Cursor Releases Feature to Run AI Agents on Your Own Internal Network
Source Cursor changelog
At a glance
Cursor has released a feature that lets AI agents run on a company's own machines. Code and passwords stay on internal devices and do not leave the company.
Key points
Teams can create a shared pool of machines. When a request comes in, an idle worker takes it on.
Machines with no requests are put to sleep and woken up again when follow-up requests arrive.
Agents can also run in cloud environments teams already use, such as AWS Lambda, Cloudflare, and Vercel.
On Linux and Mac, agents can view the screen and perform clicks, typing, and browser actions.
Why it matters
Teams that find it hard to upload code to external clouds because of company security rules can still use AI coding tools.
Original article
Self-hosted machines
Cursor changelog · Sep 2, 2026, 9:00 AM GMT+9 · cursor.com
Read on Cursor changelogAI read the original article and summarized it in plain language. It may contain mistakes, so please check the original for accuracy. The article's copyright belongs to Cursor changelog.