OpenClaw

This documentation is provided for informational purposes only and demonstrates how to configure and use our API with third-party AI chat interfaces. Any third-party software, websites, or services mentioned are not operated, controlled, or endorsed by us.

Introduction to OpenClaw

OpenClaw is a personal AI assistant you run on your own devices. It answers you on the channels you already use (WhatsApp, Telegram, Slack, Discord, Google Chat, Signal, iMessage, BlueBubbles, IRC, Microsoft Teams, Matrix, Feishu, LINE, Mattermost, Nextcloud Talk, Nostr, Synology Chat, Tlon, Twitch, Zalo, Zalo Personal, WeChat, WebChat). It can speak and listen on macOS/iOS/Android, and can render a live Canvas you control. The Gateway is just the control plane — the product is the assistant.

OpenClaw Key Features:

• Autonomous AI agent that executes real tasks
• Self-hosted with full data control
• Multi-channel (Telegram, Slack, Web, etc.)
• Extensible skill/plugin system
• Supports multiple AI models
• Persistent memory across sessions
• Built for automation & workflows

Step

Install OpenClaw

OpenClaw requires Node >= 22.14, please install the newest LTS version of Node.js.

After installation is complete, open the terminal (Windows users use PowerShell) and check the version number.

• macOS, Linux, Windows:

node -v

If it cannot be displayed correctly, please search for related issues and make sure that your current system version is not outdated.

Windows users may be unable to run scripts because of digital signature requirements. Please run the following command:
Windows PowerShell:

Set-ExecutionPolicy -Scope CurrentUser -ExecutionPolicy RemoteSigned -Force

Install OpenClaw.

npm install -g openclaw@latest

Configure OpenClaw

Windows users may encounter issues running the software due to missing VC runtime libraries. Please download and install this software.

Open the terminal and run the following command to begin configuration.

openclaw onboard

Select “Yes”, “QuickStart”.

Select “Custom Provider”.

Here are example model configurations compatible with both Anthropic and OpenAI formats.

Claude Opus 4.7

Field	Content
API Base URL	https://router-link.world3.ai/api
API Key	Obtain one from RouterLInk
Endpoint compatibility	Anthropic-compatible
Model ID	claude-opus-4-7

GPT-5.3-Codex

Field	Content
API Base URL	https://router-link.world3.ai/api/v1
API Key	Obtain one from RouterLInk
Endpoint compatibility	OpenAI-compatible
Model ID	gpt-5.5

Gemini 3.1 Pro Preview

Field	Content
API Base URL	https://router-link.world3.ai/api/v1
API Key	Obtain one from RouterLInk
Endpoint compatibility	OpenAI-compatible
Model ID	gemini-3.1-pro-preview

You can add other models based on these:

Next, you can configure it as needed.

Start using OpenClaw

Run

openclaw gateway

Verify the Gateway is running

openclaw gateway status

You should see the Gateway listening on port 18789.

Open the dashboard

openclaw dashboard

This opens the Control UI in your browser. If it loads, everything is working.

Send your first message.

Type a message in the Control UI chat and you should get an AI reply.

Want to chat from your phone instead? The fastest channel to set up is Telegram (just a bot token). See Channels for all options.

Troubleshooting

How to add a model

Run it again

openclaw onboard

Select “Use existing values” in Config handling.Add the new model you need under Custom Provider.

The Gateway process is already in use

openclaw gateway stop
openclaw gateway
openclaw dashboard

How can I upgrade OpenClaw?

Enter the following command in the terminal:

openclaw update

For more information

Please check the official documentation.