Explore On-Device AI

Intelligence Catalog is an interactive knowledge base and playground for on-device AI — discover, learn, and experience real models running through curated demos and educational content, right on your iPhone, iPad, and Mac.

Learn Explore Run Understand
Why Intelligence Catalog

A hands-on tour of Apple's on-device AI

Designed to feel like a mix of Apple sample code, Apple Developer Documentation, and an interactive AI museum.

Browse Real Models

Explore a curated catalog of Apple's Core ML and Vision models.

Run Live Demos

Try each model yourself with your own photos and text.

Learn How It Works

See inputs, outputs, and how-to-use tips for every model.

100% On-Device

Every demo runs locally — nothing you provide ever leaves your device.

See It In Action

From first launch to live results

A real capture of the app's first-launch experience, next to the Gallery and Model Detail screens you'll land on right after.

Intelligence Catalog onboarding screen
OnboardingActual app screenshot
Intelligence Catalog Gallery screen
GalleryActual app screenshot
Intelligence Catalog Model Detail screen for FastViT
Model DetailActual app screenshot
The Catalog

36 tasks. Four Apple frameworks. One app.

Real, bundled Core ML models alongside native Vision and Natural Language tasks and Apple Intelligence–powered Foundation Models — spanning image and text understanding.

36
Total Tasks
10
Bundled Core ML Models
19
Native Vision Tasks
4
Frameworks

Core ML

FastViT, MobileNetV2, ResNet-50, YOLOv3, DETR, DeepLabv3, Depth Anything V2, MNIST, and more.

Vision

Face, barcode, animal & pose detection, text recognition, saliency, document scanning, and more.

Foundation Models

Apple Intelligence–powered summarization and structured data extraction.

Natural Language

Sentiment analysis, tokenization, language ID, named entity recognition, and part-of-speech tagging.

Explore tasks across the catalog

Image Classification Object Detection Semantic Segmentation Depth Estimation Drawing Classification Text Recognition (OCR) Face Detection Barcode Detection Animal Detection Person Segmentation Pose Detection Saliency Rectangle Detection Contour Detection Horizon Detection Document Recognition Image Aesthetics Scoring Question Answering Summarization Structured Extraction Sentiment Analysis Tokenization Language Identification Named Entity Recognition Part-of-Speech Tagging
New in 1.1

Learn the concepts, not just the demo

A dedicated Learn tab pairs every topic with a Practical track (real code — Keras next to Apple's own on-device equivalent) and a Theory track (how it actually works, with a diagram where one helps) — then quizzes you on it.

8
Learn Topics
400
Quiz Questions
2
Tracks per Topic
6
Hand-Drawn Diagrams
9:41●●● 📶 🔋
Learn
👍
Sentiment Analysis
NLP
Image Classification
Vision
Object Detection
Detection
Summarization
Generative AI
Learn HubIllustration, not an actual screenshot
9:41●●● 📶 🔋
👍
Sentiment Analysis
NLP · Text Classification
TheoryPractical
✓ Similar-context words get similar embeddings.
✓ Bag-of-words ignores order; self-attention preserves it.
Take the Quiz
Topic DetailIllustration, not an actual screenshot

Real Code, Both Sides

Every Practical write-up ends with a Keras/Python snippet next to Apple's actual on-device API call — syntax-highlighted, matching what the app's own demo really runs.

Diagrams Where They Help

Hand-drawn, theme-aware diagrams — a single neuron, a CNN pipeline, self-attention, IoU, BIO tagging, precision/recall — for the topics where a picture beats a paragraph.

A Quiz That Doesn't Repeat

Each topic draws a fresh, randomized set from a 50-question bank every session, and a local Progress panel tracks your score by topic — no account, no server.

"An interactive playground for Apple's on-device AI — learn, explore, run, and understand, all in one native app."

Built natively in SwiftUI for iOS, iPadOS & Mac · Fully on-device · Dark mode supported