I might be missing something here, but from the demo it looks like the user has to enter their API keys for their LLM provider. Is this is the intended use case for this tool? If so, how is this better than making a regular API request?
Yup, it's another alternative to using the regular API. The issue was that a lot of the providers required you to build their libs and caused a lot of friction running on standalone vanilla JS. This aims to compile all those solutions and package it.
This is great! I made a thing that works with OpenAI all within browser. Thought if making it work with Anthropic etc was putting me off. Will just use this lib.