GitHub - sturnus-dev/sturnus: Latency-based load balancing across OpenAI, Azure OpenAI, Vertex AI and Anthropic. An OpenAI-compatible sidecar in a single static binary.
sturnus is a lightweight, stateless sidecar proxy that performs automatic latency-based routing between multiple LLM providers (OpenAI, Azure OpenAI, Vertex AI, Anthropic) while exposing a single OpenAI-compatible API endpoint.