One down-side to this is that it does require you to run the agent on your Mac instead of in a Sandbox. I do this too and there are lots of problems I can't solve in a sandbox. I know a lot of you are throwing your hands up at the years of security practices we're throwing out the window when we do that.
The fact that xAI uploaded someone's home directory, including their SSH keys, is giving me serious pause at my choices here.
Generally, I don't worry about my machine being "blown up". I don't have a TON of unreproducible stuff on my machine. Everything is backed up, committed to git, and the like. I can restore most of it in a couple hours.
That said, I really, really don't want my .SSH directory sent to an AI agent and it's silly to prompt your way around that. You need to block it at the system level. I'm considering a separate user and then 700 permissions on my home directory.
I feel like we're back to 1990's security here. The double-edged sword is that it's helping us get things done at a pace like never before.
I'm not throwing shade here, I'm among the guilty.
> require you to run the agent on your Mac instead of in a Sandbox
You don't have to! All recent Macs come with nearly zero perf cost virtualization. You can easily run Mac or Linux VMs assuming same architecture. Use it all the time for development and whatever.
Use Tart [1] or VirtualBuddy [2], both open-source, for a packaged solution. Or in the spirit of this post, vibe code your own wrapper around the OS API [3]
More recently, there are also Apple containers [4]
I've been working on a wrapper harness that runs claude as a separate user named `agent`. I tried this about a year ago and couldn't get it to work because of OAuth and the keychain, but took another pass recently and claude had enough self-knowledge about recent changes to say we could do it with CLAUDE_CODE_OAUTH_TOKEN. It has required building a some tooling around permissions setup with ACLs but it works on macOS today.
In terms of risk, I see it as halfway between stock claude with the sandbox and full-blown container or machine isolation.
I was recently thinking that as Claude's own sandbox gets better I'm doubting the ROI on my belt-and-suspenders project, but your comment reminds me why I'm doing it.
It is not currently published open source but I'm happy to talk about it with strangers.
I run my AI headless in a docker container and give it access to git – it can only contribute code - when it needs a secret I put it in a docker container in vault. when it needs infra, it makes me a jira ticket. that's my workflow.
I've been running my agents in a docker sandbox that automatically mounts the current directory. It's been a bit of a pain to figure out and maintain the set of tools I provision into the sandbox- but it's fun to watch codex go to the ends of the earth trying to figure out solutions using nodejs (the only runtime).
Seems to me a tool like that would stop the agent from sending those specific keys elsewhere. But a tool like that would not stop the agent who is acting as you from using the SSH keys via the CLI. You would want to combine that with other tactics like having the agent run as some other user.
Secretive (and the similar built-in functionality [1]) both allow you to require TouchID too. I found an okay balance using two SSH keys: one for commit signing (w/o TouchID) and one for everything else (requires TouchID, or PIN on Linux)
So, the actions that I really don't want the agent to take (establishing an SSH connection, pushing to a git remote) always require my manual intervention.
Many people have created Mac VM projects to do exactly this, I was working on one but was stalled too often because before I started using claude I bought a new laptop with what I KNEW was enough disk space.
The 100 GB or so I need to comfortably do the VM stuff just isn't available on my mac.
I’ve been doing the same except that my linux installation is via WSL on Windows. I’ve been using sideloadly to move my IPA over to my phone. Works great.
Dev apps need to be re-loaded every week (or two?) last time I did sideloading. The idea behind a dev app, in Apple's mind, is that it is for limited testing, so they have an expiration when not signed/installed through the App store.
If it's okay to mention my own complementary open source project, Axiom¹ does a good job of helping coding harnesses know how to do this effectively for Apple OS development.
In addition to a deep roster of skills and agencts, Axiom includes several for-LLM tools². xclog, xcprof, xcsym, and xcui are designed to be used by LLMs, and expose capabilities in a token-efficient way. These tools are equally helpful for non-Axiom skills/agents.
Silly question, but do you reckon it'll function decently in a Kotlin multiplatform codebase? There's swift native code, but I'm not sure how it would perform with some logic being shared.
Not silly at all. For Compose Multiplatform, Axiom won't do much for code review or generation. It might be useful for operations on the built app: console capture, crash symbolication, simulator UI/accessibility driving, CPU profiling, plus the whole shipping layer (signing, privacy manifests, submission).
Shameless plug: I've been working on strudel [0], a CLI that uses a lot of the same ideas in this post and allows you to build/sign/notarize Mac (and iOS) apps without touching Xcode. It has a dry run mode so you can see the actual commands being run, which was important to me to have so there's no mystery about what's happening.
I should blog about more this, but I also went to some effort to add support free iOS provisioning with just an Apple ID (using internal APIs); and creating a nice DMGs for macOS app distribution (reverse engineered .DS_store files for this). And there's also a built-in command to install skills for coding agents, which was fun.
