# SmarterRouter

A local, intelligent LLM gateway that profiles installed Ollama and llama.cpp models on your own hardware and automatically routes each request to whichever model performs best for it, as a drop-in OpenAI-compatible endpoint.

SmarterRouter sits between an application and its LLM providers, profiling each configured model's performance on the current hardware and aggregating benchmark data so it can pick the best available model for each incoming prompt without manual configuration, in contrast to tools that need a static per-provider routing setup.

It supports Ollama, llama.cpp and OpenAI backends behind one OpenAI-compatible interface, includes monitoring, metrics and error handling, and learns model profiles over time rather than relying on a fixed configuration. Setup runs through Docker Compose, and an interactive CLI wizard can configure the environment file, validate provider connections, and generate hardware-appropriate defaults.

It is written in Python and MIT licensed.

Website: https://github.com/peva3/SmarterRouter