Open-Source Project Turns LLM Usage Data Into Smarter Model Routing
A developer team called Experiential Labs has released an open-source tool that functions like OpenRouter—the popular service that lets apps call different LLMs through one API—but with a twist: it's designed to learn from how it's actually used.
Instead of relying on static rules or manual configuration to decide which model handles a given request, the system aims to build a feedback loop, using real usage signals to refine routing choices and improve outcomes over time. The project launched on Show HN and quickly drew attention, racking up 88 points and a lively discussion thread about routing strategies and self-hosted LLM infrastructure.
Because it's open source, teams can self-host the router rather than depending on a third-party service, giving them more control over cost, latency, and data privacy while still getting multi-model flexibility.