Getting Started with OpenClaw

Complete step-by-step tutorial to install, configure, and run your first OpenClaw AI assistant

This tutorial will guide you through installing and setting up OpenClaw (formerly Moltbot, Clawdbot) from scratch. By the end, you'll have a working AI assistant ready to use. Estimated time: 15-20 minutes.

Prerequisites

Before you begin, ensure you have:

  • Node.js 22+ installed (or use the one-liner installer which includes it)
  • An AI model subscription (Anthropic Claude Pro/Max recommended, or OpenAI ChatGPT Plus)
  • macOS, Linux, or Windows (Windows users should use WSL2)
  • Terminal/Command Prompt access

Step 1: Install OpenClaw

We'll use the one-liner installation method, which is the easiest for beginners. It automatically installs Node.js and all dependencies.

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

What this does: This single command downloads and runs the OpenClaw installer, which will:

  • Check if Node.js is installed (installs it if missing)
  • Install OpenClaw globally via npm
  • Set up the necessary dependencies

Platform support: Works on macOS, Linux, and Windows (via Git Bash or WSL2).

💡 Alternative Methods: If you prefer npm directly or need Docker/source installation, see the Installation Reference Guide for all available methods.

Verify Installation

After installation completes, verify it worked:

Verify Installation 
openclaw --version

You should see a version number (e.g., 2026.1.29). If you get "command not found", try restarting your terminal or check that Node.js is in your PATH.

Step 2: Run the Onboarding Wizard

The onboarding wizard is the easiest way to set up OpenClaw. It provides an interactive Terminal User Interface (TUI) that guides you through the entire setup process.

Start Onboarding 
openclaw onboard --install-daemon

The wizard will launch an interactive terminal UI and guide you through:

  • Confirmation to continue setup
  • Onboarding mode selection - Choose QuickStart (recommended for beginners) which configures everything with safe defaults
  • Gateway configuration and local setup
  • Model selection and authentication
  • Channel connections (Telegram, WhatsApp, Discord, etc.)
  • Skill installation (optional)
  • API key configuration (optional)
✅ QuickStart Mode: When prompted, select QuickStart by pressing the spacebar and then Enter. This uses safe defaults and lets you focus on getting the bot working first. You can customize settings later.
💡 Tip: The --install-daemon flag installs the Gateway as a background service. On macOS, it uses launchd; on Linux, it uses systemd.

Step 3: Configure Your AI Model

After QuickStart completes, the wizard will prompt you to set up your AI model. The wizard will show you a list of available model providers.

Supported Model Providers

OpenClaw supports multiple AI model providers:

  • Anthropic Claude - Recommended for best quality (Pro/Max subscription with OAuth)
  • OpenAI - ChatGPT Plus or API access
  • Google Gemini - Via Google Antigravity OAuth (requires Gmail account)
  • Other providers - Gemini, Moonshot, Minimax, and more

Authentication Methods

Depending on your chosen provider, you'll authenticate using:

  • OAuth - For subscription services (Claude Pro/Max, ChatGPT Plus, Google Gemini). The wizard will open a browser for authentication.
  • API Keys - For pay-per-use services. You'll paste your API key when prompted.
📱 Google/Gemini Example: If you select Google, you'll see options including "Google Antigravity OAuth". Select this, then log into your Gmail account when prompted. After authentication, you'll see available Gemini models (e.g., gemini-3-flash) to choose from.

Recommended: Anthropic Claude

We recommend Anthropic Claude Pro/Max with Opus 4.5 because it offers:

  • Excellent long-context handling for complex conversations
  • Better protection against prompt injection attacks
  • High-quality, nuanced responses
  • OAuth authentication (no API keys needed with subscription)
✅ OAuth Setup: If you have an Anthropic Pro/Max subscription, the wizard will guide you through OAuth authentication. This is more secure than API keys and doesn't require managing credentials manually.

After configuration: Your settings are saved to ~/.clawdbot/moltbot.json (or ~/.openclaw/ for newer installations). For advanced configuration options, see the Configuration Reference.

Step 4: Choose Your Interface (TUI or Control UI)

After setting up your model and channels, the wizard will ask you to choose how you want to interact with OpenClaw:

🖥️ Terminal UI (TUI)

Recommended for first-time setup. Everything stays in your terminal. Provides direct, immediate feedback and shows the same conversation flow you'll see in Telegram later.

🌐 Control UI (Browser)

Web-based dashboard that opens in your browser. Access it via the Web UI link shown in your terminal (typically http://localhost:18789).

For this tutorial, select "Hatch in TUI" to continue with the terminal interface.

Step 5: Configure Your Agent's Personality

When you select "Hatch in TUI", the wizard will ask you some simple questions to personalize your agent:

  • Bot's name - What should your assistant be called? (e.g., "Becky", "Alex", "Assistant")
  • What it can call you - How should the bot address you? (e.g., your first name, "User", "Boss")

After answering these questions, your OpenClaw will confirm its setup with a personalized response that reflects the personality you've configured. This is your agent's "hatching" moment!

✅ Success! Your agent now has a unique identity and is ready to receive commands through both the terminal and your connected messaging platform.

Step 6: Verify Gateway Status

If you used --install-daemon, the Gateway should already be running. Verify it's active:

Check Gateway Status 
openclaw gateway status

If the Gateway isn't running, start it manually:

Start Gateway 
openclaw gateway --port 18789 --verbose

You should see output indicating the Gateway is running and listening on port 18789.

Step 7: Test Your Setup

Now let's verify everything works by sending a test message:

Option A: Via CLI

Send Test Message 
openclaw agent --message "Hello! Can you introduce yourself?"

Option B: Via Connected Channel

If you set up a channel (Telegram, WhatsApp, etc.) during onboarding, simply send a message to your bot. It should respond!

✅ Success! If you received a response, congratulations! Your OpenClaw assistant is working correctly.

Step 8: Next Steps

Now that you have OpenClaw running, here's what to explore next:

💬 Connect Channels

Set up WhatsApp, Telegram, or Discord to chat with your assistant.

Setup Channel →

🔧 Install Skills

Extend functionality with community-built skills from ClawHub.

Browse Skills →

📚 Learn More

Explore advanced features and customization options.

Usage Guide →

Troubleshooting

If you encounter issues:

  • Gateway won't start: Check if port 18789 is already in use: lsof -i :18789
  • Authentication errors: Verify your API keys or OAuth tokens in the configuration file
  • Model not responding: Check your model subscription status and API limits
  • Installation issues: Ensure Node.js 22+ is installed: node --version

For more help, see our Troubleshooting Guide or FAQ.

Continue Learning

Reference Documentation