After WWDC26, Reselecting What an Indie Should Build Right Now
Now that on-device AI is free for small developers, the premises of app planning have quietly shifted. Here are five questions to choose what to build with Rork at the concept stage.
Routing inference on-device first and escaping to the cloud only when it's worth it, in a Rork app
Build a tiered, fallback-based inference router in a Rork (Expo) app: cache to on-device to Private Cloud Compute to a remote API (Claude/Gemini). Working TypeScript covering budgets, timeouts, caching, and image routing.
A Three-Layer AI Cost Design for Rork Apps After Apple Opened Foundation Models to Small Developers
Apple now offers Foundation Models on Private Cloud Compute at no charge for developers under two million first downloads. Here is a three-layer cost architecture for Rork apps, with a simulation script and working bridge code.
Gemma 4 for App Development: On-Device AI on the Cutting Edge
Learn how to integrate Google's Gemma 4 E2B and E4B models into iOS and Android apps for on-device AI. Covers privacy, offline capability, low latency, and practical code for real app use cases.