Cursor for iOS - Build with coding agents from anywhere

by
Cursor is now available as a native iOS app in public beta, so you can build from anywhere. Until now, developers have worked around the limits of their local machines, keeping laptops half-open and caffeinated everywhere they go. With Cursor for iOS, you can launch always-on agents in the cloud, or control agents running on your computer from your phone. Kick them off when ideas strike, get notified when work is ready for review, and merge PRs on the go.

Add a comment

Replies

Best

Artifacts as the review surface instead of the raw diff matches what we landed on too. The thing that decides whether they actually gate: are the screenshots and logs from an independent run, or the agent narrating its own work? We had demo clips that looked green because the agent captured the happy path it just wrote, and the regression sat one screen over. Tying review to CI output like you mentioned to Prashant is the version I'd trust from a phone.

 if you're looking for an independent run, you could set up an automation that works like a CI check!

So great!

When will it connect to the X accounts as well plz.. I hope I am writing to the right cursor..
Downloaded it immediately! Really enjoyed the smoothness and familiarity of the app when compared with the desktop application.

 fantastic to hear. Let us know if you have any feedback!

A theme across the reviews seems to be that people want more visibility into which files and symbols the agent actually pulls into context on big codebases, but also a way to steer it. Any plans to expose and let users control context selection more directly ?

If you were starting Cursor from scratch today, would you build the desktop app first again, or go in a different direction?

the part i want to try is approving agent permissions from the phone. usually a Claude Code session blocks on a prompt while i'm away from the desk and i don't notice for an hour. does iOS push a notification when an agent needs approval or do you have to open the app to check

 you'll get push notifications when the agent needs your input! You can also see Live Activities from your lock screens so you can monitor your agents without needing to open the app.

 that's exactly what i needed to hear, thanks. gonna give it a real try this week on a side project and see how the approval flow feels in practice

I am curious to use this mobile app. Could you tell me it is free or paid for first time?

 Cursor for iOS requires a paid plan. Hope you try it out!

Not sure why but I only see cloud session, I see zero local mac sessions and I do not get any updates about local sessions via push notification as well.
Is the app meant only for cloud sessions? and if not, what I am doing wrong, I am on the latests version of the mobile and desktop apps on my mac

I switched to Kilo after being burned by Cursor's predatory billing practices. Cursor charged me $313 in "Premium model overage" fees on top of my $200/month Ultra plan — charges they never disclosed upfront. Even their own AI Support Agent admitted the marketing was misleading. They refused to refund. I had to dispute the charges with my bank.

Kilo has been the exact opposite experience.

I brought my own DeepSeek API key — and it just worked. No vendor lock-in. No hidden fees. No "oh by the way, that model costs extra" surprises. I can use DeepSeek V4 Pro alongside other models at the actual provider rates, without any markup.

What I love about Kilo:

Honest pricing — you pay for what you use, and you see exactly what it costs

Model freedom — switch between models mid-session without rebuilding your workflow

DeepSeek support — finally able to use it at its full potential without restrictions

Open source — you can audit everything that runs on your machine

Cursor turned a loyal, paying customer into an activist.

Kilo turned me back into a productive developer.


If you care about transparency, control, and not being nickel-and-dimed by your AI tools, Kilo is the answer.