The Stainless docs platform does some chunking and indexing by default and also gives per endpoint code snippets for different languages. This is more for companies who want to improve the agent experience for devs than for individuals working directly from an open api spec.
No body really wants even more files for AI. It's gotten bad enough with all the vendors requiring their name in the file or dir name. It's out of hand and they need to all agree on one
So asking users to put yet another file in their repo of dubious value is going to be a major hurdle
Fwiw, my agentic framework turns OpenAPI into a toolset automatically for me, so you are def making something I already have
What do the wreken files look like?
The Stainless docs platform does some chunking and indexing by default and also gives per endpoint code snippets for different languages. This is more for companies who want to improve the agent experience for devs than for individuals working directly from an open api spec.
E.g. https://docs.sendblue.com/api/typescript/resources/messages/...
No body really wants even more files for AI. It's gotten bad enough with all the vendors requiring their name in the file or dir name. It's out of hand and they need to all agree on one
So asking users to put yet another file in their repo of dubious value is going to be a major hurdle
Fwiw, my agentic framework turns OpenAPI into a toolset automatically for me, so you are def making something I already have