Hacker News Reader

Comment by anonzzzies | Hacker News Reader

TIL people still fall for eh I mean use Langchain. Sorry, low value comment; I don’t know how to do that differently; it is such bad garbage since day one and strangely it did not improve. Sorry anyway for the comment, at least it was not LLM generated?

View on HN

To make your comment more high value, could you explain why you think langchain is bad?

It (and most other systems) abstract the wrong concepts when you want to create an agent. They promote what was likely never a great strategy but even parsimoniously what are strategies that were good ideas months or a year back.

For example how langchain or whatever else handles subagents and deep research is laughable even today.

So whats the recommendation? Just use pydantic and code everything up yourself. Maybe strands I dont know.

Which specific strategies do you think are outdated, and what would you recommend instead? This sounds more like a criticism of older versions of LangChain than its current APIs. The post also uses deepagents, a separate package in the same ecosystem. Is there something in the current implementation of either that you’re referring to?

Creating deep research multiagent systems without explicitly handing it a file system is a terrible idea. The only successful way we have found to reliably hand off context in multiagent systems is using a file system. Langchain even today doesnt make that default or even encourage it.

> This sounds more like a criticism of older versions of LangChain than its current APIs

Oh no worries, I'm always happy when library / sdk makers are constantly changing their APIs in-between versions. Why would I not want to spend time updating my code to return to baseline functionality when I could have just built something using the 4-year stable underlying chat completions API instead...?

my biggest code smell is debugging. Trying to step through the code is slow because of how much the debugger has to keep track off and it's a lot of step into / jumps until you get to the piece you actually care about. Then you also see stuff like "if langchain_v2: <branch> elif langchain_v3: <branch> else ...." ... breaking changes are ok! I feel like at this point they're hopelessly spaghettied and need a more opinionated approach to clean up a lot of the mess.

Since others are asking: My current goto is pydantic ai and it's been doing pretty well for my use cases.

I have a hard time keeping up with the space. Is langchain old news? Is there a page that kind of shows what the status quo for tooling is?

+1 would love to know as well. I have generally found the open source space to be lacking in this area and hoping it catches up!

There's like 1000 langchain alternatives and none are good, they're all vibe-coded unstable projects.

I use Apache Burr but it's not as good as LangChain. I just don't want to use software whose website has a pricing page if it's not a SAAS.

Instead of spending half the comment reflecting on your post why not point out what you don’t like about it or some better alternatives?

Totally, I find LangChain is the Vercel of ML

For what reasons?

It's a lot of sugar and high level abstractions on top of existing things, I find using the existing things not that complicated or difficult and I struggle to see the value on using the framework as it doesn't sit well with my way of abstracting the stack.

I wonder if all the cargo cult frontend JS people pivoted to doing this agentic stuff and that's why it's so much of a clusterfuck

Yes, I also thought it's crap the moment I saw they need langchain to develop a harness.

The fact that Stripe are touting a production product that (at face value) benefits their business seems to suggest that maybe crap is subjective and as ever, being overly opinionated in an emerging space might actually be a blocking mindset rather than a positive one.

It might also suggest they went with the first LLM recommendation, like Anthropic choosing React for Claude Code.

Reply on news.ycombinator.com