This guide will walk you through creating your first bridge. You'll learn how to convert between OpenAI and Anthropic formats in just a few minutes.

Step 1: Install Packages

pnpm add @amux.ai/llm-bridge @amux.ai/adapter-openai @amux.ai/adapter-anthropic

Step 2: Set Up API Keys

Create a .env file:

ANTHROPIC_API_KEY=your_key_here

Never commit your .env file to version control. Add it to .gitignore.

Step 3: Create Your First Bridge

Create bridge.ts:

import { createBridge } from '@amux.ai/llm-bridge'
import { openaiAdapter } from '@amux.ai/adapter-openai'
import { anthropicAdapter } from '@amux.ai/adapter-anthropic'

// Create a bridge: OpenAI format in → Anthropic API out
const bridge = createBridge({
  inbound: openaiAdapter,
  outbound: anthropicAdapter,
  config: {
    apiKey: process.env.ANTHROPIC_API_KEY
  }
})

// Send OpenAI-format request
const response = await bridge.chat({
  model: 'gpt-4',
  messages: [
    { role: 'user', content: 'Say hello!' }
  ]
})

console.log(response.choices[0].message.content)

What happens:

You send a request in OpenAI format
Amux converts it to Anthropic format
Claude API is called
Response is converted back to OpenAI format

Step 4: Run It

tsx bridge.ts

You should see a response from Claude, but in OpenAI format!

Try Streaming

For better user experience, use streaming:

import { createBridge } from '@amux.ai/llm-bridge'
import { openaiAdapter } from '@amux.ai/adapter-openai'
import { anthropicAdapter } from '@amux.ai/adapter-anthropic'

const bridge = createBridge({
  inbound: openaiAdapter,
  outbound: anthropicAdapter,
  config: {
    apiKey: process.env.ANTHROPIC_API_KEY
  }
})

// Enable streaming
const stream = await bridge.chat({
  model: 'gpt-4',
  messages: [
    { role: 'user', content: 'Tell me a short story' }
  ],
  stream: true
})

// Process stream events
for await (const event of stream) {
  if (event.type === 'content') {
    process.stdout.write(event.content.delta)
  }
}

Common Patterns

Reverse Direction

Switch the adapters to go the other way:

// Anthropic format in → OpenAI API out
const bridge = createBridge({
  inbound: anthropicAdapter,
  outbound: openaiAdapter,
  config: {
    apiKey: process.env.OPENAI_API_KEY
  }
})

const response = await bridge.chat({
  model: 'claude-3-5-sonnet-20241022',
  messages: [{ role: 'user', content: 'Hello!' }],
  max_tokens: 100
})

console.log(response.content[0].text)

Tool Calling

Use tools with any provider:

const response = await bridge.chat({
  model: 'gpt-4',
  messages: [
    { role: 'user', content: 'What is the weather in Beijing?' }
  ],
  tools: [{
    type: 'function',
    function: {
      name: 'get_weather',
      description: 'Get the weather for a location',
      parameters: {
        type: 'object',
        properties: {
          location: { type: 'string' }
        },
        required: ['location']
      }
    }
  }]
})

// Check for tool calls
if (response.choices[0].message.toolCalls) {
  console.log('Tool calls:', response.choices[0].message.toolCalls)
}

Error Handling

Always handle errors:

import { LLMBridgeError } from '@amux.ai/llm-bridge'

try {
  const response = await bridge.chat(request)
} catch (error) {
  if (error instanceof LLMBridgeError) {
    console.error(`${error.type}: ${error.message}`)

    if (error.retryable) {
      // Retry the request
    }
  }
}