[CuriouslyC]

LiteLLM is kind of a mess TBH, I guess it's ok if you just want a docker container to proxy to for personal projects, but actually using it in production isn't great.

[tom_usher]

I definitely appreciate all the work that has gone in to LiteLLM but it doesn't take much browsing through the 7000+ line `utils.py` to see where using it could become problematic (https://github.com/BerriAI/litellm/blob/main/litellm/utils.p...)

[swyx]

can you double click a little bit? many files in professional repos are 1000s of lines. LoC in it self is not a code smell.

[otabdeveloper4]

LiteLLM is the worst code I have ever read in my life. Quite an accomplishment, lol.

[swyx]

ok still not helpful in giving substantial criticism

[otabdeveloper4]

Sorry if this sounds harsh, but I'm not really interested in spending time to code review the worst code I've ever seen in 30 years of programming.

Is LiteLLM's code written by an LLM?

[honorable_coder]

and you say you aren't "vested" in liteLLM?

[swyx]

yes, green text hn account, i am not. i just want help in properly identifying flaws in litellm. clearly nobody here is offering actual analysis.

[dlojudice]

> but actually using it in production isn't great.

I only use it in development. Could you elaborate on why you don't recommend using it in production?

[honorable_coder]

the people behind envoy proxy built: https://github.com/katanemo/archgw - has the learnings of Envoy but natively designed to process/route prompts to agents and LLMs. Would be curious about your thoughts