Securely indexing large codebases
By securely reusing a teammate's existing index, we cut time-to-first-query from hours to seconds on the largest repos.
Software creation is changing. We are a group of researchers, engineers, and technologists inventing at the edge of what's useful and possible.
We have much to learn, try, and build.




Securely indexing large codebases
By securely reusing a teammate's existing index, we cut time-to-first-query from hours to seconds on the largest repos.
Scaling long-running autonomous coding
We've been experimenting with running coding agents autonomously for weeks at a time.
Dynamic context discovery
As models improve as agents, we've found success by providing fewer details up front, making it easier for the agent to pull relevant context on its own.
Software creation is changing. We are a group of researchers, engineers, and technologists inventing at the edge of what's useful and possible.
We have much to learn, try, and build.




如今,每天看着十几个智能体分支完成合并,已经成了常态,而由此释放出的开发速度提升体现在方方面面,从发布节奏到缺陷积压的清理。Cursor 不是一个只是提升便利性的附加工具;它是整个组织的规模放大器。

直到今天,我仍会为自己能一边骑着 Peloton,一边合并 PR 而惊叹。我再也不用碰笔记本电脑了。

也只有 Cursor 团队才能将这些模型的潜力发挥到极致。GPT-5.2 本身已经是个能力惊人的模型了,但能让它高效工作整整一周,简直不可思议。更夸张的是,竟然还能构建出一个完整的浏览器!

像 Cursor 这样的编程智能体,已经成为 AI 的杀手级应用。编程智能体不仅提升了代码创建的速度,也改善了代码质量。

Cursor 不仅帮助我变得更高效,也让我更有好奇心和信心去探索新的问题领域。它确实已经成为我日常工作流中不可或缺的工具。

如今,我们超过 70% 的工程师都在使用 Cursor,而且我们已经看到它在日常开发中带来了显著提升:大规模迁移推进得更快、调试效率更高,甚至新成员上手也更迅速。

Securely indexing large codebases
By securely reusing a teammate's existing index, we cut time-to-first-query from hours to seconds on the largest repos.
Scaling long-running autonomous coding
We've been experimenting with running coding agents autonomously for weeks at a time.
Dynamic context discovery
As models improve as agents, we've found success by providing fewer details up front, making it easier for the agent to pull relevant context on its own.
深受全球顶尖开发者信赖