Claude-OpenAI Bridge

OpenAI-compatible API interface for Anthropic's Claude models

A proxy-adapter system that provides an OpenAI-compatible API for Anthropic's Claude models. Use Claude intelligence within existing OpenAI-based tooling and infrastructure — without rewriting your code.

How It Works · Quick Start · API Reference · Configuration

---

Architecture

graph LR
    subgraph Client["Client Applications"]
        A[OpenAI SDK]
        B[ChatGPT Plugins]
        C[Custom Apps]
    end

    subgraph Bridge["Claude-OpenAI Bridge"]
        D[Request Interceptor]
        E[Payload Transformer]
        F[Response Mapper]
    end

    subgraph Anthropic["Anthropic API"]
        G[Claude Models]
    end

    A --> D
    B --> D
    C --> D
    D --> E
    E -->|Claude API Format| G
    G -->|Claude Response| F
    F -->|OpenAI Format| A
    F --> B
    F --> C

Loading

---

How It Works

The bridge operates as a transparent translation layer between OpenAI-compatible clients and Anthropic's Claude API.

sequenceDiagram
    participant Client as Client (OpenAI SDK)
    participant Proxy as Claude-OpenAI Bridge
    participant Claude as Anthropic Claude API

    Client->>Proxy: POST /v1/chat/completions
    Note over Proxy: Intercept OpenAI request
    Proxy->>Proxy: Transform payload to Claude format
    Proxy->>Claude: POST /v1/messages
    Claude-->>Proxy: Claude response
    Proxy->>Proxy: Map response to OpenAI format
    Proxy-->>Client: OpenAI-compatible response

Loading

Translation Pipeline

Step	Description
1. Intercept	Receives standard OpenAI API requests (/v1/chat/completions, /v1/models, etc.)
2. Transform	Converts OpenAI request schema to Anthropic Claude message format
3. Forward	Sends transformed request to Claude API
4. Map	Converts Claude response back to OpenAI-compatible response format

---

Quick Start

Prerequisites

• Python 3.10+ or Node.js 18+
• An Anthropic API key

Installation

# Clone the repository
git clone https://github.com/ATC-O48/Claude-OpenAI-Code..git
cd Claude-OpenAI-Code.

# For Node.js/TypeScript
npm install

# For Python
pip install -r requirements.txt

Running the Bridge

# Set your Anthropic API key
export ANTHROPIC_API_KEY="your-api-key-here"

# Start the proxy server
./upload-all.sh

---

API Reference

Endpoints

Endpoint	Method	Description
/v1/chat/completions	POST	Chat completions (maps to Claude Messages API)
/v1/models	GET	List available models
/v1/health	GET	Service health check

Chat Completions

POST /v1/chat/completions

Accepts standard OpenAI chat completion requests and translates them to Claude API calls.

---

Examples

cURL

curl http://localhost:3000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $ANTHROPIC_API_KEY" \
  -d '{
    "model": "claude-sonnet-4-20250514",
    "messages": [
      {"role": "user", "content": "Hello, how are you?"}
    ],
    "max_tokens": 1024
  }'

Node.js (OpenAI SDK)

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.ANTHROPIC_API_KEY,
  baseURL: "http://localhost:3000/v1",
});

const response = await client.chat.completions.create({
  model: "claude-sonnet-4-20250514",
  messages: [{ role: "user", content: "Explain quantum computing" }],
  max_tokens: 1024,
});

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

Python (OpenAI SDK)

from openai import OpenAI

client = OpenAI(
    api_key="your-anthropic-api-key",
    base_url="http://localhost:3000/v1",
)

response = client.chat.completions.create(
    model="claude-sonnet-4-20250514",
    messages=[{"role": "user", "content": "Write a haiku about coding"}],
    max_tokens=1024,
)

print(response.choices[0].message.content)

---

Configuration

Environment Variables

Variable	Required	Description
ANTHROPIC_API_KEY	Yes	Your Anthropic API key
PORT	No	Server port (default: 3000)
LOG_LEVEL	No	Logging level: debug, info, warn, error

---

Supported Models

Claude Model	OpenAI Mapping	Description
claude-opus-4-20250514	claude-opus-4-20250514	Most capable model for complex tasks
claude-sonnet-4-20250514	claude-sonnet-4-20250514	Balanced performance and speed
claude-haiku-3-5-20241022	claude-haiku-3-5-20241022	Fastest model for simple tasks

---

Key Features

Claude-OpenAI Bridge	Transparent translation layer between OpenAI and Anthropic API protocols
Agent AI	Autonomous agent logic for planning and tool usage via LLMs
Proxy-Adapter Pattern	Clean architecture for intercepting and transforming API payloads
Multi-runtime Support	Native implementations for both Python and Node.js environments
Apple Integration	Support for Xcode, Swift Package Manager, CocoaPods, and Fastlane

---

Roadmap

• Streaming response support
• Function calling / tool use translation
• Rate limiting and request queuing
• Response caching layer
• Docker deployment support
• OpenAPI specification
• SDK wrappers for common languages
• Metrics and monitoring dashboard

---

Contributing

Contributions are welcome! Please read our Contributing Guide for details on development setup, code style, and the PR process.

# Fork and clone
git clone https://github.com/<your-username>/Claude-OpenAI-Code..git
cd Claude-OpenAI-Code.

# Create a feature branch
git checkout -b feature/your-feature-name

# Make changes, test, commit and push
git commit -m "feat: your feature description"
git push origin feature/your-feature-name

Then open a pull request against main.

---

License

This project is licensed under the Boost Software License 1.0.

---

Contact

• Organization: ATC-O48
• Project Link: github.com/ATC-O48/Claude-OpenAI-Code.

---