Home / Docs / Getting Started

Getting Started with OpenClaw

Get your personal AI assistant up and running in under 5 minutes. This guide will walk you through installation, configuration, and your first interaction.

Prerequisites

Before you begin, make sure you have:

  • Node.js 18+ - Download from nodejs.org
  • An API key - From Anthropic (Claude), OpenAI (GPT-4), or another supported provider
  • A messaging platform (optional) - Telegram, Discord, WhatsApp, etc.

Quick Installation

Install OpenClaw globally using npm:

npm install -g openclaw

Verify the installation:

openclaw --version

Initialize Your Workspace

Create a new workspace and configuration:

openclaw init

This creates:

  • ~/.openclaw/ - Main configuration directory
  • ~/.openclaw/config.yaml - Your configuration file
  • ~/.openclaw/workspace/ - Working directory for files

Configure Your API Key

Edit your configuration file to add your API key:

# ~/.openclaw/config.yaml

model:
  provider: anthropic
  model: claude-sonnet-4-20250514
  apiKey: sk-ant-your-api-key-here

💡 Multiple Providers

OpenClaw supports multiple AI providers including Anthropic (Claude), OpenAI (GPT-4), Google (Gemini), and more. You can even use different models for different tasks.

Start the Gateway

Launch the OpenClaw gateway service:

openclaw gateway start

You should see output like:

🚀 OpenClaw Gateway started
📡 Web interface: http://localhost:3000
✓ Ready for connections

Your First Conversation

Open the web interface at http://localhost:3000 and start chatting with your assistant!

Try asking it to:

  • Search the web for current information
  • Read and analyze files
  • Execute shell commands
  • Set reminders and scheduled tasks

Next Steps

📱

Connect Messaging Channels

Set up Telegram, Discord, WhatsApp, or other messaging platforms.
🧩

Explore Skills

Discover and install skills to extend your assistant's capabilities.