HN 提问：今天最好的 AI 编程工具是什么？
2 分•作者: FrenchDevRemote•2 个月前
我目前的流程大致是这样的：撰写详细的需求，通过 SSH 连接到远程实例，让一个代理（agent）制定计划并允许其自由地在那里构建，只在完成或遇到困难时才通知我。我也可以在 IDE 中手动编写代码，但仅限于当问题过于复杂，LLM 无法处理时。
我使用 Cursor 工作已经有几年了，但我非常不喜欢将所有数据都交给 Musk。而且我认为我想减少手动编写代码的时间。
我尝试过 Antigravity，但它简直是垃圾。
我听说过 Opencode + open models/ollama cloud 的一些好消息，但 opencode 在通过 SSH 运行时似乎有些小 bug。
我非常不愿意将钱花在行业内的两大巨头身上，我不想助长他们赚更多的钱，但如果毫无疑问他们是最好的，我可能会被说服，但我对此并不完全确定。
我的预算也有限，除非有百分之百的把握物有所值，否则我不想支付 200 美元的订阅费。
我的主要关注点是构建围绕 AI/代理、移动应用以及爬虫/自动化（scraping/automation）的 MVP（最小可行产品）。
您认为目前有没有一个明显更优的解决方案值得推荐？在功能、性价比、使用限制等方面。
查看原文
My current workflow would be something like: write detailed requirements, ssh into a remote instance, ask an agent to write a plan and giving it free rein to build it there, only pinging me back when it's ready or when it's stuck. I could write code manually in an IDE too but only when the problem is too complex for an LLM.<p>I've used Cursor for work for a few years, but I'm really not a fan of giving all of my data to Musk. Also I think I want to spend less time writing code by hand.<p>I tried Antigravity but it's utter garbage.<p>I heard some good things about Opencode+open models/ollama cloud, but opencode seems slightly buggy when running it over ssh.<p>I'm really reluctant to give my money to the 2 leaders in the field, I don't think I want to contribute to them making more money, but I could be convinced if there was no doubt they're the best, which I'm not totally sure of.<p>I'm also on a limited budget and don't want to get a 200$ subscription unless there is zero doubt it's worth it.<p>My main focus is building MVPs around AI/agents, mobile apps, and scraping/automation.<p>In your opinion is there a clearly superior solution today you'd recommend? In terms of capabilities, value for money, usage limits.