Ask HN: Anyone using Claude Agent SDK in production?

[galsapir]

We're evaluating agent frameworks for a health AI product and leaning toward Anthropic's Claude Agent SDK. Did a quick POC and liked the simplicity: clean @tool decorator, native MCP support, flat mental model. But I'm finding fewer production case studies compared to LangGraph or similar. Curious about:

Multi-turn conversation handling, does it manage state well or do you thread history manually? Long-running tasks (minutes/hours), any gotchas with timeouts or checkpointing? The latency overhead people mention (~12s per query per one github issue). is this still an issue or has it improved? General production rough edges we should know about?

For context: most of our context is pre-computed, occasional JIT tool calls. Comparing against Pydantic AI and LangGraph but trying to avoid over-engineering. Appreciate any war stories.

[dragonmage65535]

Yeah, I'm also exploring the same, we use langgraph in production, but seeing how much more powerful claude code is with little guidance, I just have more trust on it, but the library right now is a library with a subprocess (claude code) and the tools also need to be served via MCP, not exactly light weight, and also it would be good to have more visibility. Did you find any good resources on this?