GitHubDiscord

Getting Started with OpenClaw: Complete Installation Guide

SetupInstallationRequirements

Getting Started with OpenClaw: Complete Installation Guide

How to install OpenClaw: system requirements, installation commands, configuration, and first run. Start your OpenClaw server with this step-by-step guide.

8 min readLast updated Feb 20, 2026
Stuck?Check the troubleshooting index or ask in Discord.

Prerequisites & Requirements

Before installing OpenClaw, make sure your system meets the minimum requirements.

  • 64-bit Linux, macOS, or WSL2 on Windows
  • 4 GB RAM minimum (8 GB recommended)
  • Node.js 22+ (check with node --version)
  • A supported model backend (Ollama, vLLM, or compatible API)
Check your Node version
OpenClaw requires Node.js 20 or later. Run node --version to verify. Older versions will fail silently during startup.

Installation

Choose your platform below for the appropriate install commands.

The easiest way to install OpenClaw on macOS or Linux:

terminal
curl -fsSL https://openclaw.ai/install.sh | bash

For Windows (PowerShell):

powershell
iwr -useb https://openclaw.ai/install.ps1 | iex

First Run

After installation, run the onboarding wizard to configure your Gateway:

terminal
openclaw onboard --install-daemon

The wizard will guide you through setting up authentication, gateway settings, and optional channels.

1

Run the wizard

Run the onboarding command above. It will prompt you for:

  • API key configuration (Anthropic, OpenAI, etc.)
  • Gateway settings
  • Optional channel setup (Telegram, Discord, WhatsApp)
2

Check Gateway status

If you installed as a service, it should already be running:

bash
openclaw gateway status
3

Open the dashboard

Launch the Control UI in your browser:

bash
openclaw dashboard

Or open http://127.0.0.1:18789/ on the gateway host.

Verify Installation

Check your Gateway status:

terminal
openclaw gateway status

# Or check the health endpoint:
curl http://localhost:18789/api/health
Tip
If the health endpoint returns models: 0, your model backend is likely not running. Check the troubleshooting guide for common errors.

Next Steps

  • Set up a reverse proxy for production access (Caddy or Nginx)
  • Configure model routing and context window settings
  • Review the performance tuning guide for high-traffic deployments
  • Join the Discord community for support and config sharing