llama-swap by mostlygeek

A programmable Mixture-of-Models router for heterogeneous LLM inference. Maintained by vllm-project on GitHub, where it has earned 5,116 stars from the community.

Unified management and routing for llama.cpp, MLX and vLLM models with web dashboard. Maintained by lordmathis on GitHub, where it has earned 139 stars from the community.

Enterprise-grade API gateway that helps you monitor and impose cost or rate limits per API key. Get fine-grained access control and monitoring per user, application, or environment. Supports OpenAI, Azure OpenAI, Anthropic, vLLM, and open-source LLMs. Maintained by bricks-cloud on GitHub, where it has earned 1,221 stars from the community.