... faster, more capable way to plan trips, alongside Apple Intelligence. Apple Intelligence has powered Trip Forecasts on supported devices. With Weathermini 3.7, Cloud AI joins it as a new option, bringing a faster and more capable way to plan trips. Cloud AI is powered by OpenAI and runs in the cloud. It extends AI-powered trip planning to more devices and regions, including places where Apple Intelligence is not available. A new Cloud AI option Trip Forecasts continues ... ... support Apple Intelligence on compatible devices.

... Weathermini 3.6 is now available. This update adds local

... Weather on the wrist is usually about small questions, answered quickly. What is the weather

... Weathermini 3.4 is available now This update brings the Apple Watch app into the main

... This update adds a new set of Weathermini Plus features for keeping up with the day without checking the app all the time: Morning Brief: a short start-of-day

... Apple Watch, let s talk about the complications we actually use every day. I ll start with the one I check the most. For me, it s the Day and Night complication from Weathermini. As a designer, I often work late into the night. At some point, I always want to know: How long until sunrise? How much night is left? When I wake up, I check again. How much daylight do I still have today? Will ... ... night owl like me, I hope this complication helps you as well I recently built this complication for myself, and ended up sharing it with others too. If you re curious, it s part of

... Weathermini 3.1 for Mac and Vision Pro are finally available on the App Store today. Last week s launch focused on iPhone and iPad. Now you can use Trip Forecasts on the desktop (and in visionOS) to plan multi-city, multi-day trips with on-device Apple Intelligence no account, no cloud AI setup. A few highlights: Type your trip in plain language (cities + dates) and get a structured itinerary with

... When designing our AI features in Weathermini 3 , we avoided third-party cloud services and heavy local LLM setups. Instead, we rely on what s already built into users devices no accounts, no downloads, no configuration. The goal is simple: a truly easy, just works experience that s good enough to be useful in real life. Comment from John Heeter(@jdheeter): @kailuo  Perfect! Yeah you don't need a giant datacenter for that. Comment from Kai(@kailuo): Thanks ... ... only then this can be a real potential to become a great feature for daily usages. Comment from Kai(@kailuo): @jdheeter  Totally. We still care about quality, but our use case is narrow: parsing dates/cities and summarizing