This [1] is an example app I built with it, a simple utility to manage macOS file extension handling.
> I had Claude Code create mine: I told Claude, more or less: I want to archive, Developer ID-sign, notarize, staple, and install this app to /Applications without ever opening Xcode. Write me a script that does the whole chain and fails loudly if any step breaks.
Even though the text we're reading is Claude talking to us as well :)
Also it was weird to see the mention of "ask your LLM" at almost every stage in the blog post:
> point Claude Code or your LLM coding tool of choice to this blog post, and let it figure it out
> When in doubt, ask your LLM of choice about them and have it help you get set up. It’s the one that’s going to be using Xcode for you anyway.
> The whole point of using the LLM in the first place is to avoid doing things manually that you don’t want to do.
> Again, if in doubt, ask Claude Code or your LLM of choice to create this for you.
> Again, this is why you talk to your LLM, tell it what you want, and have it help build your workflow.
It seems too concise to be AI. My (conscious) heuristic for AI writing is how much context is squeezed into a sentence. LLMs seem to be pretty bad at the kind of elegant compression of meaning humans can do when they have done a lot of writing practice.
If I had to guess, I would say this is the human summarised conversation(s) with a bot.
Everyone will still need to use Xcode for at least some debugging, no way around that.
As for the builds, your agent probably already knows how to do a lot of this from the command line, although explicit suggestions can help it build faster for different situations.
As for XcodeGen, you may find it unnecessary overhead if you're already using Xcode file system synced groups.
I have one weird trick for people who are exploring this vein. I last opened an Xcode project about five years ago so I could be way behind the times.
Having spent many years fighting with Xcode professionally, I was thrilled when swift build came out, and then appalled at how badly Xcode adopted it. Eventually I realized that you can set up your entire app as a swift package, and then the Xcode project with a single main source file that calls some `app_main()` (or whatever you want to call it) function in your package.
I cannot remember exactly but there was something annoying about setting up a new project; I think by default Xcode assumes that you want a swift package to be treated as a dependency that is checked out from git, but there was a way to drag and drop a local dependency in the same project directory and then it worked.
What this buys you is that files are no longer tracked by Xcode, so renames/merges no longer trigger project.pbxproj surgery. Instead you specify the swift package directories and are done.
I used this for some large personal projects and was very happy with it.
At one point I also wrote my own build tool that imitated all of the steps that Xcode took so that I could truly be Xcode-free. That also worked (and was not even that hard) but I went back to Xcode because the debugger UI was better than what I could get out of VS Code at the time, and especially because I was playing around with the Metal debugger.
In my experience, the better long-term choice if you're going to vibe code an app is to use Expo.
Its basis is React, so the code output quality is much higher than Swift because there is much more React code in LLM training data.
Everything is in the command line, and debugging is a breeze because it's a web view. But once it's compiled to native iOS, it feels like any other native app.
Expo + Fastlane = fully automated iOS submission and deployment. I issue one command and see a new version in the App Store.
Check also Sweetpad CLI. It’s basically wrapper around xcodebuild, but humans and agents. It’s my next project after Sweetpad VSCode extension for developing iOS/Swift applications in VSCode. Cli is still in beta, but I see on my own project that it’s already quite pleasant to use
I went to build an open source app from GitHub and was pretty surprised that it requires Xcode and that Xcode can't really be installed without an apple id. I do not want to make one and I certainly will not sign my computer into one.
I did end up somehow installing Xcode via some shady download and was on my way. But the whole ordeal left a very sour taste.
Though the primary way of installing Xcode is via MAS (requiring Apple ID login), Xcode can be downloaded from the Apple Developer website without an ADP membership, though you do have to log in to the website with an Apple ID. You don’t have to log into the Mac with an Apple ID though, you can then install and use it on a Mac without an Apple ID (though you will need one inside Xcode to sign apps to get them to run on an iOS device).
The main iPhone app I maintain for work is 100% claude edited now ... I don't touch the code anymore ... I do occasionally look at it. It does a way better job than I could. I do have Xcode open as claude does its thing ... and I occasionally sign and deploy with Xcode. No coding though.
I find it hard to believe xcodegen is in a state where it would reliably generate xcodeproj for all edge states (widgets, watchos app, notification extensions …) - it certainly wasn’t when I last tried it for Weathergraph few years ago.
That said, it might be well enough for simpler apps.
