Ask HN: Anyone using OpenAI's Agent SDK in production?

[sukit]

I'm exploring building a simple agent-based app and came across OpenAI's Agent SDK: https://openai.github.io/openai-agents-js/ . From what I understand, it wraps a lot of functionality — like the agent loop, function calling, and integration with the OpenAI MCP server — which could potentially save me a lot of work compared to using the plain OpenAI SDK.

However, I'm wondering:

Is the Agent SDK too abstracted or hard to debug?

Has anyone actually used it in a real production app yet?

Would I be better off just implementing the logic myself on top of the plain OpenAI SDK for more control and transparency?

Appreciate any insights.

[pancsta]

I agree with the debugging part - we need a new approach to handle these abstractions, and a regular code-stepping or reading logs isn't enough in the case of agents. It's all about managing state, and most ppl here say to avoid it. What I say is that if you go all-in and unify the architecture from the bottom layer, it's actually easier in the long run, but you'll need dedicated devtools for that.

This is precisely why I've created AI-gent Workflows (launched on HN today [0]), which comes with a purpose-built state machine and devtools. Unlike LangGraph, it starts already in the lowest layer and everything is state-based. You can time travel and even modify states of a live agent.

[0] https://news.ycombinator.com/item?id=44386314

[codingwagie]

OpenAI SDK is much simpler to use and understand than langchain etc. I havent deployed really complicated agents, but I have a number of simple use cases that work just fine

[android521]

you're better off just implementing the logic yourself as it is more flexible.