ClewdR Xerxes-2
winget install --id=Xerxes-2.ClewdR -e
High-Performance LLM Proxy Specifically built for Claude (Claude.ai) and Gemini (Google AI Studio, Google Vertex AI) Core Advantages Full-Featured Frontend - Integrated React frontend providing a complete functional experience Efficient Architecture - Occupies one-tenth the resources compared to script language implementations, with ten times the performance, easily handling thousands of requests per second - Event-driven design, decoupled logic, supports hot reloading and multiple configuration methods - High-performance response caching supported by Moka technology - Multi-threaded asynchronous processing based on Tokio and Axum - Fingerprint-level Chrome simulation Rquest HTTP client Intelligent Cookie Management - Automatic classification and management of account status - Fine-grained polling mechanism to maximize resource utilization Full Platform Compatibility - Rust static compilation, single binary deployment, no environment dependencies needed - Native support for macOS/Android and other platforms - Extremely low memory usage (only single-digit MB) - No need for virtual machines or complex dependencies Enhanced Features - Built-in proxy server support (no TUN required) - Concurrent cache request handling - Gemini additional support: - Google AI Studio and Google Vertex AI - OpenAI compatible mode / Gemini format - Painless HTTP Keep-Alive support - Claude additional support: - OpenAI compatible mode / Claude format - Extend Thinking - Stop sequences implemented on the proxy side - Image attachment uploads - Web search - Claude Max
README
ClewdR
High-Performance LLM Proxy
Specifically built for Claude (Claude.ai) and Gemini (Google AI Studio, Google Vertex AI)
Core Advantages
Full-Featured Frontend
- Integrated React frontend providing a complete functional experience
Efficient Architecture
- Occupies one-tenth the resources compared to script language implementations, with ten times the performance, easily handling thousands of requests per second
- Event-driven design, decoupled logic, supports hot reloading and multiple configuration methods
- High-performance response caching supported by Moka technology
- Multi-threaded asynchronous processing based on Tokio and Axum
- Fingerprint-level Chrome simulation Rquest HTTP client
Intelligent Cookie Management
- Automatic classification and management of account status
- Fine-grained polling mechanism to maximize resource utilization
Full Platform Compatibility
- Rust static compilation, single binary deployment, no environment dependencies needed
- Native support for macOS/Android and other platforms
- Extremely low memory usage (only single-digit MB)
- No need for virtual machines or complex dependencies
Enhanced Features
- Built-in proxy server support (no TUN required)
- Concurrent cache request handling
- Gemini additional support:
- Google AI Studio and Google Vertex AI
- OpenAI compatible mode / Gemini format
- Painless HTTP Keep-Alive support
- Claude additional support:
- OpenAI compatible mode / Claude format
- Extend Thinking
- Stop sequences implemented on the proxy side
- Image attachment uploads
- Web search
- Claude Max
Quick Start
- Download the program package for your platform (Latest Version)
- The password will be automatically generated on the first run. Access the default frontend address , and log in using the Web Admin Password displayed in the console.
- If you need to change the password, you can set a new one in the frontend interface.
- If you forget the password, you can delete the
clewdr.toml
file to regenerate it. - Note: If deploying with Docker, the password will be generated and displayed in the logs when the container starts.
- Configure the proxy address and other parameters in the frontend interface, add Cookies and Keys.
- Third-party application configuration:
- ClewdR will print the access addresses for each API in the console when it starts.
- Choose the API format you want (Claude or Gemini or OpenAI compatible).
- Set the corresponding proxy address in applications like SillyTavern, and fill in the API Password displayed in the console as the proxy password.
- Enjoy the high-performance LLM proxy service!
Community Resources
Github Aggregated Wiki: