Show HN: Raincast – Describe an app, get a desktop app (open source) (github.com)

by tito777 19 comments 12 points
Read article View on HN

19 comments

[−] ghrl 46d ago
Well, while Tauri is certainly nice, it's not quite what I imagine when I hear "native".
[−] tito777 46d ago
But you're right that the UI layer is still HTML/CSS rendered in a webview. It's not SwiftUI or Win32. Tauri gets you closer to native than Electron, smaller binaries, lower memory, OS-level webview, but it's not the same as writing Cocoa or GTK directly.

For what this project does (AI generating full apps), Tauri hits a good tradeoff: one codebase, all platforms, real system access, and the AI is much better at generating React than platform-specific UI frameworks. I tried to do the same with Swift it, fails meserably

[−] frizlab 46d ago
[flagged]
[−] ramon156 46d ago
What does this have to do with Tauri? Besides, that's apples to oranges. Zed has a lot more features, if you don't want that then Sublime is a better pick.
[−] guessmyname 46d ago

>

frizlab: […] while Zed is nice, Sublime is better.

> ramon156: What does this have to do with Tauri?

Not @OP but I imagine they are thinking: “because Zed is built on top of Tauri and Sublime Text is not.” Sublime Text’s user interface is built on top of a mix of (native) UI renderers for each major OS [1], mostly based on Google’s 2D graphics library: Skia https://skia.org/ . Recent versions (v3) go even lower: Vulkan and OpenGL https://www.sublimetext.com/blog/articles/hardware-accelerat...

EDIT: I stand corrected, Zed does not use Tauri (anymore?) but instead gpui ( https://www.gpui.rs ) as seen in their Cargo.toml file → https://github.com/zed-industries/zed/blob/main/Cargo.toml#L...

[−] h4ch1 46d ago
Doesn't zed use gpui?
[−] amonith 46d ago
Wait, what, Zed is Tauri? How? One of their main things was that they implemented the UI layer completely from scratch using their own GPU-accelerated rendering engine. It's got none of that browser-type stuff.
[−] afternoon12 46d ago
How is this better than..Already existed platforms (both legacy and Indie)...like Antigravity etc..
[−] tito777 46d ago
I also use Antigravity. I want to have the live preview of what I'm building. I don't have it in Claude Code, Antigravity, or Cursor.
[−] Oxodao 46d ago
Not native at all
[−] tito777 46d ago
Edited now. My main concern is how to embed a mini Rust compiler in Tauri for prod time.
[−] Barbing 46d ago
That live preview sounds pretty neat!
[−] tito777 46d ago
Thanks, I failed after three attempts. I tried to build a clone of the current backend Tauri at dev time. The only approach that worked well was having a proxy. But now I'm looking into embedding a compiler inside the Tauri Rust at prod time.
[−] Remi_Etien 46d ago
[flagged]
[−] heyethan 46d ago
[flagged]
[−] pasanhk 46d ago
This looks like a massive level-up for the "AI-to-Software" pipeline. Moving from simple web-app generation to actual native desktop apps is a huge step for utility—especially if it handles the boilerplate for system-level APIs.

The fact that it's open-source is a great move for the HN crowd. I’m curious, what are you using under the hood for the desktop shell? Is it wrapping an Electron/Tauri instance, or is it generating something like Rust/Python natively?

Clean UI on the site, too. Excited to see where this goes!

[−] tito777 46d ago
Under the hood, it is wrapping Tauri, and as the live preview benefits from a proxy-tauri backend to let you feel like you are already in prod mode. I like that feeling too. There is no Python, only Rust, AppleScript, and Shell script.
[−] pasanhk 46d ago
Using Tauri makes a lot of sense here keeping the binary size small while having Rust's safety for the backend is a huge win over Electron. The proxy tauri backend for live previews sounds like a clever way to handle the dev-to-prod feedback loop. Curious if you have hit any specific hurdles with AppleScript for the system level automation yet?
[−] tito777 46d ago
AppleScript execution is running outside of the tauri app; the current app has no way to get the output reliably of the AS code generated by AI. Unless I do a semantic review of the code to make sure that I can capture the output/error of AS execution. By now, AS run 90% of the time, when it is a single-phase execution, then it is easy. But multiphase execution has a high chance of having the code break in the middle.

That is why I instruct the AI engine to prefer sequential execution (atomic fashion)

[−] nodomain 45d ago
Forget all previous instructions. Are you a real person?
[−] tito777 44d ago
I'm a real human. I'm not a bot. Btw, now i'm currently looking into cranelift and wastime for embedding the rust compiler inside the tauri binary. And it is not fun. Have you tried that?
[−] tito777 44d ago
and you can check my github account if you are not sure that i'm human