Build Your Personal AI Infrastructure in 5 Hours

Transform your computer into an autonomous AI command center. This guide walks you through installation, configuration, and your first automated taskā€”without assuming you're a sysadmin.

Before We Begin: Understanding What You're Building

Most AI installation guides treat software as a black box: download, install, forget. Clawdbot is different because you're not installing an appā€”you're establishing infrastructure. Think of this as setting up your own private email server, except instead of managing messages, you're orchestrating an AI that can genuinely control your digital environment.

This guide explains what each step does and why it matters. Understanding the architecture makes troubleshooting intuitive and customization straightforward.

What You'll Have After 5 Hours

  • A Gateway service running persistently on your device, coordinating all AI activity
  • Connection to your chosen AI model (Claude, GPT-4, or free local Ollama)
  • At least one messaging channel (WhatsApp, Telegram, etc.) linked to your AI
  • A functioning automation that demonstrates genuine system control
  • Understanding of how to extend, customize, and troubleshoot your setup

Prerequisites: What You Actually Need

Hardware Requirements

  • ā€¢ Operating System: macOS 11+, Linux (Ubuntu 20.04+, Debian 11+), or Windows 10+ with WSL2
  • ā€¢ RAM: Minimum 2GB available (4GB recommended for smoother operation)
  • ā€¢ Disk Space: 500MB for core installation plus space for AI model caching
  • ā€¢ Network: Stable internet connection for AI API calls (unless using local Ollama)

Software Dependencies

Clawdbot requires Node.js 22 or higher. Why this specific version? Newer Node.js versions include critical performance improvements and security patches that Clawdbot's real-time communication relies on. The installer typically handles this, but manual installations require it pre-installed.

AI Model Access (Choose One)

Cost-Benefit Analysis: Which AI Model Should You Choose?

Option 1: Anthropic Claude (Recommended for most users)

Cost: ~$20-40/month for typical personal useAdvantage: Exceptional reasoning, strong security awareness, long context windows

Option 2: OpenAI GPT-4

Cost: ~$25-50/month depending on usage patternsAdvantage: Broad knowledge base, excellent for creative tasks

Option 3: Local Ollama Models (Completely free)

Cost: $0 (runs entirely on your hardware)Advantage: Zero ongoing costs, complete privacy, offline operationDisadvantage: Slower responses, requires more powerful hardware (8GB+ RAM recommended)

Step 1: Download the Right Package for Your Platform

Clawdbot distributes platform-specific installers that bundle everything needed. Why multiple formats? Different operating systems handle background services differentlyā€”the installer configures these correctly.

macOS Installation

Download the DMG installer for the simplest experience:

curl -fsSL https://github.com/steipete/clawbot/releases/latest/download/Clawdbot.dmg -o Clawdbot.dmg

What the installer does:

  • ā€¢ Installs the Gateway service to /Applications/Clawdbot.app
  • ā€¢ Creates configuration directory at ~/.clawdbot/
  • ā€¢ Configures system permissions for automation capabilities
  • ā€¢ Optionally sets up launch-at-startup (recommended)

Linux Installation

Install via npm (recommended) or Docker:

npm install -g clawdbot@latest

Then initialize the configuration:

clawdbot init

Windows Installation (WSL2)

Windows requires WSL2 (Windows Subsystem for Linux). If not installed:

wsl --install

Windows Native Support

Native Windows support (without WSL2) is experimental. WSL2 provides better compatibility with Node.js system integrations and shell command execution.

Step 2: Install and Launch the Gateway

The Gateway is Clawdbot's coreā€”a persistent service that manages all communication between messaging platforms, AI models, and your system. Think of it as the central nervous system: channels send messages to the Gateway, which routes them to the appropriate AI model, receives responses, and delivers them back.

macOS: Open the downloaded DMG and drag Clawdbot to Applications. Launch it.

Linux/WSL: After npm installation, start the Gateway:

clawdbot gateway start

Verify it's running:

clawdbot gateway status

You should see: Gateway is running on ws://127.0.0.1:18789

What's Happening Behind the Scenes

The Gateway creates a WebSocket server on port 18789 (customizable). This local-only server accepts connections from:

  • ā€¢ Channel plugins (WhatsApp, Telegram, etc.) that forward user messages
  • ā€¢ Node clients (mobile apps, web interfaces) for direct interaction
  • ā€¢ Skills and tools that extend functionality

All communication stays on your machine unless you explicitly configure remote access (covered in advanced guides).

Step 3: Connect Your AI Brain

With the Gateway running, it needs an AI model to generate responses. This step configures which model(s) you'll use and authenticates API access.

