Google AI Edge Gallery vs ReadOS

AI Edge Gallery is the premier destination for running the world’s most powerful open-source Large Language Models (LLMs) on your mobile device. Experience high-performance Generative AI directly on your hardware - fully offline, private, and lightning-fast. Now Featuring: EmbeddingGemma 2 & XR Language Teacher This update brings official support for the newly released EmbeddingGemma 2 model for multimodal semantic search, alongside interactive vocabulary games and on-device speech in XR Language Teacher and AI Chat - all running 100% on your device. Core Features - XR Language Teacher: Point your camera at the world around you to learn new languages in real time, turn saved vocabulary photos into editable sticker flashcards with Magic touch, and practice in the Vocab Popper and Buddy Runner study games. - Agent Skills: Transform your LLM from a conversationalist into a proactive assistant. Use the Agent Skills tile to augment model capabilities with tools like Wikipedia for fact-grounding, interactive maps, and rich visual summary cards. You can even load modular skills from a URL or browse community contributions on GitHub Discussions. - AI Chat with Thinking Mode & Voice: Engage in fluid, multi-turn conversations using text or on-device speech-to-text and text-to-speech with live word-level highlighting. Toggle Thinking Mode on supported models (starting with the Gemma 4 family) to see the model’s step-by-step reasoning process. - Instant Media Search: Explore your photo library (or built-in sample media) with fast, search-as-you-type natural language queries and image-to-image similarity matching with zero cloud roundtrips. - Video Moment Finder: Pinpoint exact moments inside videos using natural language descriptions. Jump straight to highlighted timestamps on an interactive timeline, trim clips, and save or export your favorite moments. - Ask Image: Use multimodal power to identify objects, solve visual puzzles, or get detailed descriptions using your device’s camera or photo gallery. - Audio Scribe: Transcribe and translate voice recordings into text in real time using high-efficiency on-device language models. - Prompt Lab: A dedicated workspace to test different prompts and single-turn use cases with granular control over model parameters like temperature and top-k. - Mobile Actions: Unlock offline device controls and automated tasks powered entirely by a finetune of FunctionGemma 270M. - Tiny Garden: A fun, experimental mini-game that uses natural language to plant and harvest a virtual garden using a finetune of FunctionGemma 270M. - Model Management & Benchmark: Gallery is a flexible sandbox for a wide variety of open-source models. Easily download models from the list or load your own custom models. Manage your model library effortlessly and run benchmark tests to understand exactly how each model performs on your specific hardware. - 100% On-Device Privacy: All model inferences happen directly on your device hardware. No internet is required, ensuring total privacy for your prompts, images, and sensitive data. Built for the Community AI Edge Gallery is an open-source project designed for the developer community and AI enthusiasts alike. Explore our example features, contribute your own skills, and help shape the future of the on-device agent ecosystem. Check out the source code on GitHub: https://github.com/google-ai-edge/gallery Note: This app is in active development. Performance is dependent on your device's hardware (CPU/GPU). For support or feedback, contact us at google-ai-edge-gallery-android-feedback@google.com.

ReadOS is an all-in-one, desktop-class AI agent workspace for iPad, built around the place serious work often begins: reading. Open a PDF, collect research, inspect evidence, create a report, analyze data, build office files, and continue the task without rebuilding context across separate apps. ReadOS keeps source materials, reading position, selections, files, and project context connected so you can move from understanding to creating. READ WITH CONTEXT • Open PDFs, EPUBs, Markdown, images, local audio and video files, and common office files. • Navigate document structure and page references when the source provides them. • Annotate PDFs, take notes, organize tabs, and export annotated documents. • Build knowledge maps and visual explanations connected to source material. RESEARCH WITH READEX Readex is the AI agent inside ReadOS. When you choose to share content with it, Readex can work with the current document, selected passages, attachments, webpage context, and files in your workspace. Use Readex to: • Summarize and compare source material. • Develop study guides, research plans, and structured notes. • Trace an answer back to relevant pages and context. • Work across multiple files while keeping the research question visible. CREATE, AUTOMATE, AND DELIVER With ReadOS Pro, Readex can help: • Create and edit documents, spreadsheets, and presentations. • Analyze data with Python and JavaScript. • Build charts, tables, interactive visualizations, and knowledge maps. • Browse the web, inspect pages, collect relevant context, and carry out browser tasks. • Transcribe and analyze local audio and video files, extract useful frames, and continue from a playback position. • Carry out multi-step and long-running tasks across available files and tools, with progress you can review and stop. FREE AND PRO ReadOS Free includes library management, local file opening and playback, PDF annotation, notes, navigation, tabs, workspaces, and annotated-PDF export. ReadOS Pro unlocks Readex and advanced AI-assisted work, including browser automation, creation and editing tools, code and data analysis, document and media understanding, and multi-step or long-running tasks. ReadOS Pro is available through Apple In-App Purchase as an auto-renewing annual subscription or a one-time lifetime purchase. ReadOS Pro also requires a supported AI provider account or compatible API connection. Provider subscriptions, usage quotas, and model or API fees are separate and are not included with ReadOS Pro. Availability and results can vary by source format, selected provider or model, network access, and permissions. Start with what you are reading. Keep the context. Build what comes next. TERMS OF USE ReadOS uses Apple's Standard Terms of Use (EULA): https://www.apple.com/legal/internet-services/itunes/dev/stdeula/