What's a not-simple app? I've had Claude generate:
* A Markdown viewer (obviously pretty simple)
* A menu bar Apple TV remote (surprisingly complicated)
* A menu bar and desktop temperature tracker for the silly Tapo temperature trackers I have all over my house (a little complicated because multiple user interfaces, a backing database, scheduling, and multiple local/remote protocol interfaces)
* A graphical CAS calculator frontend to Sage Math with LaTeX math rendering
* An LLMwiki implementation that uses macOS filesystem extensions to reflect a SQLite database into a local filesystem for agents to traverse (basically the new macOS way to do FUSE, fussy enough that the app has to run out of /Applications to work)
* An agent-driven Music.app replacement with AirPlay streaming support managing Apple Music catalogs and tracks
All of these have worked without me ever once touching the xcode UI, except one time to generate Apple Developer certificates, which I then drove exclusively from CLI tools.
I've been using essentially this process (with Claude Code) for about six months. There are a couple of places where I've opened xcode; mostly to update the simulators for new betas of xcode 27, and once to add a target for Apple Watch (and I think something for HealthKit).
Interestingly, since about Opus 4.6, Claude has been able to reason its way into this process on its own. It was clunky until 4.7, and in 4.8 it's managed to find its way around every reason I had to open xcode myself.
I just set up my pipeline to do this exact thing for both the Apple and Android ecosystems, dispatching loads to my mac studio or Linux box accordingly. I moved the runners off GitHub because uptime for GitHub actions has been trash lately, and the Apple Silicon runners are pricey.
Claude was great at figuring out what was broken when and either fixing it, or clicking as far as it could until it needed me.
You could say I'm mostly just IRL hands for the AI now.
Making your app buildable from the CLI is not something I do personally to use on my Mac but it is very useful when you're automating your CI. If you have GitHub Actions set up to build your app, so can Claude, assuming you have the right signing setup on your machine.
In addition to the challenged Xcode, just using Swift seems to require a lot more tokens for both coding and dealing with build/platform quirks. Probably not super significant on indie scale but for anything more robust, it builds up quickly.
React Native and Flutter seem to be much more predictable for the bots (and more fun for humans, since they have actual hot reload).
Xcode does have (or had, haven't checked for a while) a lightweight "command line tools only" installer. Unfortunately, that installer omits a lot of the actual useful command line tools, like the notary and stapler tools. I also recall that the command line tool only installer leaves out things like the metal compiler, too. Not sure what the point of it is.
My only familiarity with it is because it's needed by brew. I honestly never looked into exactly what is in the package, but I assumed things like what is installed with -devel packages of yum/apt-get/dnf/etc. Lots of repos have common list of things to install like gcc/make/etc. Again, just guessing, but it's one of the first things I've always run on a new Mac to get it usable for CLI usage.
This is cool but also makes me worried about the tendency with llms for all of us to make bespoke solutions rather than building a better community tool or extending an existing tool to solve the problem. fastlane exists to solve exactly this problem in the mobile space.
Also, shell scripts as part of a build are usually a little worrying. I'd at least want the build steps to be all integrated into my Makefile or CMakeLists.txt
The llm is the better community tool. The important change is that you don't have to settle with someone developing a monolithic tool that happens to do what you need it to do. That was the way things used to need to be done because of the cost.
Bespoke solutions are better in many cases. They do exact things required for the project without taking extra dependency. Reducing dependencies is beneficial, because dependencies require management. So with llms economy of taking dependency shifted.
I built an iOS simulator simulator, though only for RN. Runs in browser but covers 100% of the API of RN, iOS UI, and the top 1k native libraries basically now. Been an ongoing agentic experiment of mine that's about ready to release.
Kind of fun, you can develop iOS and Android both without a build step and without a Mac even.
Last I used flutter, editable text views was where it wasn't acceptable for me. On iOS, the default text view comes with a lot of built in stuff automatically such as cut copy paste, lookup definition, translate etc. Flutter's didn't have these.
Wait, I am not aware that I've done ANY of those setup steps, yet I'm building iOS and macOS apps without XCode. Both Claude and Codex handle it just fine and didn't ask me for any setup steps.
Per year, but still amazing. I'd like to think of myself who knows what he is doing, but I just launched a Rails-based platform for a client on web, iOS and Android, and had to spend an annoying amount of time in Google Play and App Store Connect. $299 would be a tiny fraction of the billable hours I'd have to spend messing around in there, and that's not counting mobile app dev time at all, so I'm on the lookout for a good candidate project to try Ruby Native on!
Being outside of the approved development loop has rough edges. How do you keep the app from putting up that permission to access documents folder all the time while you rebuild it?
Oh god, the app store does not need more slop. If you can't be bothered to open XCode (which I agree is a dumpster fire, but), you shouldn't be bothered to submit an app that a person has to review and another person has to filter out of their search results.
Counterpoint: XCode is such slop that an app made by a developer with the taste to avoid it has a higher probability of being less "sloppy" than average.
