DoCube vs Open Minis

DoCube is a multi-format reader and personal knowledge base built for deep reading. Bring PDFs, EPUBs, local videos, web snapshots, Markdown, and organized scanned documents into one library. Annotate, link, search, translate, export, and review while you read or watch. Your materials are not merely stored—they gradually become knowledge you can retrieve, connect, and remember. 【Deep Reading Across Formats】 DoCube supports PDFs, EPUBs, local videos, offline webpages, Markdown, and parsed documents. Whether you work with research papers, ebooks, web articles, course videos, lectures, interviews, or your own Markdown notes, you can read, watch, and manage them together in DoCube. 【Deep Study for Video】 Import local videos and study courses, lectures, and interviews as deeply as documents. DoCube can read embedded subtitles and, on supported devices, generate subtitles for videos that do not have them. Search subtitles; switch between original, translated, and bilingual views; annotate subtitles; use chapter outlines, playback speeds, and A/B looping. Open a search result, annotation, or chapter to return to the exact moment, turning video into knowledge you can retrieve, connect, and review. 【Multi-Tab Reading】 Open multiple documents and videos in tabs, just like a browser, and switch quickly between materials. Read a paper, compare references, watch a course, or return to where you left off without losing context. 【Annotations and Notes in Context】 Use highlights, underlines, strikethroughs, quotations, links, and Markdown notes directly on source text or at a precise location in video subtitles. Your thinking stays connected to its context. 【Link Materials Together】 DoCube can link an annotation in a document or video to a precise location in another resource. Connect scattered chapters, paragraphs, webpages, video clips, and notes into your own paths through knowledge. 【Search What You Have Read and Watched】 Search not only titles and body text, but also video subtitles, highlights, quotations, links, notes, and cards. Anything you have read, watched, marked, or written can help you find the right material again. 【Keep Reading in Other Languages】 Translate selected text while reading. Some document types support full-document translation and translated exports, while videos support subtitle translation and original, translated, or bilingual display. Read foreign papers, webpages, ebooks, and course videos without constantly switching tools. 【From Annotation to Review】 Turn important content from documents and videos into review cards. Flip cards, mask cards, and review plans bring what you have read and watched back at the right time, instead of letting it disappear after you finish. 【Export and Sync】 Export document content and translations to common formats, including bilingual versions. DoCube is available on iPhone, iPad, and Mac, with iCloud sync and local Wi-Fi transfer. Ideal for: - People who read research papers and professional materials - Learners organizing PDFs, EPUBs, webpages, Markdown, and videos - People who study long-term with course, lecture, and interview videos - Deep readers who want annotations, notes, and review in one loop - Anyone building a personal knowledge base instead of merely collecting files The free version manages up to 5 documents and lets you experience the core reading and knowledge-management workflow. Upgrade to Pro to remove the document limit and build an unrestricted personal library.

Minis — Local-First On-Device AI Agent Minis is a local-first, on-device AI agent that goes beyond chat. All your data stays on your iPhone — nothing is uploaded to a server by default. Running locally means lower latency and stronger privacy, while the agent still takes real action: browsing the web, accessing your health data, managing your schedule, controlling your smart home, and automating complex tasks. Local-First AI Agent Unlike cloud-only chatbots, Minis runs directly on your device and keeps your data there. The agent executes multi-step tasks autonomously, using tools and native iOS frameworks to get things done — not just answer questions, and not just relay everything to the cloud. Multi-Model, Your Choice Bring your own API key. Choose from leading AI providers: • Anthropic Claude • OpenAI GPT • Google Gemini • DeepSeek • Kimi (Moonshot AI) • OpenRouter • Any OpenAI-compatible endpoint Deep iOS Integration The agent accesses Apple frameworks natively: • HealthKit — steps, heart rate, sleep, workouts, SpO₂ • Calendar & Reminders — create events, check availability, manage tasks • HomeKit — control lights, switches, scenes, and smart accessories • Photos — search, organize, and export from your library • Location & Maps — current location, directions, nearby POIs • Vision — OCR text recognition, object detection, barcode scanning • Speech — real-time transcription and text-to-speech • Weather — current conditions, hourly and daily forecasts Built-in Web Browser Navigate pages, take screenshots, extract content, fill forms, and interact with websites — all driven by the AI agent in the background. Skills System Import or create custom AI skills to extend the agent's capabilities. Share skills with others or build your own for specialized workflows. Persistent Memory The agent remembers your preferences, project context, and recurring patterns across sessions — building a personalized assistant that improves over time, all stored locally on your device. Siri Shortcuts Automate AI tasks with Siri and the Shortcuts app. Send prompts with file attachments, wait for results, and chain into complex workflows — all hands-free. Privacy by Design Your API keys and data stay on-device. Fine-grained permission controls let you decide exactly which personal data the agent can access. No account required. No data collected.