eCopy vs Gadeon

eCopy for iPhone and iPad is the mobile companion app for eCopy 2.1. Browse, search, organize, and copy your clipboard history on the go. You can also save content you just copied on your iPhone or iPad, then continue using it later on your Mac or other devices. Version 2.1 adds manual text items, image text recognition, OCR search, and system translation, making screenshots, references, and reusable text easier to find and reuse. === Core Features === Cross-Device Clipboard History Sync clipboard history across Mac, iPhone, and iPad with iCloud using the same Apple ID. Your data stays on your devices and in your private iCloud database. It is not sent to our servers. Browse and Search Quickly browse clipboard history on mobile devices. Search by keyword, recognized image text, and notes. Filter by favorites, content type, source app, time range, custom groups, and items with notes. Save Current Clipboard After copying text, images, links, or colors on iPhone or iPad, you can save the current clipboard content to eCopy and keep it searchable and organized. Create Text Items Add a text record manually for frequently used addresses, account notes, support replies, code snippets, and temporary references. Empty text is ignored, and duplicate text updates the existing record. Image Text Recognition Images and image files can be recognized in the background after they are saved. Recognized text can be searched, viewed, copied, and sent to system translation. System Translation On supported system versions, text content and recognized text can use Apple system translation to show a translation without relying on third-party translation services. Three-Column iPad Layout On iPad, eCopy uses a large-screen layout with groups on the left, history in the middle, and detail preview on the right. Groups, Favorites, Pins, and Notes Organize items with groups, keep frequent content in favorites, pin important records, and add notes for easier lookup later. Deleting a favorited or pinned item asks for confirmation to help prevent mistakes. Rich Content Support eCopy supports common clipboard content including text, images, files, links, and colors, with clean list and detail previews. === Platform Role === The iPhone and iPad app focuses on browsing, searching, organizing, copying, translating, and saving current clipboard content. The Mac app remains the full productivity workflow with the menu bar panel, keyboard shortcuts, automatic paste, context menu actions, and paste queue. === Privacy === All clipboard data is stored only on your devices and in your private iCloud database. eCopy does not upload your data to third-party servers, contains no ads, no tracking, and no analytics telemetry.

Gadeon runs Qwen3.5 and QwenPaw hybrid language models entirely on your device's Apple Neural Engine, using Core ML as its only framework dependency. There's no C, no Python, and no cloud calls: every token is generated locally, keeping your conversations private. Under the hood, these models mix Gated DeltaNet recurrent layers with a smaller number of attention layers. Gadeon compiles that hybrid architecture directly onto the Neural Engine's dataflow accelerator, so both prompt processing (prefill) and token generation (decode) run on-chip instead of falling back to the CPU or GPU. On an Apple Silicon Mac, prefill measures roughly 2 to 2.4 times faster and about 4.4 times more energy-efficient per token than a Metal GPU baseline, while leaving the GPU free for other work. Conversations in Gadeon are append-only: each turn extends the model's fixed-size recurrent state instead of re-processing the entire chat history, so response latency doesn't grow as a conversation gets longer. The app can also roll back to an earlier point in a conversation, dropping reasoning traces or replaying tool calls in a clean form without reprocessing everything from scratch. For ternary-quantized models, Gadeon switches to a pure-Swift Metal GPU backend behind the same session and tokenizer interface, so both compute paths feel identical from the chat UI. Gadeon is a proof of concept for bringing Gated DeltaNet hybrid models to the Neural Engine through Core ML - built to explore what's possible on Apple's own silicon.