https://github.com/fuergaosi233/claude-code-proxy
Claude Code to OpenAI API Proxy
https://github.com/fuergaosi233/claude-code-proxy
Last synced: 8 days ago
JSON representation
Claude Code to OpenAI API Proxy
- Host: GitHub
- URL: https://github.com/fuergaosi233/claude-code-proxy
- Owner: fuergaosi233
- Created: 2025-06-22T17:31:28.000Z (4 months ago)
- Default Branch: main
- Last Pushed: 2025-06-22T18:08:27.000Z (4 months ago)
- Last Synced: 2025-06-22T18:46:57.073Z (4 months ago)
- Language: Python
- Size: 741 KB
- Stars: 1
- Watchers: 0
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
- awesome-claude-code - claude-code-proxy - code-proxy) | Claude Code 到 OpenAI API 代理 | API 代理服务| (代理与 API 工具)
- awesome-claude-code - **claude-code-proxy**
- awesome-ChatGPT-repositories - claude-code-proxy - Claude Code to OpenAI API Proxy (Openai)
README
# Claude Code Proxy
A proxy server that enables **Claude Code** to work with OpenAI-compatible API providers. Convert Claude API requests to OpenAI API calls, allowing you to use various LLM providers through the Claude Code CLI.
## Features
- **Full Claude API Compatibility**: Complete `/v1/messages` endpoint support
- **Multiple Provider Support**: OpenAI, Azure OpenAI, local models (Ollama), and any OpenAI-compatible API
- **Smart Model Mapping**: Configure BIG and SMALL models via environment variables
- **Function Calling**: Complete tool use support with proper conversion
- **Streaming Responses**: Real-time SSE streaming support
- **Image Support**: Base64 encoded image input
- **Error Handling**: Comprehensive error handling and logging
## Quick Start
### 1. Install Dependencies
```bash
# Using UV (recommended)
uv sync
# Or using pip
pip install -r requirements.txt
```
### 2. Configure
```bash
cp .env.example .env
# Edit .env and add your API configuration
# Note: Environment variables are automatically loaded from .env file
```
### 3. Start Server
```bash
# Direct run
python start_proxy.py
# Or with UV
uv run claude-code-proxy
# Or with docker compose
docker compose up -d
```
### 4. Use with Claude Code
```bash
# If ANTHROPIC_API_KEY is not set in the proxy:
ANTHROPIC_BASE_URL=http://localhost:8082 ANTHROPIC_API_KEY="any-value" claude
# If ANTHROPIC_API_KEY is set in the proxy:
ANTHROPIC_BASE_URL=http://localhost:8082 ANTHROPIC_API_KEY="exact-matching-key" claude
```
## Configuration
The application automatically loads environment variables from a `.env` file in the project root using `python-dotenv`. You can also set environment variables directly in your shell.
### Environment Variables
**Required:**
- `OPENAI_API_KEY` - Your API key for the target provider
**Security:**
- `ANTHROPIC_API_KEY` - Expected Anthropic API key for client validation
- If set, clients must provide this exact API key to access the proxy
- If not set, any API key will be accepted
**Model Configuration:**
- `BIG_MODEL` - Model for Claude opus requests (default: `gpt-4o`)
- `MIDDLE_MODEL` - Model for Claude opus requests (default: `gpt-4o`)
- `SMALL_MODEL` - Model for Claude haiku requests (default: `gpt-4o-mini`)
**API Configuration:**
- `OPENAI_BASE_URL` - API base URL (default: `https://api.openai.com/v1`)
**Server Settings:**
- `HOST` - Server host (default: `0.0.0.0`)
- `PORT` - Server port (default: `8082`)
- `LOG_LEVEL` - Logging level (default: `WARNING`)
**Performance:**
- `MAX_TOKENS_LIMIT` - Token limit (default: `4096`)
- `REQUEST_TIMEOUT` - Request timeout in seconds (default: `90`)
### Model Mapping
The proxy maps Claude model requests to your configured models:
| Claude Request | Mapped To | Environment Variable |
| ------------------------------ | ------------- | ---------------------- |
| Models with "haiku" | `SMALL_MODEL` | Default: `gpt-4o-mini` |
| Models with "sonnet" | `MIDDLE_MODEL`| Default: `BIG_MODEL` |
| Models with "opus" | `BIG_MODEL` | Default: `gpt-4o` |
### Provider Examples
#### OpenAI
```bash
OPENAI_API_KEY="sk-your-openai-key"
OPENAI_BASE_URL="https://api.openai.com/v1"
BIG_MODEL="gpt-4o"
MIDDLE_MODEL="gpt-4o"
SMALL_MODEL="gpt-4o-mini"
```
#### Azure OpenAI
```bash
OPENAI_API_KEY="your-azure-key"
OPENAI_BASE_URL="https://your-resource.openai.azure.com/openai/deployments/your-deployment"
BIG_MODEL="gpt-4"
MIDDLE_MODEL="gpt-4"
SMALL_MODEL="gpt-35-turbo"
```
#### Local Models (Ollama)
```bash
OPENAI_API_KEY="dummy-key" # Required but can be dummy
OPENAI_BASE_URL="http://localhost:11434/v1"
BIG_MODEL="llama3.1:70b"
MIDDLE_MODEL="llama3.1:70b"
SMALL_MODEL="llama3.1:8b"
```
#### Other Providers
Any OpenAI-compatible API can be used by setting the appropriate `OPENAI_BASE_URL`.
## Usage Examples
### Basic Chat
```python
import httpx
response = httpx.post(
"http://localhost:8082/v1/messages",
json={
"model": "claude-3-5-sonnet-20241022", # Maps to MIDDLE_MODEL
"max_tokens": 100,
"messages": [
{"role": "user", "content": "Hello!"}
]
}
)
```
## Integration with Claude Code
This proxy is designed to work seamlessly with Claude Code CLI:
```bash
# Start the proxy
python start_proxy.py
# Use Claude Code with the proxy
ANTHROPIC_BASE_URL=http://localhost:8082 claude
# Or set permanently
export ANTHROPIC_BASE_URL=http://localhost:8082
claude
```
## Testing
Test the proxy functionality:
```bash
# Run comprehensive tests
python src/test_claude_to_openai.py
```
## Development
### Using UV
```bash
# Install dependencies
uv sync
# Run server
uv run claude-code-proxy
# Format code
uv run black src/
uv run isort src/
# Type checking
uv run mypy src/
```
### Project Structure
```
claude-code-proxy/
├── src/
│ ├── main.py # Main server
│ ├── test_claude_to_openai.py # Tests
│ └── [other modules...]
├── start_proxy.py # Startup script
├── .env.example # Config template
└── README.md # This file
```
## Performance
- **Async/await** for high concurrency
- **Connection pooling** for efficiency
- **Streaming support** for real-time responses
- **Configurable timeouts** and retries
- **Smart error handling** with detailed logging
## License
MIT License