# How to integrate RouterLink in OpenClaw {% hint style="info" %} 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. {% endhint %} ## Overview This tutorial guides you through integrating **RouterLink**—WORLD3's decentralized AI model routing infrastructure—with **OpenClaw**, a personal AI assistant you run on your own devices. ### Purpose RouterLink provides a unified API endpoint that routes requests to multiple AI model providers through a decentralized network. By integrating RouterLink with OpenClaw, you gain access to a diverse range of large language models (LLMs) without managing multiple API keys or provider-specific configurations. ### What You Will Learn By completing this tutorial, you will: * **Configure OpenClaw** to connect with RouterLink's API endpoint * **Authenticate** using your RouterLink API credentials with custom headers * **Add and manage AI models** available through the RouterLink network * **Execute inference requests** through OpenClaw's conversational interface ### Prerequisites Before proceeding, ensure you have: * A RouterLink API key (obtain one from the [Quick Start Guide](https://docs.world3.ai/world3/how-to-guides/routerlink/quick-start-guide)) * A web browser with internet access * Basic familiarity with API configuration concepts ## 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 1: Install OpenClaw OpenClaw requires Node >= 22.14, please install [the newest LTS version of Node.js](https://nodejs.org/en/download/)After installation is complete, open the terminal (Windows users use PowerShell) and check the version number. * macOS, Linux, Windows: ```bash node -v ``` If it cannot be displayed correctly, please search for related issues and make sure that your current system version is not outdated.Install OpenClaw ```bash npm install -g openclaw@latest # or: pnpm add -g openclaw@latest ``` ### Step 2: Configure OpenClaw Open the terminal and run the following command to begin configuration. ```bash openclaw onboard ``` Select “Yes”, "QuickStart"
Select “Custom Provider”
Here are example model configurations compatible with both Anthropic and OpenAI formats. #### Claude Opus 4.7 | API Base URL | | | ---------------------- | ---------------------------------------------------------------------------------------------------------------------------------------- | | API Key | A RouterLink API key (obtain one from the [Quick Start Guide](https://docs.world3.ai/world3/how-to-guides/routerlink/quick-start-guide)) | | Endpoint compatibility | Anthropic-compatible | | Model ID | anthropic/claude-opus-4-7 | #### GPT-5.3-Codex | API Base URL | | | ---------------------- | ---------------------------------------------------------------------------------------------------------------------------------------- | | API Key | A RouterLink API key (obtain one from the [Quick Start Guide](https://docs.world3.ai/world3/how-to-guides/routerlink/quick-start-guide)) | | Endpoint compatibility | OpenAI-compatible | | Model ID | world3-router-north-america/openai/gpt-5.3-codex | #### Gemini 3.1 Pro Preview | API Base URL | | | ---------------------- | ---------------------------------------------------------------------------------------------------------------------------------------- | | API Key | A RouterLink API key (obtain one from the [Quick Start Guide](https://docs.world3.ai/world3/how-to-guides/routerlink/quick-start-guide)) | | Endpoint compatibility | OpenAI-compatible | | Model ID | world3-router-north-america/google/gemini-3.1-pro-preview |
You can add other models based on the Integration Guide at
Next, you can configure it as needed. ### Step 3: Start using OpenClaw Run ```bash openclaw gateway ``` Verify the Gateway is running ```bash openclaw gateway status ``` You should see the Gateway listening on port 18789.Open the dashboard ```bash 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](https://docs.openclaw.ai/channels/telegram) (just a bot token). See [Channels](https://docs.openclaw.ai/channels) for all options. ## Troubleshooting ### **How to add a model** Run it again ```bash 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. ```bash openclaw gateway stop openclaw gateway openclaw dashboard ``` ### **How can I upgrade OpenClaw?** Enter the following command in the terminal: ```bash openclaw update ``` ### Need more help? Please check the official documentation: --- # Agent Instructions: Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter: ``` GET https://docs.world3.ai/world3/how-to-guides/routerlink/tutorials/how-to-integrate-routerlink-in-openclaw.md?ask= ``` The question should be specific, self-contained, and written in natural language. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.