Tangentially, I despise Xcode and love the Expo ecosystem and all the lovely tooling that they have built. It is React Native but Expo honestly makes it so trivial to build stuff from the CLI without ever needing to open that abomination of an app. And with AI, I have built a lot of side project apps onto my iPhone, like a homelab app for monitoring my cameras with push notifications whenever someone is at the door, starting my irrigation and a whole lot more. Plus Tailscale of course. Kind of a crazy world that we live in now.
As someone who tried my very best to not open Xcode for building and shipping Mac and iOS apps, I agree, there are things there are literally no way around opening the GUI, not even terminal utilities for. You cannot do this 100% headless, which is what I attempted at first.
I've used opencode on a plane with local models to make small updates to local MacOS apps. It's not fast or amazing, but it does work well enough to do trivial changes.
What could go wrong? Might Apple change something across five ecosystems and leave you in the lurch, and now you have to go through all the slop to try to fix it?
One down-side to this is that it does require you to run the agent on your Mac instead of in a Sandbox. I do this too and there are lots of problems I can't solve in a sandbox. I know a lot of you are throwing your hands up at the years of security practices we're throwing out the window when we do that.
The fact that xAI uploaded someone's home directory, including their SSH keys, is giving me serious pause at my choices here.
Generally, I don't worry about my machine being "blown up". I don't have a TON of unreproducible stuff on my machine. Everything is backed up, committed to git, and the like. I can restore most of it in a couple hours.
That said, I really, really don't want my .SSH directory sent to an AI agent and it's silly to prompt your way around that. You need to block it at the system level. I'm considering a separate user and then 700 permissions on my home directory.
I feel like we're back to 1990's security here. The double-edged sword is that it's helping us get things done at a pace like never before.
I'm not throwing shade here, I'm among the guilty.
> require you to run the agent on your Mac instead of in a Sandbox
You don't have to! All recent Macs come with nearly zero perf cost virtualization. You can easily run Mac or Linux VMs assuming same architecture. Use it all the time for development and whatever.
Use Tart [1] or VirtualBuddy [2], both open-source, for a packaged solution. Or in the spirit of this post, vibe code your own wrapper around the OS API [3]
More recently, there are also Apple containers [4]
[1] https://tart.run/
[2] https://github.com/insidegui/VirtualBuddy
[3] https://developer.apple.com/documentation/virtualization
[4] https://github.com/apple/container
I've been working on a wrapper harness that runs claude as a separate user named `agent`. I tried this about a year ago and couldn't get it to work because of OAuth and the keychain, but took another pass recently and claude had enough self-knowledge about recent changes to say we could do it with CLAUDE_CODE_OAUTH_TOKEN. It has required building a some tooling around permissions setup with ACLs but it works on macOS today.
In terms of risk, I see it as halfway between stock claude with the sandbox and full-blown container or machine isolation.
I was recently thinking that as Claude's own sandbox gets better I'm doubting the ROI on my belt-and-suspenders project, but your comment reminds me why I'm doing it.
It is not currently published open source but I'm happy to talk about it with strangers.
I run my AI headless in a docker container and give it access to git – it can only contribute code - when it needs a secret I put it in a docker container in vault. when it needs infra, it makes me a jira ticket. that's my workflow.
I've been running my agents in a docker sandbox that automatically mounts the current directory. It's been a bit of a pain to figure out and maintain the set of tools I provision into the sandbox- but it's fun to watch codex go to the ends of the earth trying to figure out solutions using nodejs (the only runtime).
okay but that doesn't help a single bit with the OPs point. Your xcode tools do not run inside a docker container
You could move your SSH keys onto a password encrypted usb drive that you physically remove from the computer.
An alternative is to use ssh keys stored in the Secure Enclave with tools like https://secretive.dev/
Seems to me a tool like that would stop the agent from sending those specific keys elsewhere. But a tool like that would not stop the agent who is acting as you from using the SSH keys via the CLI. You would want to combine that with other tactics like having the agent run as some other user.
Secretive (and the similar built-in functionality [1]) both allow you to require TouchID too. I found an okay balance using two SSH keys: one for commit signing (w/o TouchID) and one for everything else (requires TouchID, or PIN on Linux)
So, the actions that I really don't want the agent to take (establishing an SSH connection, pushing to a git remote) always require my manual intervention.
[1] https://gist.github.com/arianvp/5f59f1783e3eaf1a2d4cd8e952bb...
Your sandbox can be a separate Mac user account.
You can also use native Mac VMs.
Many people have created Mac VM projects to do exactly this, I was working on one but was stalled too often because before I started using claude I bought a new laptop with what I KNEW was enough disk space.
The 100 GB or so I need to comfortably do the VM stuff just isn't available on my mac.
