OmniClassify vs Helmrig Agents

Transform your iPhone into a powerful machine learning lab. OmniClassify is the complete iOS toolkit for training, deploying, and running AI models entirely on-device. Your data never leaves your device—complete privacy, zero cloud uploads. COMPLETE ML WORKFLOW Import datasets from local folders, videos, Parquet files, or download directly from HuggingFace. Train custom models using CreateML, ONNX, or Vision Transformer architectures. Run real-time inference on images, videos, and live camera feed. Process everything locally with zero data transmission. KEY FEATURES Dataset Management Import from local folders, videos, Parquet files, or HuggingFace (Premium). DICOM medical imaging support. Automatic class detection, train/validation splits, and comprehensive statistics. Model Training (Premium) Train classification and segmentation models with CreateML, ONNX, or ViT. Custom training iterations (unlimited), advanced preprocessing, and progress monitoring. Model Import CoreML and ONNX model support. HuggingFace model downloads with automatic server-side conversion. Thousands of pre-trained models available. Image Classification Batch processing with unlimited capacity (Premium). Multi-model inference, confidence scores, detailed metrics, and result export (Premium). Object Detection YOLO model support with real-time bounding boxes. Multi-object detection, confidence thresholds, and live camera capabilities. Image Segmentation Semantic segmentation with pixel-level masks. Visual overlays and export capabilities (Premium). Video Processing Frame-by-frame AI analysis with custom intervals. Export annotated videos with bounding boxes, labels, and segmentation overlays. Live Camera Inference Real-time classification, detection, and segmentation using iPhone camera. Instant on-device results, works completely offline. DICOM Medical Imaging Full DICOM file support with multi-frame extraction, header reading, and integration with classification/detection models. HuggingFace Integration (Premium) Browse and download thousands of datasets and models. Automatic ONNX/CoreML conversion. Search by task type and license. Advanced Analytics (Premium) Confusion matrices, training metrics, validation curves. Export to JSON, CSV, PDF formats. Automation & Triggers Detection-based automations, Shortcuts app integration, custom notifications, URL opening, and haptic feedback. 100% ON-DEVICE PROCESSING Everything happens locally on your iPhone. Training, inference, analysis, and storage—all without internet or cloud servers. Your images, models, and data remain completely private. No uploads, no tracking, no data collection. PRIVACY FIRST All ML processing on-device. No cloud uploads. Complete offline functionality. No analytics or tracking. HIPAA-compliant workflows for medical imaging. PERFECT FOR ML researchers, data scientists, medical imaging professionals, computer vision developers, students, and hobbyists experimenting with AI. PREMIUM FEATURES Unlock unlimited datasets, unlimited models, unlimited inference, advanced training, exports, HuggingFace integration, and comprehensive analytics. Free tier includes 3 datasets, 2 models, and unlimited inference—perfect for getting started. Start building and deploying AI models on your iPhone today. Complete privacy. Complete control. Complete ML toolkit. Terms of Use: https://www.apple.com/legal/internet-services/itunes/dev/stdeula/ Privacy Policy: https://omniclassify.com/privacy

Helmrig is a remote development client for iPhone. It pairs with helmrig-server running on your own laptop and gives you the AI coding agents, terminal, and filesystem of that machine — over an end-to-end encrypted tunnel. FEATURES • AI coding agents — run Claude Code or Codex on your laptop. Tell the agent what to do in plain language; it reads files, runs commands, and edits code on your machine. The app shows the output, diffs of any proposed changes, and approval prompts before anything is applied. You bring your own subscription or API keys; Helmrig doesn't sell or proxy AI access. • Attach files — pull any file from your laptop into the agent conversation in one tap, so the agent has exactly the context it needs. • Terminal — full PTY shell on your laptop with ANSI colors and resize. Use whatever you've installed: bash, zsh, fish, tmux, vim, nano, htop. • Files — browse and view the laptop filesystem with syntax highlighting for common languages. • Multi-project — switch between active projects in one tap; each project keeps its own terminal session and AI thread. HOW IT WORKS 1. Install the server on your laptop: npx helmrig@latest 2. Open Helmrig on iPhone, scan the QR code shown in the server. 3. The pairing key is generated locally on your devices and never leaves them. After pairing, phone and laptop talk directly over LAN or NAT-traversal when possible. When direct connection fails, the encrypted tunnel falls back through one of our regional relays. Relays forward opaque ciphertext only — they cannot decrypt anything. REQUIREMENTS • Laptop: macOS or Linux with Node.js 20+ • iPhone: iOS 17+ PRIVACY No third-party SDKs. No analytics. No crash reporting. Helmrig servers never see code, files, terminal output, or AI conversations. Full policy at helmrig.app/privacy.html CONTACT hi@helmrig.dev Privacy Policy: https://www.helmrig.app/privacy.html Terms of Use (EULA): https://www.helmrig.app/terms.html