Ask HN：使用 Vercel 的 AI SDK 有什么具体的缺点吗？
1 分•作者: dennisy•8 个月前
我用 AI / Agent 框架启动过多个项目，但最终都感到失望。目前我正在从头开始实现我的项目，这让我更满意，因为我知道所有状态都存在于哪里，而且不必花费数小时试图从 agent 循环中提取我需要的一些数据。
然而，今天我研究了在这个领域中我认为“优秀”的开源代码，试图找到一些有趣的抽象，并注意到几乎所有项目[0][1]都在使用 Vercel 的 AI SDK 来连接到 LLM。目前，我拥有自己的内部接口，并且正在实现几个提供商（ollama、openai、anthropic）。
所以我想看看 HN 的观点，我是不是傻了——AI SDK 真的一个好的抽象吗？我应该利用它来节省时间吗？
- [0] https://github.com/sst/opencode
- [1] https://github.com/VoltAgent/voltagent
查看原文
I have started multiple projects using AI / Agent frameworks and have always been disappointed in the end. My current project I am implementing everything from scratch and I am much happier, I know where all the state exists and I do not have to spend hours trying to find how to extract some data from the agent loop which I need.<p>However today I was researching what I would deem to be "good" open source code in this area to try and find some interesting abstractions and noticed that nearly all the projects[0][1] are using Vercel's AI SDK for connecting to LLMs. Right now I have my own internal interface and am implementing a few providers (ollama, openai, anthropic).<p>So I wanted to see what the view of HN is, am I being stupid - is the AI SKD truly a good bit of abstraction and I should leverage it to save time?<p>- [0] https://github.com/sst/opencode
- [1] https://github.com/VoltAgent/voltagent