Code Analyzer vs Vision Detector

For the latest, full-featured Code Analyzer experience, download Code Analyzer from the Mac App Store. Code Analyzer turns opaque software into a workspace you can navigate. Analyze APK, JAR, and JMOD archives, inspect Mach-O and ELF binaries and font files, and move naturally from package structure to readable code, functions, symbols, assembly, and raw bytes. Code Analyzer combines an APK analyzer, JAR/JMOD decompiler, native disassembler, font glyph viewer, bytecode viewer, and hex viewer in one focused iPhone and iPad workspace. There is no command-line setup and nothing to upload. PACKAGE AND BYTECODE ANALYSIS • Open APK packages and browse files, compiled classes, decoded resources, and manifest data • Decompile supported class files from JAR and JMOD archives into readable high-level output • Fall back to low-level bytecode automatically when a higher-level result is unavailable • Follow nested ZIP, APK, and JAR containers in place without manually unpacking them NATIVE BINARY ANALYSIS • Inspect Mach-O universal binaries, dynamic libraries, application bundles, and frameworks • Explore ELF executables and shared libraries across multiple CPU architectures • Browse architecture slices, headers, segments, sections, symbols, and discovered functions • Explore ELF and Mach-O machine code in a continuous, architecture-aware disassembly view • Jump directly to discovered functions and symbols, including useful results from stripped binaries FIND THE SIGNAL • Open TrueType, OpenType, and font collections in a searchable glyph viewer with metadata and outline inspection • Use Quick Open to find files, classes, methods, resources, and symbols with responsive fuzzy matching • Filter Project Explorer by filename to find files quickly • Search raw data as text or hex and step through every match • Jump to decimal or hexadecimal offsets without losing context • Copy any byte selection as hex, text, or Base64 • Keep syntax highlighting and symbol outlines beside the content you are reading ANALYZE ON THE GO • Native SwiftUI interface adapted for iPhone and iPad • Responsive background processing for large, multi-part files • Runs entirely offline, so your files stay on your device Built for developers, security professionals, and students who need clear answers from software they are authorized to inspect.

Vision Detector is an AI image analysis tool that supports CoreML machine learning models, multi-modal Large Language Models, and on-device Apple Intelligence. Choose the mode that best fits your use case. You can choose one of the following image input sources: - Live video by built-in camera - Still image by the built-in camera - Photo Library - Files (iCloud, Google Drive, Dropbox, etc) For live video inputs, continuous inference is performed on the camera feed. However, the frame rate and other parameters depend on the device. # Notification Center Vision Detector can call Notification Center for predefined conditions. Broadcasting notifications send notification to your all Apple devices signed in with the same Apple Account. ## CoreML Mode Vision Detector locally executes CoreML models using Apple’s Vision framework. Before using this mode, prepare a machine learning model in the CoreML format (.mlmodel or .mlpackage) using Create ML. Import ML models via iClpoud or AirDrop. Vision Detector supports the following types of CoreML models: - Image classification - Object detection - Style transfer ## Vision LLM Mode Vision Detector can use multi-modal large language model (LLMs). Define what to do with prompt as following samples: - If the image is screen shot, answer the name software - Call notification when you see a cat - Count number of persons in the image, and notify when it changes ## Apple Intelligence mode Available with iOS 27 on selected devices (iPhone 17 Pro, iPhone Air, etc). The images are completely processed on your device locally with your prompt.