This makes so much more sense than langchain! I read all the docs for langchain, but the abstractions seemed broken and it wasn't obvious what was happening at the LLM level. In contrast, I grokked the entire llm_agents API within 5 minutes.
To be fair to langchain, though: I like it a lot and it offers a lot more than my repo, but yeah definitely not the best place to understand how it all plays together.