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.




每天看著十幾個 Agent 分支合併已成為常態,而這釋放出的開發速度體現在從發布節奏到錯誤待辦清單消化的各個方面。Cursor 不只是一個便利的附加工具;它是整個組織的規模倍增器。

我永遠不會對能在騎 Peloton 時合併 PR(拉取請求)感到不驚奇。我再也不想碰筆記型電腦了。

讓 Cursor 團隊來發揮模型的最大潛力吧。GPT-5.2 是一個極其勤奮的模型,但要讓它持續工作整整一週實在太瘋狂了。構建整個瀏覽器更是瘋狂至極!

像 Cursor 這樣的程式設計代理已成為 AI(人工智慧)的殺手級應用。程式設計代理不僅提升了程式碼的建立速度,還改善了程式碼品質。

Cursor 不僅幫助我提升了生產力,也讓我更有好奇心和信心去探索新的問題領域。它已真正成為我日常工作流程中不可或缺的工具。

我們超過 70% 的工程師現在使用 Cursor,並且在日常開發、大規模遷移的執行速度、除錯效率,甚至新人入職速度方面都看到了顯著的提升。

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.
受全球頂尖開發者信賴