GitHub - Gysho/LLMrPro: LLM Router PRO: Your machines run the models. The cloud only fills the gaps. Call every model through one OpenAI format. Self-hosted, and yours to own

LLMrPro is a self-hosted LLM router exposing one OpenAI-compatible API that routes requests to user-owned machines running local inference engines including LM Studio, Ollama, vLLM, llama.cpp, and MLX. When local workers cannot serve a request, it falls back to configured cloud providers such as OpenAI, Anthropic, Google, or Azure OpenAI. The system is single-tenant, with encrypted provider keys and per-source rate limiting. A balancer and desktop agent comprise the two installable components.