I built a small iOS app that performs text rewriting and summarization entirely on-device using Apple’s Foundation Models (iOS 18+).

Most AI writing tools rely on cloud APIs. That introduces API costs, privacy concerns, and infrastructure overhead. I wanted to explore what it looks like to build a useful AI writing utility with:

- no backend - no external APIs - no server costs - fully offline support

The app can rewrite text in different tones, generate summaries, extract key points, and produce short post-ready output. Everything runs locally on supported devices.

Why I built it

I was curious whether on-device language models are “good enough” for everyday writing tasks like cleaning up emails, summarizing articles, or restructuring notes.

I also wanted to test a different economics model: since inference runs locally, marginal cost per user is essentially zero. That allowed me to avoid subscriptions and instead use a simple free tier with an optional one-time unlock.

Technical notes

- SwiftUI main app - Share Extension for system-wide text processing - Apple FoundationModels for local inference - No networking layer

Some interesting constraints compared to cloud LLMs: - Smaller context window - More sensitive prompt design - Device-dependent performance - Latency perception is critical in extensions

On-device models are obviously less capable than large cloud models, but for constrained rewriting tasks they are surprisingly usable.

If anyone is experimenting with FoundationModels or on-device inference, I’d be curious how you’re handling prompt structure and long input segmentation.

App Store link: https://apps.apple.com/us/app/rewrite-text-ai-writing-tool/i...

Happy to answer technical questions.

Comments URL: https://news.ycombinator.com/item?id=47162985

Points: 1

# Comments: 0

Thanks, I'll use it and print it at home.

I built a small macOS menu bar utility after running into the same daily annoyance for years: bookmarks are still tied to the browser you're using.

As a developer I often switch between Safari, Chrome, Arc, Brave and Edge depending on testing, debugging extensions, or isolating workflows. Every browser keeps its own independent bookmark list, and syncing them (or importing/exporting) never really works well. I kept losing structure or duplicating folders.

Why I built it I needed a simple way to access the same set of bookmarks no matter which browser I was in. Instead of syncing browser-to-browser or relying on cloud extensions, I thought a menu bar layer on top of all browsers would be more reliable and reduce cognitive load.

Platform & Tech - macOS menu bar app - Built with SwiftUI + SwiftData - Uses system APIs to open URLs in specific browsers - All data is stored locally - No accounts, no network usage

If you're curious Here’s the App Store link: https://apps.apple.com/us/app/bookmark-bar-browser-hub/id675...

Happy to answer technical questions or hear ideas from others who work with multiple browsers daily (profiling, testing setups, automation, etc.).

Comments URL: https://news.ycombinator.com/item?id=46087034

Points: 1

# Comments: 0

Thanks Otto

I’ve been experimenting with Apple’s new on-device Foundation Models (iOS 18 / macOS Sequoia) and built a small tool around them: AppReview AI, a Mac + iPad app to analyze App Store reviews privately and offline.

The motivation was simple: as an indie developer, reading hundreds of reviews from competitor apps was slow, noisy, and hard to extract signal from. Existing tools rely on cloud processing, API keys, or external servers. I wanted something lightweight and private that used Apple’s new local AI instead.

What it does - Summarizes reviews using Apple’s on-device models - Extracts sentiment, recurring issues, bugs, and feature requests - Shows per-country ratings to detect market differences - Displays basic estimated downloads and revenue (SensorTower public data) - Syncs selected apps and analyses through iCloud

All AI processing stays on-device. No external servers, no accounts, no OpenAI key.

Why I built it I wrote a recent article on Apple Foundation Models and was surprised how far the local models can go with the right prompts. This project was a way to test how practical on-device analysis could be in a real use case for developers.

Free tier The app has a small free tier (1 app + 3 AI analyses) so anyone can try it without registration.

If you’re curious, here’s the link: https://apps.apple.com/lu/app/appreview-ai-review-analyzer/i...

I’d love feedback, criticism, or ideas for what to analyze next (keywords, rankings, crashes, changelogs, etc.). Happy to answer technical questions about the on-device AI integration as well.

Comments URL: https://news.ycombinator.com/item?id=45989976

Points: 2

# Comments: 0

Otherwise, keep it the same. Thanks

I'll test it more, congratulations.

Do you have any other features in mind? Thanks

TimeCalc is a small utility I’ve been maintaining for years. I originally built it to help pilots log and calculate flight hours without the hassle of spreadsheets or clunky online tools.

Over time, it evolved into a simple and accurate time calculator that lets you add, subtract, and compare hours, minutes, and seconds — or even calculate the exact difference between two dates.

This new version was completely rebuilt for iOS 26 and macOS, with: - A clean, native interface - iCloud sync across devices - No ads, no accounts, no third-party servers - Accurate operations on hours, minutes, seconds, and dates

It’s designed to do one thing well: make time math fast and reliable. Data stays in your iCloud account, and everything works offline.

I’d love feedback especially from anyone who’s built or used similar tools. Are there features or workflows you’d expect from a native time calculator that could make it better?

Thanks for checking it out. App Store link: https://apps.apple.com/us/app/time-calc-time-calculator/id12...

Comments URL: https://news.ycombinator.com/item?id=45512976

Points: 1

# Comments: 0

I'm a developer who got tired of jumping between tabs just to run everyday tasks — decoding Base64, converting timestamps, generating UUIDs, etc.

So I built a small macOS menu bar app called CodeSwissKnife Bar. It gives you quick access to essential dev tools, all running 100% offline.

No accounts, no cloud, no tracking — just useful utilities where you need them.

Right now it includes: - Base64 / URL / HTML encoder & decoder - UUID and color converters - Unix timestamp ↔ Date - Text base conversions (binary / decimal / hex) - A simple daily Scrum journal - One-click feedback shortcut

It’s not trying to replace IDEs or big tools — I just wanted to remove friction from tiny, repetitive dev actions.

Happy to share it here and get your thoughts! https://www.codeswissknife.com/codeswissknifebar.html

Comments URL: https://news.ycombinator.com/item?id=44755491

Points: 1

# Comments: 0

iPantry is a simple app I built to solve a recurring problem in my home: forgetting what we already had in the pantry or fridge, buying duplicates, and letting food expire.

With a busy schedule and a shared household, it became easy to lose track of what was available, especially when grocery shopping was split among family members. We'd end up with multiple milk cartons or expired pasta tucked away in the back of the cupboard.

I couldn’t find an app that was both easy to use and shareable with native iOS tools. Most were either too complex or locked features behind account systems or external sync.

So I made iPantry: - Track products with quantities and expiration dates - Get low stock and expiry alerts - Export lists or share items via iCloud and Apple Reminders - All data stays in your iCloud account, synced across devices - No registration or third-party service required

It’s a small tool built for clarity and speed. I'd love to hear your thoughts, ideas, or critique. Thanks for taking a look.

Comments URL: https://news.ycombinator.com/item?id=44568541

Points: 1

# Comments: 3