I wonder what it is actually building. Tauri apps, maybe?
> Design Philosophy Create apps that feel premium, polished, and worthy of being featured on Dribbble's most popular shots. Every pixel matters. White space is your friend. Less is more, but what remains must be perfect.
> Visual Design Principles
> Color & Theming
> • Use sophisticated, limited color palettes (2-3 primary colors maximum) ...
Have it create a swift app, unless extended permissions are needed it can compile withouy going into xcode.
Few simple util apps, disk cleaner, clipboard manager. Worked pretty well.
Had better results than using xcode's built in ai extension.
Raycast -> Glaze AirTable -> Lovable Competitor Retool -> Lovable Competitor
Even those early in the journey are converging towards coding.
1. macOS and Windows require installation of Xcode and Visual Studio respectively, and if in Apple's case you kinda can install these tools headlessly and choose to install only the "build tools" package, Microsoft's creature is gonna daze and confuse you with a crap-ton of checkboxes and no easy "just install whatever is minimally needed to compile my code" button, and I don't recall if there is way to install build tools on Windows through terminal.
2. what is going to be distributed? source code itself or actual binaries? and what will the security model of Glaze store be? same as extensions, "everything is open-source and undergoes Raycast's and community review"?
3. Glaze is going to come to Windows and Linux, if we trust the Q&A section at the end. what will Glaze build upon? separate frameworks and languages for each platform or something multi-platform [1] like Tauri or Kotlin Multiplatform? or are you going to copy the Raycast extension model - just run Node, expose some platform integration, and parse React render trees through "Glaze Runtime"? I've been working on a bug in Vicinae [2][3], and I've seen this model in action. it's very hard to make it perform well, but all it takes to achieve native look and feel is to just map React render trees to whatever system component OS offers. (in Vicinae's case, it's Qt. bet that it's done with SwiftUI on macOS and WinUI 3 on Windows.)
[1]: there is a difference between "cross-platform" and "multi-platform". "cross-platform" means "I behave equally across platforms and have no awareness of native look and feel" (e.g. Electron, Unity, Flutter), while "multi-platform" means "I can adapt across platforms to the degree you need" (e.g. C/C++, Rust, KMP)
that's would be Electron app, but without unneeded bloat
Having antigravity is useful because Gemini 3.1 is pretty good at generating UI sugar. Claude 4.6 Opus provides nothing to write home about. Their shadcn looksmaxxing hasn't generalized to writing good desktop UIs.
Raycast's only edge here seems to be the fact that they are obviously very good at Mac app development and probably have impeccable skills/documentation for building them.
Taking a step back, it's pretty clear that Raycast is angling for an Apple acquisition here with this play. If I'm Apple, the reason to buy a product/team like this is a no-brainer.
I do have prior experience developing for iOS but that was pre-swift.
I am worried this is the start of them trying to diversify their product offering because revenue has stalled in the core Raycast product and VC demands more returns. I don't want to be jaded, but history teaches me to be. Here's hoping that Raycast itself is still a focus for the company.
My first thought was, "So, Replit and ilk?", seems they expected that comparison:
> How is Glaze different from Lovable, Replit, or v0?
> Those tools build for the browser. Glaze builds for your desktop. That means your apps can access your file system, your camera, keyboard shortcuts, menu bar integration, and background processes. Things a web app can’t do. It’s a different category entirely.
Pretty sure modern web apps can do all of those (sans menu bar). (If anything they do background processes better since you can send a very long task off to a server and shut off your computer, come back later and pick up where you left off.)
Also, as others mentioned, this just seems like Claude Code with extra steps, unless they managed to nail some sort of design standard enforcement they feel is better than what most people can get out of it.
The quick publishing is kind of nice, but it immediately made me think it would be more interesting to have a way to quickly remix other people's creations, similar to the Figma Community tab: you can take someone else's work, break it apart to see how it works, then tweak it how you want it.
ie the annoying way that LLMs interact with users
Glaze is in private beta. Join the waitlist and we’ll let you in as soon as we can. Existing Raycast users will get priority access. We’re also hosting in-person events, and those who attend will get early access. Keep an eye on our Luma page.
No. You describe what you want in plain language and Glaze builds it. If something isn’t right, just talk to it and change it. And if you do know how to code, you’ll feel right at home shaping things further.
Those tools build for the browser. Glaze builds for your desktop. That means your apps can access your file system, keyboard shortcuts, menu bar integration, background processes, and deeper integration with your OS. Your data stays on your machine, not on someone else’s server. It’s a different category entirely.
Anything that comes to mind. Internal tools for your team, personal utilities, menu bar apps, workflow automations, or just quick one-off things that make your life easier. If you can describe it, Glaze can build it.
Yes. Glaze apps run on your Mac, so they can connect to your APIs, local files, and hardware. You can hook into the tools you already use, pull in AI models, or connect to any service with an API.
Both. Glaze has a free tier with daily credits to build your first apps, and you can explore and use everything on the public store. Paid plans start at $20/month with a bigger bundle of monthly credits, and teams can create a private team store to share apps with colleagues. You can also top up with one-off credit packs anytime. We’ll share more details on pricing closer to the public launch.
Mac to start. Windows and Linux will come down the road.
