​
Installation

Install the VibeKit Proxy package: 
npm install @vibe-kit/proxy

​
Start the Proxy Server

Launch the proxy server: 
npx @vibe-kit/proxy start
The proxy is now running at http://localhost:8080 and ready to intercept AI requests.

​
Additional Commands

# Check proxy status
npx @vibe-kit/proxy status

# Stop the proxy server
npx @vibe-kit/proxy stop

​
Update Your Application

Simply change your base URL to point to the VibeKit proxy:

​
Before

const client = new OpenAI({
  baseURL: 'https://api.openai.com/v1',
  apiKey: process.env.OPENAI_API_KEY,
});

​
After

const client = new OpenAI({
  baseURL: 'http://localhost:8080/v1',
  apiKey: process.env.OPENAI_API_KEY,
});

​
Test Your Setup

Make a test request to verify everything is working: 
const response = await client.chat.completions.create({
  model: "gpt-4",
  messages: [
    { role: "user", content: "My SSN is 123-45-6789. What can you tell me about privacy?" }
  ],
});

console.log(response.choices[0].message.content);
// The SSN will be automatically redacted in both the request and response

​
Configuration Options

You can customize the proxy with these options: 
# Start with custom port
npx @vibe-kit/proxy start --port 3000

# Run in background (daemon mode)
npx @vibe-kit/proxy start --daemon

# Check status on specific port
npx @vibe-kit/proxy status --port 3000

# Stop proxy on specific port
npx @vibe-kit/proxy stop --port 3000