Interceptor | Network Debugger vs CoreAI Zoo

Interceptor helps you inspect HTTPS traffic for selected hosts on your own iPhone or iPad. View saved request and response headers, cookies, and available JSON bodies, and inspect supported service tokens. The app uses an iOS VPN configuration to direct selected hosts through a proxy running on your device. It does not provide a remote VPN server, change your public IP address, or protect public Wi-Fi traffic. HTTPS inspection requires you to install and trust a locally generated certificate authority certificate in iOS Settings. At startup, Interceptor explains what it can access and requires agreement to the current data-use notice before you can access the main interface. Agreement alone does not start capture, install a certificate or VPN configuration, or request notification permission. Captured traffic can contain sensitive cookies, authentication tokens, account identifiers, and request or response content. Use it only with accounts and devices you are authorized to inspect. Capture is limited by the app's configured hosts; service changes or certificate restrictions may prevent capture. New capture records are stored in the app's local shared storage. New certificates, private keys, and saved tokens use Keychain items with iCloud Keychain synchronization disabled. Interceptor does not upload captured data to a developer-operated server, sell it, use it for advertising, or automatically share it with third parties. Requests still reach their original destination services. Data you choose to copy, earlier iCloud Keychain copies, and operating-system backups are separate from this local capture flow. You can review the notice and withdraw consent in Settings → Data Use & Consent. Withdrawal stops the VPN, disables automatic reconnection and clears capture notifications, and returns to the required consent screen until you agree again. Withdrawal does not erase saved records, tokens, certificates, or private keys, or remove an installed certificate profile. Clear saved request history from Home. Optional local notifications announce captured records without including tokens or captured headers and bodies in the notification.

CoreAI Zoo puts the open-weight AI model zoo on your iPhone, iPad and Mac. Pick a model, download it once, and run it entirely on your device. No account, no server, and nothing you type, say or photograph ever leaves the device. CHAT Stream answers from open language models such as Qwen3, Gemma, LFM2.5, Granite and Mistral, from 0.6B to 30B+ parameters depending on your device's memory. Vision-language models (Qwen3-VL, MiniCPM-V, LFM2.5-VL) answer questions about your photos. VISION Ask questions about an image, read text with on-device OCR, and describe what the camera sees. AUDIO Transcribe speech with Whisper large-v3-turbo, Parakeet and Qwen3-ASR. Talk to an audio-understanding model, generate speech with Kokoro and VoxCPM, and try on-device music generation. CAMERA Live depth estimation, object detection (YOLOX, RF-DETR), action recognition and super-resolution on the camera feed. TOOLS Experimental models such as diffusion-based language models. BENCH Measure load time, tokens per second and memory for any chat model on your own hardware. HOW IT WORKS Every model runs through Core ML on Apple silicon. Weights are downloaded from the Hugging Face Hub on first use over HTTPS, then cached, so the app works offline afterwards. One model is resident at a time to stay within memory limits. New models arrive through a live catalog without an app update. GETTING STARTED Start with Qwen3-0.6B (454 MB) for the fastest first run. Larger models state the free space and memory they need; a recent iPhone Pro or an Apple silicon Mac runs the mid-size ones comfortably. Model weights follow their own licenses, listed on each model's Hugging Face page. The app itself is BSD-3-Clause and part of the open CoreAI model zoo. Report issues and request models at github.com/john-rocky/coreai-model-zoo.