[This tutorial is based on official docs — docs.openclaw.ai]
This program concerns Windows Installation & Configuration Guide.
What is OpenClaw?
OpenClaw is an open-source, self-hosted AI gateway that connects popular chat apps — WhatsApp,
Telegram, Discord, iMessage, and more — to AI coding agents. You run a single Gateway process
on your own machine or server, and it becomes the bridge between your messaging apps and an
always-available AI assistant. Your data stays entirely under your control.
Key highlights:
• Self-hosted: runs on your hardware, your rules;
• Multi-channel: one Gateway serves WhatsApp, Telegram, Discord, and more simultaneously;
• Agent-native: built for coding agents with tool use, sessions, memory, and multi-agent routing;
• Open source: MIT licensed, community-driven;
System Requirements
Before you begin, make sure your environment meets the following requirements:
Step 1: Install OpenClaw
OpenClaw provides an official one-line installer that automatically detects your OS, installs Node.js if needed, installs OpenClaw, and launches the onboarding wizard.
Open PowerShell and run the following single command:
The script handles everything: Node.js detection, OpenClaw installation, and launching the onboarding wizard.
If Node.js (v22.16+ or v24) is already installed, you can install directly via npm:
After installation, run the following commands to confirm everything is working:
The doctor command automatically checks for configuration issues and suggests fixes.
Step 2: Run Onboarding
The onboard wizard is OpenClaw's interactive setup flow. It guides you through choosing an AI model provider, entering your API key, and installing the Gateway as a background service. The whole process takes about 2 minutes.
The wizard will walk you through the following steps:
1. Choose an AI model provider (Anthropic, OpenAI, Ollama, etc.)
2. Enter the corresponding API key, or select a local Ollama model
3. Install the Gateway as a system service (auto-starts on boot)
To use Ollama local models without any API key, first install Ollama and pull a model:
4. Download and install Ollama from: https://ollama.com/download
5. Pull a model (llama3.3 shown here as an example):
Other popular models you can pull:
Then run onboard and select Ollama from the provider list. The wizard will automatically discover all locally available models.
During onboarding, select your preferred provider and paste the corresponding API key when prompted. Supported providers include:
Step 3: Start and Verify the Gateway
After onboarding completes, run the following command to confirm the Gateway is running:
A healthy output will show Runtime: running and RPC probe: ok
Launch the OpenClaw web control panel in your browser with:
The dashboard opens at: http://127.0.0.1:18789/
If the dashboard loads and you can send a message and receive an AI reply, your setup is complete.
Gateway Management
Common commands for day-to-day Gateway operations:
Troubleshooting
Resources
• Official Docs: https://docs.openclaw.ai
• GitHub Repository: https://github.com/openclaw/openclaw
• Discord Community: https://discord.com/invite/clawd
• Ollama Model Library: https://ollama.com/library
• Windows Platform Guide: https://docs.openclaw.ai/platforms/windows
• Provider Configuration: https://docs.openclaw.ai/providers
• Gateway Runbook: https://docs.openclaw.ai/gateway