On a Mac. Just get a Mac mini. It doesn't have to be a crazy big beefy one, and if you're selling apps, it's a justifiable business expense.
I've been building and testing my iOS app just for fun via Linux only.
Surprisingly, it's very easy. This works like a charm: https://github.com/xtool-org/xtool
You do not need to upload to TestFlight or the App Store; you can just install the app locally to your iPhone via usb -- even from Linux!
When in doubt, just ask your coding agent of choice to help you create and upload a Hello World iOS app. It's really easy.
I’ve been doing the same except that my linux installation is via WSL on Windows. I’ve been using sideloadly to move my IPA over to my phone. Works great.
Woah thanks for sharing will have to check this out.
Do the coding agents know about this tool?
just link it?
Does the iPhone need to remain tethered if it is transferred via USB?
Dev apps need to be re-loaded every week (or two?) last time I did sideloading. The idea behind a dev app, in Apple's mind, is that it is for limited testing, so they have an expiration when not signed/installed through the App store.
If it's okay to mention my own complementary open source project, Axiom¹ does a good job of helping coding harnesses know how to do this effectively for Apple OS development.
In addition to a deep roster of skills and agencts, Axiom includes several for-LLM tools². xclog, xcprof, xcsym, and xcui are designed to be used by LLMs, and expose capabilities in a token-efficient way. These tools are equally helpful for non-Axiom skills/agents.
¹ Axiom: https://charleswiltgen.github.io/Axiom/ ² Axiom CLI tools: https://charleswiltgen.github.io/Axiom/tools/
Silly question, but do you reckon it'll function decently in a Kotlin multiplatform codebase? There's swift native code, but I'm not sure how it would perform with some logic being shared.
Not silly at all. For Compose Multiplatform, Axiom won't do much for code review or generation. It might be useful for operations on the built app: console capture, crash symbolication, simulator UI/accessibility driving, CPU profiling, plus the whole shipping layer (signing, privacy manifests, submission).
Axiom is excellent, thanks for making it!
I'm glad that it's been valuable for you!
Use axiom all the time thanks for your work. The next frontier in iOS app tooling is self-hostable Linux based build server. Thoughts?
Sounds very intriguing! Please reach out (see my profile) when you're ready to share more.
will it work with flutter ?
Axiom covers only native APIs and tools, but the Flutter team maintains what looks like a nice set of skills at https://github.com/flutter/agent-plugins, and the Dart team at https://github.com/dart-lang/skills.
Shameless plug: I've been working on strudel [0], a CLI that uses a lot of the same ideas in this post and allows you to build/sign/notarize Mac (and iOS) apps without touching Xcode. It has a dry run mode so you can see the actual commands being run, which was important to me to have so there's no mystery about what's happening.
I should blog about more this, but I also went to some effort to add support free iOS provisioning with just an Apple ID (using internal APIs); and creating a nice DMGs for macOS app distribution (reverse engineered .DS_store files for this). And there's also a built-in command to install skills for coding agents, which was fun.
This [1] is an example app I built with it, a simple utility to manage macOS file extension handling.
[0] https://github.com/octavore/strudel
[1] https://github.com/octavore/tots.app
It's kind of funny to be reading this:
> I had Claude Code create mine: I told Claude, more or less: I want to archive, Developer ID-sign, notarize, staple, and install this app to /Applications without ever opening Xcode. Write me a script that does the whole chain and fails loudly if any step breaks.
Even though the text we're reading is Claude talking to us as well :)
Also it was weird to see the mention of "ask your LLM" at almost every stage in the blog post:
> point Claude Code or your LLM coding tool of choice to this blog post, and let it figure it out
> When in doubt, ask your LLM of choice about them and have it help you get set up. It’s the one that’s going to be using Xcode for you anyway.
> The whole point of using the LLM in the first place is to avoid doing things manually that you don’t want to do.
> Again, if in doubt, ask Claude Code or your LLM of choice to create this for you.
> Again, this is why you talk to your LLM, tell it what you want, and have it help build your workflow.
Claude telling us to point Claude to a web site written by Claude so that we can use Claude to create a build environment...
yo dawg
I heard you liked Claude, so I put extra Claude in your Claude so you can do more Claude.
I suppose it's easier to turn everyone into unwitting tokenmaxxers than it is to raise prices again.
… that Claude can use, because Claude can’t use the XCode gui very efficiently.
"Claude was the only LLM to survive the LLM Wars."
The mistakes in the text made me doubt it was AI, but who knows, maybe it's doing that on purpose now
It seems too concise to be AI. My (conscious) heuristic for AI writing is how much context is squeezed into a sentence. LLMs seem to be pretty bad at the kind of elegant compression of meaning humans can do when they have done a lot of writing practice.
If I had to guess, I would say this is the human summarised conversation(s) with a bot.
