A personal LLM gateway with fault-tolerant capabilities for calls to LLM models from any provider with OpenAI-compatible APIs. Advanced features like retry, model sequencing, and body parameter injection are also available. Especially useful to work with AI coders like Cline and RooCode and providers like OpenRouter.
Configurable, interactive proxy server for all LLM hackers. Features API key rotation, protocol conversion, and piping API traffic through locally installed CLI apps like gemini-cli. Route any app to any remote LLM model or backend, override hardcoded models
Add a description, image, and links to the llm-proxy topic page so that developers can more easily learn about it.
To associate your repository with the llm-proxy topic, visit your repo's landing page and select "manage topics."