Modelence Mobile Builder - Build mobile apps by chatting with AI

Now Modelence App Builder has support for creating native mobile apps. Just like web apps, describe what you want and get a fully working mobile app, working in sync with your Modelence auth and backend.

Add a comment

Replies

Best

Nice! How does this fit into an existing project, or is it mainly designed for building apps from scratch? Congrats and good luck on the launch!

 Thanks, and appreciate the kind words! Right now Modelence is mainly for apps you are building from scratch, since it builds your app on the Modelence framework. If your product already runs on another stack, you can still move it over, but that means recreating the app, the DB, and the architecture on Modelence, so it is closer to a port than a plug in.

Where it really pays off is when you are building a serious, production-ready app: the framework and cloud are made to get you to production fast (deployment, DB, monitoring, observability all handled).

Looks very cool! Will have to give this a try. Great that the code is fully available and not hidden.

Thanks! Owning your code and database matters a lot to us, so we make sure you keep full control of your app: code, db, deployment, monitoring, observability, all of it.

Love the structure of your website - it made me interested even not being the developer. "Build real apps, not prototypes" is a strong positioning line!
I'm curious though, do you find that non-technical founders also try to use Modelence, or is it really purely a developer tool?"

 thank you, I am very glad you liked it! To your question: our users are mostly non-technical and semi-technical founders, not pure developers; that is exactly who we build Modelence for. You get to a real production-ready app without being an engineer, while still owning the code if you want to go deeper.

 Got it, thank you! That's really interesting! I'm a designer with a few app ideas but very little understanding of how development actually works - things like how a product ends up in the App Store, what the process looks like from zero. Do you have any educational content for people at that level? Blog posts, guides, anything that walks complete beginners through the basics? I feel like there's a real opportunity to turn curious non-technical people into users by meeting them even earlier in the journey.

 Thanks, good point. Inside the product we already guide you through the steps that stay manual, like signing the build before publishing and submitting to TestFlight, the App Store, and Google Play, so you are not stuck at those points.

But you are right that we do not yet have beginner content explaining the whole journey from zero. That is a good idea for both web and mobile deployment, and something we will work on. Thanks for the idea 🙌

 great point and yes we will consider adding more educational content on how everything works. But in general the AI chat is already playing that role - all general knowledge like how products end up in App Store is already just one prompt away, and whether you're using the Modelence AI chat or Cursor / ChatGPT / Claude, they will all be able to explain that as needed.

How much control do I actually have over the generated code if I want to swap out the auth provider later?

 you fully own the generated code and can do whatever you want with it. You can extend it to use any other auth providers as well.

How does the generated code handle custom domain setup and ongoing maintenance when you want to swap out the built-in auth for something like Clerk or Auth0 later?

 You should not swap out the built-in auth with Clerk and Auth0, it defeats the whole purpose. Clerk and Auth0 own your users and charge by number of users. Modelence is based on an open-source framework where you own your users, in your own database, without having to do anything extra. Connecting external auth services is exactly the kind of a thing that breaks in production for AI-built apps.

Pulled it up and was surprised the auth and database bits were already wired together, no extra setup needed. Editing the generated code actually felt like normal code rather than some locked-in template.

 Exactly, that is the idea. Modelence is a batteries-included framework, so auth, database, email, and a lot more come already wired together out of the box. That cuts down the time to a production-ready app and keeps the quality high, since you are not stitching together services yourself. And glad the generated code felt like normal code, that is the part we are proud of 🙌

code ownership is what sold me, being able to inspect and edit after generation instead of being locked into a black box

 Owning your code and database matters a lot to us, so we make sure you keep full control of your app: code, db, deployment, monitoring, observability, all of it.

 I think one of the biggest things that AI has changed is that people want way more ownership than before. Everyone has access to AI and powerful tools now, so owning things is even more important for all.

the fact that you actually own the generated code instead of being trapped in some walled garden is such a rare move for this category of tools, really appreciate that you made that the default rather than an upsell

 thanks, glad you like it! We did it because the framework & its cloud platform is our main product, rather than the AI builder, which is typically the main product for most other app builders.

Scaffolded a quick side project over the weekend and the auth plus database wiring came through on the first try, which saved me a ton of setup time. The generated code was actually readable enough to tweak without fighting it.

 Thank you for the feedback!

How does the generated code actually work under the hood - do I get a full repo I can self-host anywhere, or am I locked into running it on your infra?

 you get a full repo you can self-host anywhere, although we don't recommend self-hosting because Modelence Cloud is exclusively built for Modelence apps and already takes care of everything you would have to do yourself otherwise.