🦞
🍎

macOS Installation

Mac / Mac Mini setup guide

Recommended for beginners

Why Mac?

  • • Native Apple Silicon performance
  • • Run Ollama locally for free AI
  • • Perfect "always-on" home server with Mac Mini
  • • No cloud costs - runs on your own hardware

macOS App Features

  • • Menu bar integration for quick access
  • • Canvas support for visual workflows
  • • Full permissions management for Accessibility, Screen Recording, etc.
  • • LaunchAgent (bot.molt.gateway) for automatic startup

Requirements

macOS Version

12.0+ (Monterey or later)

RAM

8GB+ (16GB for Ollama)

Storage

10GB free space

Processor

Apple Silicon or Intel

Installation Steps

1

Install Homebrew (if not installed)

Homebrew is the package manager for macOS.

$/bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/HEAD/install.sh)"
2

Install Node.js

OpenClaw requires Node.js 22 or higher.

$brew install node@22
3

Install OpenClaw

This will download and set up OpenClaw in your home directory.

$curl -fsSL https://openclaw.ai/install.sh | bash
4

Configure your AI provider

Add your API key for Claude, GPT-4, or set up Ollama. Config is stored in ~/.openclaw/openclaw.json.

$openclaw config
5

Start OpenClaw

Complete the onboarding and install the gateway daemon (runs on port 18789).

$openclaw onboard --install-daemon

Optional: Run Free with Ollama

Install Ollama to run AI models locally with zero API costs:

Install Ollama:

$brew install ollama

Download a model:

$ollama pull llama3.1

Configure OpenClaw to use Ollama:

$openclaw config --provider ollama --model llama3.1
Learn more about Ollama →

Next Steps

Connect OpenClaw to your favorite messaging apps.

Browse SkillsTroubleshooting