Technically, you are using Xcode.
Xcode is a [buggy as hell] GUI wrapper for a lot of system-level UNIX utilities and apps [which are generally, not so buggy].
Using CLI to release apps is a pretty old practice; at least as long as I've been doing it (I released my first Xcode app in 2012).
That's good to hear. I never even tried to make anything for macOS because I opened Xcode and.. well, you know.
Everyone will still need to use Xcode for at least some debugging, no way around that.
As for the builds, your agent probably already knows how to do a lot of this from the command line, although explicit suggestions can help it build faster for different situations.
As for XcodeGen, you may find it unnecessary overhead if you're already using Xcode file system synced groups.
For iOS my biggest suggestion would be to enable App Store Connect skills for your agent (https://github.com/rorkai/App-Store-Connect-CLI).
With this not only do you not need Xcode all the time, you also don't even need to be near a MacBook.
Just make changes via Codex on your iPhone, the tell asc to build and upload to TestFlight, download and run the new version, iterate.
I have one weird trick for people who are exploring this vein. I last opened an Xcode project about five years ago so I could be way behind the times.
Having spent many years fighting with Xcode professionally, I was thrilled when swift build came out, and then appalled at how badly Xcode adopted it. Eventually I realized that you can set up your entire app as a swift package, and then the Xcode project with a single main source file that calls some `app_main()` (or whatever you want to call it) function in your package.
I cannot remember exactly but there was something annoying about setting up a new project; I think by default Xcode assumes that you want a swift package to be treated as a dependency that is checked out from git, but there was a way to drag and drop a local dependency in the same project directory and then it worked.
What this buys you is that files are no longer tracked by Xcode, so renames/merges no longer trigger project.pbxproj surgery. Instead you specify the swift package directories and are done.
I used this for some large personal projects and was very happy with it.
At one point I also wrote my own build tool that imitated all of the steps that Xcode took so that I could truly be Xcode-free. That also worked (and was not even that hard) but I went back to Xcode because the debugger UI was better than what I could get out of VS Code at the time, and especially because I was playing around with the Metal debugger.
In my experience, the better long-term choice if you're going to vibe code an app is to use Expo.
Its basis is React, so the code output quality is much higher than Swift because there is much more React code in LLM training data.
Everything is in the command line, and debugging is a breeze because it's a web view. But once it's compiled to native iOS, it feels like any other native app.
Expo + Fastlane = fully automated iOS submission and deployment. I issue one command and see a new version in the App Store.
Some parts when creating a new app cannot be automated right? Eg registering the app itself for example.
You can have your AI agent use computer-use to click around on in a browser open on developer.apple.com if that's counts as automated to you.
This one?? https://expo.dev/
HN hug of death? seems to be back now.
fwiw, expo seems solid; the uptime of expo.dev won't affect an app built with it.
Check also Sweetpad CLI. It’s basically wrapper around xcodebuild, but humans and agents. It’s my next project after Sweetpad VSCode extension for developing iOS/Swift applications in VSCode. Cli is still in beta, but I see on my own project that it’s already quite pleasant to use
1. https://sweetpad.hyzyla.dev/
2. https://github.com/sweetpad-dev/sweetpad
Interesting this is coming across as novel. This is how CI build machines for Apple’s platforms have been setup in perpetuity.
Regardless of the vibe coding aspect, there's good information here for anyone new to the mac/ios build/distribution workflows.
I went to build an open source app from GitHub and was pretty surprised that it requires Xcode and that Xcode can't really be installed without an apple id. I do not want to make one and I certainly will not sign my computer into one.
I did end up somehow installing Xcode via some shady download and was on my way. But the whole ordeal left a very sour taste.
Running a Mac without an Apple ID feels like an exercise in masochism. I wasn’t aware one could even still it through first run without
Why do you need one?
Heck you can't even compile against many of the Mac APIs without a cert unlocked by a paid developer account.
Though the primary way of installing Xcode is via MAS (requiring Apple ID login), Xcode can be downloaded from the Apple Developer website without an ADP membership, though you do have to log in to the website with an Apple ID. You don’t have to log into the Mac with an Apple ID though, you can then install and use it on a Mac without an Apple ID (though you will need one inside Xcode to sign apps to get them to run on an iOS device).
The main iPhone app I maintain for work is 100% claude edited now ... I don't touch the code anymore ... I do occasionally look at it. It does a way better job than I could. I do have Xcode open as claude does its thing ... and I occasionally sign and deploy with Xcode. No coding though.
I find it hard to believe xcodegen is in a state where it would reliably generate xcodeproj for all edge states (widgets, watchos app, notification extensions …) - it certainly wasn’t when I last tried it for Weathergraph few years ago.