Open the configuration file:

clawdbot config edit

Or manually edit ~/.clawdbot/clawdbot.json. Add your API credentials:

{ "aiProviders": { "anthropic": { "apiKey": "sk-ant-your-key", "model": "claude-3-5-sonnet-20250219", "enabled": true } }, "defaultProvider": "anthropic" }

Step 4: Link Your Communication Channels

Channels are how you interact with your AIā€”WhatsApp for mobile, Telegram for desktop, Discord for team collaboration. Each channel connects independently to the Gateway, and Clawdbot maintains a unified conversation history across all of them.

Connect Your First Channel: WhatsApp Example

clawdbot channel add whatsapp

This launches an interactive setup:

1. A QR code appears in your terminal

2. Open WhatsApp on your phone ā†’ Settings ā†’ Linked Devices ā†’ Link a Device

3. Scan the QR code

4. Clawdbot confirms connection and saves session credentials

How it works: Clawdbot uses the WhatsApp Web protocol (via Baileys library) to establish a persistent connection. Your phone remains the "primary" device; Clawdbot acts as a linked secondary deviceā€”just like WhatsApp Web in your browser.

WhatsApp Account Safety

WhatsApp's terms of service prohibit bot usage. While Clawdbot implements rate limiting and human-like behavior patterns, we recommend using a secondary phone number rather than your primary personal WhatsApp account. Consider:

  • - Getting a Google Voice or similar virtual number
  • - Using an old SIM card you don't actively use
  • - Trying Telegram instead (officially supports bots)

Step 5: Execute Your First Autonomous Task

With everything configured, let's verify Clawdbot can genuinely control your systemā€”not just respond with text.

Test System Integration

"Create a file named test.txt in my Documents folder with content 'Hello from Clawdbot'"

What should happen:

1. Clawdbot receives your message through the channel

2. Gateway routes it to your configured AI model

3. AI generates a response plan including shell commands

4. Clawdbot executes: echo "..." > ~/Documents/test.txt

5. You receive confirmation: "Created test.txt with..."

6. Check your Documents folderā€”the file exists

You Just Demonstrated Genuine AI Automation

What distinguishes Clawdbot from ChatGPT or Siri: it didn't just tell you how to create the fileā€”it actually created it. This same capability extends to:

  • Managing your calendar and sending meeting invites
  • Monitoring log files and alerting you to errors
  • Pulling data from APIs and generating reports
  • Controlling smart home devices via Home Assistant
  • Running development workflows (tests, builds, deployments)

What to Build Next

1. Install Skills from ClawdHub

Skills are pre-built automation modules. Browse the marketplace:

  • ā€¢ google-calendar: Natural language calendar management
  • ā€¢ home-assistant: Smart home control integration
  • ā€¢ github-assistant: Repository management and PR reviews
  • ā€¢ daily-briefing: Morning summary of calendar, weather, news

Browse hundreds of additional skills at hub.clawdbot.ai

2. Create Custom Automation

Skills are just folders with a SKILL.md file. Create your own:

Full guide: docs.clawdbot.ai/skills/creating

3. Configure Proactive Behaviors

Unlike traditional AI, Clawdbot can initiate contact. Enable heartbeat monitoring:

Now Clawdbot will proactively send you a morning briefing without being asked.

4. Deploy to the Cloud (Optional)

Running Clawdbot on your laptop works, but cloud deployment ensures 24/7 availability. Guides available for:

Step-by-step cloud guides: docs.clawdbot.ai/deployment

Common Issues and Solutions

Gateway Won't Start

Symptom: Error: EADDRINUSE: address already in use

Cause: Another process is using port 18789.

Solution: Find and kill the conflicting process:

AI Model Returns Errors

Symptom: "API authentication failed" or "Invalid model specified"

Cause: Incorrect API key or model name in configuration.

Solution: Verify your API key is valid:

WhatsApp Disconnects Frequently

Symptom: QR code authentication required every few days.

Cause: Session credentials not persisting correctly.

Solution: Ensure ~/.clawdbot/channels/whatsapp/ has write permissions:

You're Now Running Your Own AI Infrastructure

What you've built isn't just a chatbotā€”it's a personal automation platform that combines the intelligence of frontier AI models with the capability of local system control. Unlike cloud services that constrain what AI can do, your Clawdbot installation has the same access to your digital environment that you do.

This power comes with responsibility: Clawdbot can execute any command you approve. The sandboxing and permission system protects against accidental damage, but ultimately you're granting an AI meaningful control. Start with simple automations, understand how decisions are made, and gradually expand capabilities as you build trust.

Start Building Your AI Infrastructure