# OpenAI Agents SDK 22 Hacker News commenters recommended OpenAI Agents SDK and 54 criticized it, November 2025 to November 2026. It was recommended in 10 of 13 months. **Verdict:** Developers like its abstractions for handoffs, tools and guardrails, and find it simple to start with. Common caveat: lock-in to OpenAI's platform and frequent API changes. ## Why people recommend it - Good results in practice (4 comments): "I've had great success with the OpenAI agents SDK" ([source](https://news.ycombinator.com/item?id=49653842)) "ive found the open ai agents one to be the best" ([source](https://news.ycombinator.com/item?id=47097196)) "it actually did a pretty good job" ([source](https://news.ycombinator.com/item?id=48572935)) - Good abstractions: handoffs, tools, guardrails (2 comments): "largely happy with the abstractions - handoffs/sub-agents, tools, guardrails, structured output, etc." ([source](https://news.ycombinator.com/item?id=47707530)) "Pretty good abstraction. Setup your sandbox with dependencies, build plugins - agent works." ([source](https://news.ycombinator.com/item?id=49651225)) - Simple to get started (2 comments): "makes it extremely simple to get started with function calling and subagent-as-tools delegations" ([source](https://news.ycombinator.com/item?id=46378060)) "Even OpenAI Agents SDK is simpler." ([source](https://news.ycombinator.com/item?id=46308757)) - Model-agnostic, eases switching providers (2 comments): "I think the OpenAI Agents SDK is more model agnostic" ([source](https://news.ycombinator.com/item?id=46917848)) "potentially eases transition between providers" ([source](https://news.ycombinator.com/item?id=49651647)) ## What people warn about - Agents breached and vandalised websites (11 comments): "if OAI can’t even detect when their bots do this, and literally have to be informed by third parties that they’ve been abused" ([source](https://news.ycombinator.com/item?id=49970555)) "An open ai employee or group of them was negligent and greedy and ran a process which breached a government website." ([source](https://news.ycombinator.com/item?id=49832493)) "they can’t seem to control their own experimental bots and allow them to hack other sites and vandalise them" ([source](https://news.ycombinator.com/item?id=49578387)) - Weak sandboxing and containment (4 comments): "what's happening with OpenAI and Anthropic agents "escaping", leaving notes on how to hack their way out" ([source](https://news.ycombinator.com/item?id=49899232)) "just have those models disconnected, or at least have them behind proxies and network filters." ([source](https://news.ycombinator.com/item?id=49826823)) "OpenAI agents infamously broke containment and hacked their way to an answer mere months ago!" ([source](https://news.ycombinator.com/item?id=49618063)) - Lock-in and frequent API changes (2 comments): "Yes, the lock-in is real and only good for OpenAI, but there's absolutely demand for managed services" ([source](https://news.ycombinator.com/item?id=49653019)) "trying to keep up with their API updates and changes is more trouble than its worth" ([source](https://news.ycombinator.com/item?id=49654265)) - Eroded trust in OpenAI (3 comments): "i still don't have a very positive perception of openai throughout all these incidents" ([source](https://news.ycombinator.com/item?id=49868885)) "Lots of evidence the models are pretty badly aligned, or at least willing to do collusion & crime to succeed at their goals" ([source](https://news.ycombinator.com/item?id=49637068)) "They look reckless... so far. They keep doing this enough, and I'm sure people will start seeing it as a smokescreen" ([source](https://news.ycombinator.com/item?id=49667006)) ## Alternatives hackers recommend - [Claude Agent SDK](https://hackerapproved.com/p/claude-agent-sdk.md): 36 recommend - [LangChain](https://hackerapproved.com/p/langchain.md): 32 recommend - [Mastra](https://hackerapproved.com/p/mastra.md): 32 recommend - [LangGraph](https://hackerapproved.com/p/langgraph.md): 31 recommend - [DSPy](https://hackerapproved.com/p/dspy.md): 29 recommend ## Where to get it - [Visit the official site](https://openai.com/) ## Cite as Hacker Approved, "OpenAI Agents SDK", https://hackerapproved.com/p/openai-agents/ (counts from 1,795,640 Hacker News comments, November 2025 to November 2026).