That said, it might be well enough for simpler apps.
What's a not-simple app? I've had Claude generate:
* A Markdown viewer (obviously pretty simple)
* A menu bar Apple TV remote (surprisingly complicated)
* A menu bar and desktop temperature tracker for the silly Tapo temperature trackers I have all over my house (a little complicated because multiple user interfaces, a backing database, scheduling, and multiple local/remote protocol interfaces)
* A graphical CAS calculator frontend to Sage Math with LaTeX math rendering
* An LLMwiki implementation that uses macOS filesystem extensions to reflect a SQLite database into a local filesystem for agents to traverse (basically the new macOS way to do FUSE, fussy enough that the app has to run out of /Applications to work)
* An agent-driven Music.app replacement with AirPlay streaming support managing Apple Music catalogs and tracks
All of these have worked without me ever once touching the xcode UI, except one time to generate Apple Developer certificates, which I then drove exclusively from CLI tools.
These are all pretty modern SwiftUI applications.
I've been using essentially this process (with Claude Code) for about six months. There are a couple of places where I've opened xcode; mostly to update the simulators for new betas of xcode 27, and once to add a target for Apple Watch (and I think something for HealthKit).
Interestingly, since about Opus 4.6, Claude has been able to reason its way into this process on its own. It was clunky until 4.7, and in 4.8 it's managed to find its way around every reason I had to open xcode myself.
I just set up my pipeline to do this exact thing for both the Apple and Android ecosystems, dispatching loads to my mac studio or Linux box accordingly. I moved the runners off GitHub because uptime for GitHub actions has been trash lately, and the Apple Silicon runners are pricey.
Claude was great at figuring out what was broken when and either fixing it, or clicking as far as it could until it needed me.
You could say I'm mostly just IRL hands for the AI now.
I prefer Tuist (writing Project.swift) to XcodeGen but otherwise, yeah, this tracks
Or use https://swiftbundler.dev/ ?
The thing is, in a perspective, who would need any apps at all? Users will get what they want from AI directly.
built cable detective like this https://apps.apple.com/at/app/cable-detective/id6765963737?l... and the soon to come https://aifcc.franzai.com/ which is more ambitious
honestly would not even know what to do / click in xcode
You can as well make it simpler and use those skills:
https://github.com/software-mansion/argent
or
https://github.com/callstack/agent-device
both callstack and swmansion are mostly react native shops but those should work even in native ios/android as well
Making your app buildable from the CLI is not something I do personally to use on my Mac but it is very useful when you're automating your CI. If you have GitHub Actions set up to build your app, so can Claude, assuming you have the right signing setup on your machine.
Shout out to fastlane! I would have loved to have found it sooner in my app shipping journey.
In addition to the challenged Xcode, just using Swift seems to require a lot more tokens for both coding and dealing with build/platform quirks. Probably not super significant on indie scale but for anything more robust, it builds up quickly.
React Native and Flutter seem to be much more predictable for the bots (and more fun for humans, since they have actual hot reload).
Having to have Xcode installed is more than half the problem. It makes Visual Studio look lightweight.
Xcode does have (or had, haven't checked for a while) a lightweight "command line tools only" installer. Unfortunately, that installer omits a lot of the actual useful command line tools, like the notary and stapler tools. I also recall that the command line tool only installer leaves out things like the metal compiler, too. Not sure what the point of it is.
> Not sure what the point of it is.
My only familiarity with it is because it's needed by brew. I honestly never looked into exactly what is in the package, but I assumed things like what is installed with -devel packages of yum/apt-get/dnf/etc. Lots of repos have common list of things to install like gcc/make/etc. Again, just guessing, but it's one of the first things I've always run on a new Mac to get it usable for CLI usage.
It lets you build basic UNIX-like tools.
It’s mostly all the emulators and platform APIs.
I’m not defending Xcode (I hate it), just clarifying.
This is cool but also makes me worried about the tendency with llms for all of us to make bespoke solutions rather than building a better community tool or extending an existing tool to solve the problem. fastlane exists to solve exactly this problem in the mobile space.
Also, shell scripts as part of a build are usually a little worrying. I'd at least want the build steps to be all integrated into my Makefile or CMakeLists.txt
The llm is the better community tool. The important change is that you don't have to settle with someone developing a monolithic tool that happens to do what you need it to do. That was the way things used to need to be done because of the cost.
Bespoke solutions are better in many cases. They do exact things required for the project without taking extra dependency. Reducing dependencies is beneficial, because dependencies require management. So with llms economy of taking dependency shifted.
... avoiding this problem: https://xkcd.com/974
I’ve done this forever on Foqos. Have a makefile, never even open Xcode and the instructions are in the agents md
Doesn't that mean you need to distribute the app (TestFlight) before you can preview your app? How do you test locally without the simulators?
