DEV Community

zhiku
zhiku

Posted on

How to Set Up a Self-Hosted AI Gateway for 181+ Providers with Wenker Router

#ai #agents #programming #api

Managing multiple LLM APIs across different tools and extensions can quickly get chaotic. Wenker Router solves this by offering an open-source, self-hosted AI gateway that centralizes over 181+ providers and models under a single entry point running on your local machine.

Whether you're developing locally, using VS Code, or routing requests across multiple services, here is how you can set up and run Wenker Router in minutes.

🌟 Key Features

  • 181+ Providers & Models: Unified interface for OpenAI, Anthropic, Gemini, DeepSeek, Kimi, and many more.
  • Localhost-First: Complete control over your API keys, prompts, and local environment.
  • Full Developer Suite: Comes out of the box with a Web Landing UI, Admin UI, and VS Code extension integration (IDE/wenker-vscode).
  • Open Architecture: Clean workspace split into modular packages (server, client, web, system-prompts, scripts).

🚀 Quick Start Guide

1. Clone the Repository

Start by cloning the repository to your local workspace:

git clone [https://github.com/WENKER-AI/wenker-router.git](https://github.com/WENKER-AI/wenker-router.git)
cd wenker-router
Enter fullscreen mode Exit fullscreen mode

2. Install Dependencies

Install all necessary packages for the server, client, and web interface:

npm install
Enter fullscreen mode Exit fullscreen mode

3. Launch the Gateway

For Windows users, you can run the quick setup batch file directly:

./start.bat
Enter fullscreen mode Exit fullscreen mode

Or start the server and client components manually:

npm run dev
Enter fullscreen mode Exit fullscreen mode

Once running, your local router will be active on localhost, ready to listen for local proxy requests and UI interactions.

🛠️ VS Code Integration

To integrate Wenker Router directly into your development workflow:

  1. Navigate to the IDE/wenker-vscode directory in the repo.
  2. Follow the setup instructions inside to link the VS Code extension to your local router server.
  3. Enjoy seamless AI-assisted coding using any of the 181+ supported models directly within your editor!

🤝 We are Looking for Contributors!

Wenker Router is 100% open-source under the MIT license. We are actively inviting developers to join and build with us!

Here are a few ways you can contribute:

  • Add new AI Provider Adapters / Models
  • Improve UI/UX for the Web Landing and Admin dashboard
  • Optimize token usage and implement intelligent fallback routing
  • Enhance VS Code Extension capabilities

🔗 GitHub Repository: https://github.com/WENKER-AI/wenker-router

If you find this project useful, feel free to give it a ⭐ Star on GitHub and submit your Pull Requests!
Enter fullscreen mode Exit fullscreen mode

Top comments (0)