TensorZero, LLMOps gateway, was archived yesterday and I forked it to continue development and keep it open source. I also applied for 6 months of codex credits which I will dedicate to the project.

https://github.com/agentify-sh/gateway

I've built similar a couple of different ways. I'm currently focusing on running outputs through a local model to to enable tokenmaxing before sending onto a model I am paying with credits, not OAuth.