Lovable launches mobile vibe-coding app on iOS and Android after Apple's App Store restrictions
Lovable has launched its vibe-coding app on iOS and Android app stores, allowing users to build web apps through voice or text prompts on mobile devices. The launch comes after Apple blocked updates to competitors like Replit and Vibecode, forcing vibe-coding apps to preview generated code in web browsers rather than within the app itself.
Lovable launches mobile vibe-coding app on iOS and Android after Apple's App Store restrictions
Lovable has launched its no-code AI app builder on iOS and Android, becoming one of the first vibe-coding platforms to navigate Apple's recent App Store restrictions. The mobile app allows users to generate web applications through voice or text prompts directly from their phones.
Key features
The mobile app enables users to:
- Build web apps through AI prompts while on the go
- Let the AI agent run autonomously after receiving initial input
- Switch between desktop and mobile to continue projects
- Receive notifications when builds are ready for review
Apple's vibe-coding restrictions
Lovable's launch follows Apple's enforcement of developer guidelines that prohibited vibe-coding apps from downloading new code or changing functionality within the app itself. Apple temporarily blocked updates to Replit and Vibecode, and removed Anything from the App Store before it returned after compliance changes earlier this month.
According to Apple, apps that download code or alter functionality present security risks and prevent the App Review team from properly vetting applications during the approval process. Apple clarified it wasn't banning vibe-coding apps entirely, but would not allow in-app execution of generated code.
Compliance approach
To comply with Apple's rules, Lovable's mobile app generates "working websites or web apps" that run in web browsers rather than within the host application. This mirrors the approach taken by other vibe-coding apps that have successfully returned to the App Store.
The app is now available on both Apple's App Store and Google's Play Store.
What this means
Apple's restrictions have established a clear boundary for AI coding tools on mobile: they can generate code, but must preview and run it externally. This limitation may reduce the seamless experience these apps promised but keeps them viable on iOS. Lovable's successful launch suggests the vibe-coding category can adapt to platform restrictions, though the requirement to preview apps in browsers adds friction to the mobile development workflow. The availability on both iOS and Android gives Lovable a distribution advantage over competitors still working through Apple's approval process.
Related Articles
Apple announces Siri AI overhaul with Google Gemini-derived model at WWDC 2026
Apple announced a redesigned Siri AI at WWDC 2026, powered by a custom Gemini-derived model from Google that runs on Apple's Private Cloud Compute infrastructure. The company also introduced Core AI, a new library that integrates with PyTorch to enable developers to deploy models on Apple hardware.
Apple waives cloud API fees for developers under 2M downloads using Private Cloud Compute
Apple announced it will waive cloud API fees for developers with fewer than 2 million first-time App Store downloads who use its Foundation Models running in Private Cloud Compute. The company also expanded its Foundation Models framework to include image input and support for server models from third-party cloud providers.
Google: 3.5 million users tested Gemini for Home assistant, speaker launch next week
Google announced that 3.5 million users have tested its Gemini for Home assistant since the early access program launched in October 2025. The company delivered over 2,500 bug fixes and 50 major feature updates based on user feedback, and is teasing a Google Home Speaker launch for next week.
Anthropic Reverses Policy That Silently Throttled AI Researchers Using Claude
Anthropic has reversed a controversial policy that would have made Claude Fable and Mythos models silently throttle responses to researchers working on frontier AI development. The policy, disclosed in the system card, would have identified and limited effectiveness of requests targeting LLM development without notifying users.
Comments
Loading...