ChimeraGate

OpenAI API Compatible Gateway for Claude Agent SDK

Warning

⚠️ Disclaimer

This project is intended for personal use only. It is designed to help individual developers integrate Claude models into their local development workflow via an OpenAI-compatible interface.

Do not use this project to provide services to third parties or for commercial purposes
Do not redistribute or resell access to Claude models through this gateway
Users are responsible for complying with Anthropic's Terms of Service and all applicable laws and regulations

The authors assume no liability for any misuse of this software.

ChimeraGate is a lightweight local HTTP server that provides complete OpenAI API compatibility, but routes all requests to the Claude Agent SDK. It can replace the OpenAI API directly—just change the baseURL and you can use Claude subscription models through normal API calls.

Features

Full OpenAI API Compatibility - Compatible with any client that supports OpenAI's Chat Completions API
Multi-Model Support - Access Claude Sonnet, Opus, and Haiku models through familiar model identifiers
Streaming & Non-Streaming - Support for both response modes with Server-Sent Events (SSE)
Bearer Token Authentication - Secure API access with configurable API keys
Automatic Format Conversion - Bidirectional conversion between OpenAI and Claude message formats
Debug Logging - Comprehensive logging for development and troubleshooting
Lightweight & Fast - Built on Hono framework (~15KB) for minimal overhead

Quick Start

Prerequisites

Node.js 18+
npm or yarn
Claude subscription (Pro or Max, configured for Claude Agent SDK)

Installation

# Clone the repository
git clone https://github.com/yourusername/ChimeraGate.git
cd ChimeraGate

# Install dependencies
npm install

# Configure environment
cp .env.example .env
# Edit .env with your settings

# Build the project
npm run build

# Start the server
npm start

Development

npm run dev

The server will start with hot reload enabled:

╔═══════════════════════════════════════════════════════════╗
║                      CHIMERA GATE                         ║
║        OpenAI API Compatible Gateway for Claude           ║
╠═══════════════════════════════════════════════════════════╣
║  Server: http://localhost:3721                            ║
║  Debug:  ON                                               ║
╠═══════════════════════════════════════════════════════════╣
║  Endpoints:                                               ║
║    GET  /v1/models           - List available models      ║
║    POST /v1/chat/completions - Chat completion API        ║
║    POST /v1/completions      - Legacy completion API      ║
╚═══════════════════════════════════════════════════════════╝

Configuration

Create a .env file in the project root:

# Server port (default: 3000)
CHIMERA_PORT=3721

# API authentication key (default: chimera-key-123)
CHIMERA_API_KEY=your-secure-api-key

# Default model when not specified in request (default: claude-sonnet-4-5)
CHIMERA_DEFAULT_MODEL=claude-sonnet-4-5

# Enable debug logging (default: false)
CHIMERA_DEBUG=true

API Reference

Endpoints

Method	Endpoint	Description
`GET`	`/health`	Health check
`GET`	`/`	Service info
`GET`	`/v1/models`	List available models
`POST`	`/v1/chat/completions`	Chat completion (primary)
`POST`	`/v1/completions`	Legacy completion

Supported Models

Model ID	Claude Model
`claude-sonnet-4-5`	Claude Sonnet 4.5 (default)
`claude-opus-4-5`	Claude Opus 4.5
`claude-haiku-4-5`	Claude Haiku 4.5

Chat Completion Request

POST /v1/chat/completions
Authorization: Bearer <API_KEY>
Content-Type: application/json

Request Body:

{
  "model": "claude-opus-4-5",
  "messages": [
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "What is the capital of France?"}
  ],
  "temperature": 0.7,
  "max_tokens": 2000,
  "stream": false
}

Supported Parameters:

Parameter	Type	Description
`model`	string	Model ID (optional, uses default if omitted)
`messages`	array	Array of message objects (required)
`temperature`	number	Sampling temperature 0.0-2.0 (optional)
`max_tokens`	number	Maximum response length (optional)
`stream`	boolean	Enable SSE streaming (optional)

Response:

{
  "id": "chatcmpl-abc123...",
  "object": "chat.completion",
  "created": 1702310400,
  "model": "claude-opus-4-5",
  "choices": [{
    "index": 0,
    "message": {
      "role": "assistant",
      "content": "The capital of France is Paris."
    },
    "finish_reason": "stop"
  }],
  "usage": {
    "prompt_tokens": 24,
    "completion_tokens": 10,
    "total_tokens": 34
  }
}

Usage Examples

cURL

# List models
curl -X GET http://localhost:3721/v1/models \
  -H "Authorization: Bearer chimera-key-123"

# Chat completion
curl -X POST http://localhost:3721/v1/chat/completions \
  -H "Authorization: Bearer chimera-key-123" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-opus-4-5",
    "messages": [{"role": "user", "content": "Hello!"}],
    "max_tokens": 100
  }'

# Streaming
curl -X POST http://localhost:3721/v1/chat/completions \
  -H "Authorization: Bearer chimera-key-123" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-sonnet-4-5",
    "messages": [{"role": "user", "content": "Tell me a story"}],
    "stream": true
  }'

Python (OpenAI SDK)

from openai import OpenAI

client = OpenAI(
    base_url="http://localhost:3721/v1",
    api_key="chimera-key-123"
)

# Non-streaming
response = client.chat.completions.create(
    model="claude-opus-4-5",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "What is 2+2?"}
    ],
    max_tokens=500
)
print(response.choices[0].message.content)

