2014 check the README for whether Node.js or Python is required for your version:
          \u00a0\u00a0\u00a0 # Node.js example:
          \u00a0\u00a0\u00a0 npm install<\/li>\n\n\n\n
        • Copy the environment file template and configure it:
          \u00a0\u00a0\u00a0 cp .env.example .env
          \u00a0\u00a0\u00a0 nano .env
          \u00a0 Add your AI model API key and gateway credentials. Save the file.<\/li>\n\n\n\n
        • Follow any additional setup steps in the repository README.<\/li>\n<\/ul>\n\n\n\n

          Step 3: Connect Your Messaging App<\/h2>\n\n\n\n

          The following messaging platforms are confirmed on the official page: WhatsApp, Telegram, Discord, Slack, Signal, iMessage, Microsoft Teams.<\/p>\n\n\n\n

          Telegram<\/h3>\n\n\n\n

          Create a bot via @BotFather on Telegram: send \/newbot, follow the prompts, copy the bot token. Add the token to your .env file \u2014 verify the exact key name from OpenClaw documentation.<\/p>\n\n\n\n

          Discord<\/h3>\n\n\n\n

          Create a Discord application at discord.com\/developers\/applications, add a Bot, copy the token and add to .env. Generate an OAuth2 invite URL with the bot scope and required permissions, then invite the bot to your server. Verify required permissions from OpenClaw docs.<\/p>\n\n\n\n

          Slack<\/h3>\n\n\n\n

          Create a Slack app at api.slack.com\/apps. Use the app manifest method if available. Copy the bot token and signing secret to .env. Verify the current Slack manifest template from OpenClaw documentation.<\/p>\n\n\n\n

          WhatsApp<\/h3>\n\n\n\n

          WhatsApp integration method varies \u2014 verify the current supported approach from the OpenClaw GitHub repository before proceeding, as platform policy changes affect available methods.<\/p>\n\n\n\n

          Step 4: Configure Your AI Model<\/h2>\n\n\n\n

          Add credentials for your chosen AI model to .env. All four providers below are confirmed on the official page:<\/p>\n\n\n\n\n