llmrouter

A programmable Mixture-of-Models router for heterogeneous LLM inference

Fast LLM swapping with sleep/wake support, compatible with vllm, llama.cpp, etc. llama-swap fork.

High-performance Java LLM router & proxy with intelligent multi-model routing, failover, quota management, and OpenAI-compatible API endpoints.

Efficient Agent Router (EAR) is a Python-first orchestration service that selects and executes the best LLM for a request based on quality, cost, latency, context window, and safety constraints.