# Streaming
stream = client.chat.completions.create(
    model="claude-sonnet-4-5",
    messages=[{"role": "user", "content": "Write a poem"}],
    stream=True
)
for chunk in stream:
    if chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="")

Node.js (OpenAI SDK)

import OpenAI from 'openai';

const client = new OpenAI({
  baseURL: 'http://localhost:3721/v1',
  apiKey: 'chimera-key-123',
});

const response = await client.chat.completions.create({
  model: 'claude-opus-4-5',
  messages: [{ role: 'user', content: 'Hello!' }],
});

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

Architecture

┌─────────────────────────────────────────────────────────────┐
│                    Client Application                       │
│              (Any OpenAI-compatible client)                 │
└─────────────────────────┬───────────────────────────────────┘
                          │ HTTP Request (OpenAI format)
                          ▼
┌─────────────────────────────────────────────────────────────┐
│                      ChimeraGate                            │
│  ┌───────────────────────────────────────────────────────┐  │
│  │                   Hono Server                         │  │
│  ├───────────────────────────────────────────────────────┤  │
│  │  ┌─────────────┐  ┌─────────────┐  ┌──────────────┐   │  │
│  │  │    Auth     │  │   Routes    │  │  Converters  │   │  │
│  │  │ Middleware  │──│   /v1/*     │──│ OpenAI↔Claude│   │  │
│  │  └─────────────┘  └─────────────┘  └──────────────┘   │  │
│  │                          │                            │  │
│  │                          ▼                            │  │
│  │              ┌─────────────────────┐                  │  │
│  │              │  Claude Agent SDK   │                  │  │
│  │              │      Service        │                  │  │
│  │              └─────────────────────┘                  │  │
│  └───────────────────────────────────────────────────────┘  │
└─────────────────────────┬───────────────────────────────────┘
                          │
                          ▼
┌─────────────────────────────────────────────────────────────┐
│                    Claude Agent SDK                         │
│                   (Anthropic API)                           │
└─────────────────────────────────────────────────────────────┘

Project Structure

ChimeraGate/
├── src/
│   ├── index.ts              # Application entry point
│   ├── config.ts             # Configuration & model mappings
│   ├── types/
│   │   └── openai.ts         # OpenAI-compatible type definitions
│   ├── middleware/
│   │   └── auth.ts           # Bearer token authentication
│   ├── routes/
│   │   ├── models.ts         # GET /v1/models
│   │   ├── chat.ts           # POST /v1/chat/completions
│   │   └── completions.ts    # POST /v1/completions
│   ├── services/
│   │   └── claudeAgent.ts    # Claude Agent SDK wrapper
│   └── converters/
│       └── index.ts          # Format conversion utilities
├── package.json
├── tsconfig.json
├── .env
└── .gitignore

Error Handling

All errors follow OpenAI's error response format:

{
  "error": {
    "message": "Invalid API key",
    "type": "authentication_error",
    "param": null,
    "code": "invalid_api_key"
  }
}

Error Type	Description
`authentication_error`	Invalid or missing API key
`invalid_request_error`	Malformed request, missing fields, invalid model
`api_error`	Internal server errors

Tech Stack

Runtime: Node.js (ES modules)
Framework: Hono - Lightweight, fast web framework
Language: TypeScript 5.7
Claude SDK: @anthropic-ai/claude-code

Roadmap

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

Fork the repository
Create your feature branch (git checkout -b feature/amazing-feature)
Commit your changes (git commit -m 'Add some amazing feature')
Push to the branch (git push origin feature/amazing-feature)
Open a Pull Request

License

This project's source code is licensed under the MIT License - see the LICENSE file for details.

Note: This project depends on @anthropic-ai/claude-code, which is proprietary software owned by Anthropic PBC. Use of Claude Code is subject to Anthropic's Commercial Terms of Service.

Acknowledgments

Anthropic for Claude and the Agent SDK
Hono for the excellent web framework
The OpenAI community for the API specification

ChimeraGate - Bridging the gap between OpenAI compatibility and Claude's capabilities.

Name		Name	Last commit message	Last commit date
Latest commit History 16 Commits
ai-doc		ai-doc
src		src
.env.example		.env.example
.gitignore		.gitignore
.mise.toml		.mise.toml
LICENSE		LICENSE
README.md		README.md
README_CN.md		README_CN.md
package-lock.json		package-lock.json
package.json		package.json
tsconfig.json		tsconfig.json

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Repository files navigation

ChimeraGate

Features

Quick Start

Prerequisites

Installation

Development

Configuration

API Reference

Endpoints

Supported Models

Chat Completion Request

Usage Examples

cURL

Python (OpenAI SDK)

Node.js (OpenAI SDK)

Architecture

Project Structure

Error Handling

Tech Stack

Roadmap

Contributing

License

Acknowledgments

About

Uh oh!

Releases

Packages

Uh oh!

Contributors 2

Uh oh!

Languages

License

onevcat/ChimeraGate

Folders and files

Latest commit

History

Repository files navigation

ChimeraGate

Features

Quick Start

Prerequisites

Installation

Development

Configuration

API Reference

Endpoints

Supported Models

Chat Completion Request

Usage Examples

cURL

Python (OpenAI SDK)

Node.js (OpenAI SDK)

Architecture

Project Structure

Error Handling

Tech Stack

Roadmap

Contributing

License

Acknowledgments

About

Resources

License

Uh oh!

Stars

Watchers

Forks

Releases

Packages 0

Uh oh!

Contributors 2

Uh oh!

Languages

Packages