Cursor launches iPhone app to oversee coding agents on the go
Cursor launched an iPhone app that lets developers steer cloud or local coding agents from their phone, review diffs and merge PRs anywhere.

Cursor launched a native iOS app in public beta and turned the iPhone into a remote console for coding agents that can run in the cloud or on a developer’s own machine. The app lets users kick off work from a phone, get notified when it is ready for review, inspect changes, and merge pull requests without returning to a laptop.
The new app adds voice input, slash commands, Live Activities on the lock screen, push notifications, artifact review, diff inspection and follow-up instructions. Early testers are already using it for on-call incident response, customer bug fixes and for turning screenshots from other mobile apps into visual context for design and UI changes. For agents running on a user’s computer, the app uses Remote Control, and users can keep the machine awake while away from the desk.

The iPhone release extends a rollout that began with Cursor’s web app for managing agents in June 2025 and widened in February 2026 to the web, mobile, desktop app, Slack and GitHub. Its cloud agents run in isolated virtual machines with full development environments, can produce merge-ready pull requests, demos, screenshots and logs, and more than 30% of the pull requests Cursor merges internally are now created by autonomous agents in cloud sandboxes.
In April 2026, Cursor 3 introduced a unified workspace with seamless handoff between local and cloud agents and support for many agents in parallel, while access spans desktop, CLI, web and mobile. In June 2025, Cursor raised $900 million at a $9.9 billion valuation, topped $500 million in annual recurring revenue and was used by more than half of the Fortune 500.
This article was produced by Prism’s automated news system from verified source data, official records, and press releases, then run through automated quality and moderation checks before publishing. The system is built and supervised by the people who set the standards it runs under. Read our full AI policy.
Did this article answer your question?

