Ask HN: 为什么开发者开始转向基于 CLI 的编码助手？
3 分•作者: just_human•9 个月前
过去几个月，我认识的大部分工程师都从 Cursor 转向了基于 CLI 的代理（主要是 Claude Code）。我个人很喜欢任何基于 CLI 的东西，但让我惊讶的是，那些几乎从不打开终端的开发者现在一夜之间变成了 Claude Code 和终端的重度用户。
从技术上讲，代理并不一定需要在终端中运行——在 Cursor 聊天中运行的代理可以使用 shell 作为工具，而且可以说拥有更好的用户界面。你通常从 CLI 工具中获得的价值（I/O 管道、可组合性）实际上并不适用于这些代理的使用方式。
我的理论有两点。首先，使用像 Claude Code 这样的 CLI 代理可以获得更好的价值，因为你不需要向 Cursor 这样的 IDE 支付“通行费”。其次，Claude Code 中有一些杀手级功能，比如“计划模式”，如果没有控制体验，Anthropic 就不可能构建出来。但我很好奇听听其他人的想法，以及基于 CLI 的代理是否会成为主流？
查看原文
In the last few months, most of the engineers I know have switched from Cursor to CLI-based agents (mostly Claude Code). I personally love anything CLI-based, but I've been surprised to see developers who almost never open a terminal now becoming Claude Code and terminal power users overnight.<p>Technically, there isn't a real need for agents to run in the terminal - an agent running in Cursor chat can use the shell as a tool and arguably has a nicer UI. The value you'd normally get from CLI tools (piping I/O, composability) doesn't really apply to how these agents are being used.<p>My theory is twofold. First, you get better value using CLI agents like Claude Code because you don't need to pay a "toll" to an IDE like Cursor. Second, there are some killer features in Claude Code like "plan mode" that wouldn't have been possible for Anthropic to build without controlling the experience. But curious to hear what others think, and whether CLI-based agents are here to stay?