Lovable Vibe-Coding App Launches on iOS, Android
Lovable has just launched its official mobile app on iOS and Android, allowing users to build full-stack web and mobile apps using AI and natural language (via TechCrunch).
Whether you are a professional developer looking to prototype quickly or a non-technical founder with a fresh idea, you can now build, edit, and ship software directly from your smartphone.
The term vibe coding gained popularity after being coined by AI researcher Andrej Karpathy. It describes a style of development where you don’t write line-by-line code. Instead, you describe the vibe or the functionality of what you want in plain English. The AI then handles the heavy lifting, generating the frontend, setting up the database, and managing the authentication.
Lovable has been at the forefront of this shift. Their platform uses advanced large language models, including early integrations with GPT-5.5 and Claude 4.7, to interpret user prompts and turn them into working code. By bringing this technology to mobile, Lovable is leaning into the idea that “English is the hottest new programming language.”
The new mobile app isn’t just a simplified viewer, it is a portable version of the full Lovable engine. Users can start a project by typing a description or even uploading a screenshot of a design they like. From there, the AI builds a working prototype in real-time.
One of the standout features of the mobile release is the Visual Edits mode. This allows users to tap on elements of their app and tell the AI to change them, shifting a layout, changing a colour scheme, or adding a new button, without ever seeing a line of code. For those who want more control, the app still supports two-way sync with GitHub, meaning the code produced is real and can be exported or refined by professional teams later.
While the app is powerful, it is still part of an evolving ecosystem. Early testers have noted that while the AI is incredibly fast, complex logic still requires a bit of back-and-forth vibe refining to get exactly right. However, with the integration of the latest models, these iterations are becoming smoother and more accurate.
Want to see more of our stories on Google?
P.S. Want to keep this site truly independent? Support us by buying us a beer, treating us to a coffee, or shopping through Amazon here. Links in this post are affiliate links, so we earn a tiny commission at no charge to you. Thanks for supporting independent Canadian media!
