[quan]

I created api2ai (https://github.com/mquan/api2ai) to solve this. You provide an OpenAPI spec and auth data to spin up an agent for your API. It’s still low level and requires dev work. But I’m working on building tools to bring it to end users

[J_Shelby_J]

That’s neat!

I took a different approach to openapi specs https://github.com/ShelbyJenkins/LLM-OpenAPI-minifier

[yu3zhou4]

This looks really cool, thx. How good it performs in practice? What are current bottlenecks, if any?