OpenClawMode
Back to articles
10 min readTutorial

Complete Guide to Setting Up OpenClawMode in 2026

Step-by-step instructions for installing and configuring OpenClawMode on macOS, Windows, and Linux with all the tips you need for a smooth setup.

Getting OpenClawMode up and running is easier than you might think. This guide walks you through every step of the installation process.

Prerequisites

Before installing OpenClawMode, ensure you have:

  • macOS, Windows, or Linux: machine
  • Node.js 18+: or use the automatic installer
  • A Claude API key: (or other supported LLM provider)
  • A messaging platform: (Telegram, Discord, or WhatsApp recommended)

    • Installation Methods

    One-Liner Install (Recommended)

    The fastest way to get started:

    # macOS/Linux
curl -fsSL https://openclaw.ai/install.sh | bash

# Windows (PowerShell)
irm https://openclaw.ai/install.ps1 | iex

    NPM Install

    If you prefer npm:

    npm i -g openclaw
openclaw onboard

    Hackable Install

    For those who want to dig into the source:

    git clone https://github.com/openclaw/openclaw.git
cd openclaw
npm install
npm start

    The Onboarding Process

    Running openclaw onboard starts an interactive setup that:

  • Configures your LLM provider (Claude, GPT, local models)
  • Sets up your preferred messaging channels
  • Creates your assistant's persona
  • Tests the connection

    • Connecting Messaging Platforms

    Telegram (Most Popular)

  • Create a bot via @BotFather
  • Get your bot token
  • Add it during onboarding or via `openclaw config`

    • Discord

  • Create a Discord application
  • Add the bot to your server
  • Configure the bot token in OpenClaw

    • WhatsApp

    OpenClawMode supports WhatsApp through various bridges. Check the documentation for the latest setup instructions.

    Your First Conversation

    Once setup is complete, send a message to your assistant:

    "Hi, what can you do?"

    Watch as OpenClawMode introduces itself and explains its capabilities. From here, you can start delegating tasks immediately.

    Troubleshooting

    Common issues and solutions:

  • Connection errors: Check your API keys and network
  • Permission issues: Run with appropriate permissions
  • Model limits: Consider using a larger context model

    • Conclusion

    Setup takes about 5 minutes, and the payoff is enormous. You now have a personal AI assistant that actually understands you and can take action.