Raycast recently made a Windows version. So perhaps they aren't as Apple-centric.
No kidding, although I think Apple would only be interested if it uses SwiftUI. (The marketing page doesn't say. Raycast itself uses React + Node for extensions, but its React components render to native widgets.)
A better replacement to iStat Menus.
A local-only voice to text whisper.cpp transcriber I can globally use while holding ctrl-semicolon.
A menubar app that manages blocky and can easily turn it off or change dns.
A tool like hammerspoon but I configure it via nix-darwin and it has no cruft.
All of these are apps that use 30MB memory and are better than the apps they replace, and I can make changes any time I want. That's far better than using someone else's software and giving it privileged access to my machine.
Also, perhaps the best point is that so much software is junk that is obsoleted by someone with better UX intuitions even if they are vibe-coding it. Being written by hand by an engineer means basically nothing when it comes to "is this a good app?" Which is why product-minded people are the biggest winners in the new AI era.
Desktop software is nowhere near good enough to consider random usecases "already done". Not that glaze looks particularly special, but there's so many improvements the desktop experience begs for.
An easy to use cross-platform GUI builder for one. Even something as basic as a calendar app doesn't have a clear obvious winner today.
Vibe apps are different. They do exactly what you want, exactly the way you want it done. No more downloading an app that is mysteriously 180MB and requires watching a youtube video to learn how to make it change your background every 5 minutes to different dog pictures.
In the DOS days, I would have whipped them up in BASIC. This was standard practice for PC users who were not "software engineers" by trade.
The complication of PCs over the past 30+ years have robbed regular users of this ability.
Tools like this close the gap, and that's awesome.
We need more of you. Not more electron slop.
Well yeah, isn’t that criticism we’ve had every LLM wrapper for years now? “Show me the prompt!” But that doesn’t mean these types of products are useless.
I think it's fair to say that's a benefit of web apps over native apps in many cases. But for the kind of business app use case they're talking about, it's also a tradeoff. I can imagine a lot of business apps where you don't want to send the data to the server of a Replit etc. and doing all the processing local is a benefit.
If you're on Chrome and give them permission, or stuff them into Electron and friends, they can. The workflow isn't as smooth as with native applications, though.
On the other hand, the web browser does protect you from some of the risks this essentially "trust me bro" curl2bash-as-a-service product inherently comes with.
Not everything is possible yet and sure more complex things need more prompts but you’ll be surprised what Glaze is capable of already. It’s day one…
I'm not using the Xcode integration and so there's still some rough parts where build errors show up in Xcode and I then have to paste them into my Terminal.
When you are used to backend work...it's kinda fun to see an app come to life and run on your phone though.
This looks like a highly specialized tool for desktop that actually works. I watch the demo and I am assuming the apps are actually made with some kind of technology a la Tauri, or Electron, thus making the apps cross-platform.
I don't think we are anywhere near a tool like this for native, but that's a lost battle anyway.
My feeling is that it's intended for a less-technical audience than Claude Code.
On the other hand it is kind of the perfect name for Yet Another AI Website Maker (YAAWM?).
Kids these days are always saying "snaoƨd" and "foʀaṅr"
Is it a real synth or license-washed Vital/Surge?
Can you one-shot a raycast alternative with this? This'll be the real test.
The FAQ was light on technical details. But I am someone keen to read all the technical details :)
More seriously, what do you believe your moat is here?
I hope it's not a lost battle, tbh. I was hoping with AI & Vibe Coding we'd see sort of a resurgence of native first desktop apps, but so far it's just all been a continuation of the web app & web tech hegemony.
Maybe not for Windows as their native GUI story is a lost cause now, but for sure macOS and I had hopes of it leading to a renaissance of desktop linux apps in GTK instead of electron, but that (the Linux) community seems to be hostile to any AI generated code at all for now.
> First you said all you want is love and affection / Let me be your angel and I'll be your protection / … / Thought I was a donut, you tried to glaze me
> I ain’t gotta tell you I had a Dunkin' Donuts fetish back in the day. I used to get a dozen donuts every day, man. So it was one of the things that was on my mind
> This was never the case for the desktop tools I mentioned.
I'd be curious how well Claude Code works for a native Swift app on macOS, if that's the platform you're on. I've found it extremely good at iOS apps so my guess is it would be equally good at building a native macOS app with the same stack.
There is no way a human wrote that page. If Lucas Gray even exists, he should probably reconsider that last image, and his life more generally.
> seems to be hostile to any AI generated code at all for now.
Because the majority of vibe-coded apps are low effort.
It works, but feels really janky and messy.
I had one very annoying bug with file export API where extra view on export window would appear with a delay. No matter what I tried it didn't manage to fix it. Instead it would go on to try and completely rewrite whole file export class in various ways... which still didn't work as it claimed it would. Ended up fixing it manually by caching instance view locally.
Native, especially on Windows and macOS, have been the domain of proprietary apps there's not much code outside of tutorials online to train a model on outside of official documentation.
I made a couple of small menu bar utilities for mac using Gemini, and it was OK at best. Kept wanting to use deprecated APIs, but with a lot of handholding I got them to work.
Would be neat to see Apple put out their own model specifically for Swift/SwiftUI