For a macOS app you don't need a simulator. For an iPhone app I've seen Claude Code launch the simulator without me needing to open Xcode.
I built an iOS simulator simulator, though only for RN. Runs in browser but covers 100% of the API of RN, iOS UI, and the top 1k native libraries basically now. Been an ongoing agentic experiment of mine that's about ready to release.
Kind of fun, you can develop iOS and Android both without a build step and without a Mac even.
Testing != Distribution. You can run directly on a connected iOS device, without setting up anything related to the app store.
I thought this would be a flutter post. Love flutter, ... , well I like flutter compared to Kotlin and Swift
Last I used flutter, editable text views was where it wasn't acceptable for me. On iOS, the default text view comes with a lot of built in stuff automatically such as cut copy paste, lookup definition, translate etc. Flutter's didn't have these.
I've built a few small MacOS dock widgets now by just telling Claude/OpenCode to build them. Works well enough if you're very explicit.
The most useful one is a little weather sparkline to show local temperature forecasts. Useful every day.
What framework was it written in, and does it trigger a scary warning from the OS when you try to install it?
Wait, I am not aware that I've done ANY of those setup steps, yet I'm building iOS and macOS apps without XCode. Both Claude and Codex handle it just fine and didn't ask me for any setup steps.
> Without Ever Opening Xcode
"Next, open Xcode"
Thought this was going to be about the new Ruby Native!
https://rubynative.com
“From bundle install to your phone in minutes. To the App Store and Google Play without a line of native code.“
holy hell $299/app is wild
One time?! That's amazing.
Per year, but still amazing. I'd like to think of myself who knows what he is doing, but I just launched a Rails-based platform for a client on web, iOS and Android, and had to spend an annoying amount of time in Google Play and App Store Connect. $299 would be a tiny fraction of the billable hours I'd have to spend messing around in there, and that's not counting mobile app dev time at all, so I'm on the lookout for a good candidate project to try Ruby Native on!
per app per year
I do something similar in GitHub actions. Every new app is setup in a few minutes to star getting rejected by iOS and Android.
Being outside of the approved development loop has rough edges. How do you keep the app from putting up that permission to access documents folder all the time while you rebuild it?
They're a paid developer, so they are probably signing the app with a stable identity that avoids this.
Oh god, the app store does not need more slop. If you can't be bothered to open XCode (which I agree is a dumpster fire, but), you shouldn't be bothered to submit an app that a person has to review and another person has to filter out of their search results.
Counterpoint: XCode is such slop that an app made by a developer with the taste to avoid it has a higher probability of being less "sloppy" than average.
The 'developer' isn't even developing much of anything tho
Although this has been well known for years and documented.
Yeah, but not only was this "on a computer" but "with an AI" so it's not the same at all. /s
Skimmed the article. Pretty close to my workflow using fastlane with tauri.
Useful sanity check!
I spent seven years as a dev on the Xcode team and this is pretty much my exact workflow these days.
Tangentially, I despise Xcode and love the Expo ecosystem and all the lovely tooling that they have built. It is React Native but Expo honestly makes it so trivial to build stuff from the CLI without ever needing to open that abomination of an app. And with AI, I have built a lot of side project apps onto my iPhone, like a homelab app for monitoring my cameras with push notifications whenever someone is at the door, starting my irrigation and a whole lot more. Plus Tailscale of course. Kind of a crazy world that we live in now.
Yes, I remember React Native being quite painful before Expo!
Upgrading from one version to the next especially so.
Expo seems to shield you from a lot of issues, without really taking any power away from you either.
You still have to open Xcode (to get the certs), and you still have to accept the Xcode EULA. Title is quite misleading if not outright false.
As someone who tried my very best to not open Xcode for building and shipping Mac and iOS apps, I agree, there are things there are literally no way around opening the GUI, not even terminal utilities for. You cannot do this 100% headless, which is what I attempted at first.
By using "Claude Code"*
* and giving Anthropic all your secrets, env vars, certificates and your source code to them.
I've used opencode on a plane with local models to make small updates to local MacOS apps. It's not fast or amazing, but it does work well enough to do trivial changes.
But also yes this is a real concern.
What bad things to you anticipate Anthropic doing with your secrets, env vars, and certificates?
Not if you've got a good sandbox.
Do you have one?
Yup, I built one! https://github.com/kstenerud/yoloai
You can even run simulators in it if you choose the Tart backend.
And how is your vibe coded sandbox better than 1000 other sandboxes?
You'll never know. And that's fine.
What could go wrong? Might Apple change something across five ecosystems and leave you in the lurch, and now you have to go through all the slop to try to fix it?
Don't make apps for iOS. The apple ecosystem is horrendous