A Mac app that turns plain English into real apps — built and stored on your machine, not someone else's servers. Your code, your GitHub, your own AI at cost. No marked-up credits, no lock-in. Free, no sign-up. macOS (Apple Silicon), Windows on the roadmap.
Hey PH We're Baptiste & Samuel, and next week we're launching Capacity Desktop a free Mac app that turns plain English into real apps, built and stored on your machine.
The bet everyone tells us is wrong: move away from credits system. You plug in your own Claude / GPT / Open Router key and pay your provider at cost. Our take is that you feel the credits system is unfair, you never know what a failed fix loop just cost you, and you feel the tool profits from your retries.
Hey Product Hunt 👋
We're Baptiste & Samuel — two product people who spent the last year obsessing over one question: why does "AI builds your app" have to mean "your app lives in someone else's browser tab"?
We love what Lovable and Bolt made possible. We just wanted the magic without the rent: no marked-up AI credits, no code held hostage in a cloud workspace, no export button as an afterthought.
So we built Capacity — a free Mac app that turns plain English into real web, mobile, desktop and game apps, built and stored on your machine.
• 🎨 Start from 80+ hand-picked design templates — or import a repo you already have
• 🧠 Bring your own AI: Claude, GPT, Gemini, Grok, Kimi, DeepSeek… your key, billed at cost, with a built-in spend dashboard
• ⏪ Every change becomes a restorable version — if the AI takes a wrong turn, roll back in one click, and nothing is ever lost
• 🚀 Publish tab: connect GitHub + Vercel, preflight your env vars, deploy in one click and watch it go live
• 🛠️ Zero terminal: Capacity detects the dev tools each project needs (Git, Node…) and installs them for you
• 📁 Your project is a normal folder and git repo — open it in any editor, hand it to any developer, walk away anytime
There are just two of us, and we've sweated the details most builders skip — the restore timeline, the empty states, the way a deploy feels. We wanted a Mac app that feels like a Mac app.
The honest bits:
• macOS (Apple Silicon) only for now. Windows and Linux are on the roadmap — tell us in the comments which one you need.
• You bring your own AI key. That's the philosophy: we sell a tool, we don't resell tokens.
• Free while in beta. When we charge later, the plan is a one-time license — never a subscription, never credit markups.
⬇️ Try it now: capacity.so/desktop — free, no sign-up, building in under a minute.
We're both here all day. Tell us what breaks, what's missing, and what you'd build first 🙏
@baboo77777 The local-first part is what caught my eye. What made you go desktop instead of another browser tab? I've built Mac-only myself and the tradeoff I keep running into is that you lose everyone who isn't on a Mac, but you gain things the browser simply can't do.
@julian_belting for people to own their stack. Online platforms are great, but the vendor lock-in is real. This app is part of a major effort for people to develop complex apps without relying on someone else infra
@chrismessina I'll have a look at Glaze, I really like Raycast products. Desktop apps will be electron first for simplicity but the beauty of templates is we can integrate native ones in the future
Report
Solo founder here, no dev background — I shipped a native iOS + Android app built almost entirely with AI, so I love watching this category mature. My biggest lesson: generating code was never the hard part, verifying it was (two app store rejections taught me to check the build artifact, not the source folder). How does Capacity help users trust what got built beyond "it looks right in the preview"? Cheers, Gero
@nevertoolateoriginal That is a great question the answer is at the heart of the philosophy of this desktop application. As you mentioned, developing websites, a mobile app, or a game is not just about code, but also quality. You have to ensure that your application is scalable to bring in more users, secure to prevent any breach, and in your case, meet the quality standards of app stores.
This is a lot to think about, especially when you're not a tech. Our goal is to make software development simple for non-tech people to handle this tedious yet necessary process. So we develop and integrate AI workflows inside the application that prove their efficiency. Today with Capacity desktop, you can vibe code, spec code, break down your work in development sprints, etc. No technical knowledge required to implement features. In the near future, we plan to help users develop mobile apps, desktop apps, games, and more. So we'll keep on integrating these battle-tested AI workflows. And handling app store requests would be part of it.
By the way, we rolled out a roadmap within the application so any users can submit feature requests, bug reports, and share with others.
Report
@baboo77777 Thanks Baptiste — "tedious yet necessary" sums up my last two months better than I could have. Glad to hear store-readiness is on the roadmap; that's exactly where non-tech builders like me hit the wall. Good luck with the launch! Cheers, Gero
Capacity
StepGrab
@baboo77777 The local-first part is what caught my eye. What made you go desktop instead of another browser tab? I've built Mac-only myself and the tradeoff I keep running into is that you lose everyone who isn't on a Mac, but you gain things the browser simply can't do.
Capacity
@julian_belting for people to own their stack. Online platforms are great, but the vendor lock-in is real. This app is part of a major effort for people to develop complex apps without relying on someone else infra
Osaurus
This seems like a competitor to @Glaze by Raycast but it seems to focus on web-distributed apps, at least from the website.
Are the desktop apps native, or Electron?
Capacity
@chrismessina I'll have a look at Glaze, I really like Raycast products. Desktop apps will be electron first for simplicity but the beauty of templates is we can integrate native ones in the future
Solo founder here, no dev background — I shipped a native iOS + Android app built almost entirely with AI, so I love watching this category mature. My biggest lesson: generating code was never the hard part, verifying it was (two app store rejections taught me to check the build artifact, not the source folder). How does Capacity help users trust what got built beyond "it looks right in the preview"? Cheers, Gero
Capacity
@nevertoolateoriginal That is a great question the answer is at the heart of the philosophy of this desktop application. As you mentioned, developing websites, a mobile app, or a game is not just about code, but also quality. You have to ensure that your application is scalable to bring in more users, secure to prevent any breach, and in your case, meet the quality standards of app stores.
This is a lot to think about, especially when you're not a tech. Our goal is to make software development simple for non-tech people to handle this tedious yet necessary process. So we develop and integrate AI workflows inside the application that prove their efficiency. Today with Capacity desktop, you can vibe code, spec code, break down your work in development sprints, etc. No technical knowledge required to implement features. In the near future, we plan to help users develop mobile apps, desktop apps, games, and more. So we'll keep on integrating these battle-tested AI workflows. And handling app store requests would be part of it.
By the way, we rolled out a roadmap within the application so any users can submit feature requests, bug reports, and share with others.
@baboo77777 Thanks Baptiste — "tedious yet necessary" sums up my last two months better than I could have. Glad to hear store-readiness is on the roadmap; that's exactly where non-tech builders like me hit the wall. Good luck with the launch! Cheers, Gero