# Lumen: Knowledge Browser — Browse. Remember. Recall. > A private, on-device browser that builds a searchable knowledge base from your reading. (iPhone/iPad app by Daniel Kosukhin.) - Source: https://appshunter.io/ios/app/lumen-knowledge-browser/id6762682475 (this page in markdown: same URL + `.md`) - Developer: [Daniel Kosukhin](https://appshunter.io/developer/1852657475) - Category: Productivity, Utilities - Price: Free - Rating: 5.00/5 from 4 App Store ratings · 1 written reviews indexed - Age rating: 17+ - Requires: iOS 18.0 · 28 MB - Languages: English - Released: 2026-05-05 - Data updated: 2026-06-28 - Monetization: free - User reviews in markdown: https://appshunter.io/ios/app/lumen-knowledge-browser/id6762682475/reviews.md ## What is Lumen? Lumen is a browser with a memory. Most browsers forget the second you close a tab. Lumen does not. As you read, it quietly builds a personal knowledge base from the pages you actually engage with, and then lets you ask questions about any of it in plain English, answered by an AI model that runs entirely on your device. Nothing you read, nothing you ask, and nothing Lumen learns about you ever leaves your phone. WHAT IT DOES Lumen reads along with you. It distinguishes between pages you genuinely read and pages you opened and swiped away, and it extracts the meaningful content from the ones that stuck. That content gets summarized, embedded, and organized into a searchable knowledge base, all on-device. Later, when you want to find something, you do not have to dig through history or remember which tab it was in. You just ask: "What did I read about sourdough starters last week?" "Summarize that article about the new M-series chips." "What were the main arguments in that piece I read on Tuesday?" Every answer cites the pages it came from, so you can jump straight back to the source. AUTO-ORGANIZED Your reading sorts itself into a clean hierarchy: Topics, Websites, and Pages. Each level carries its own AI-generated summary, so you can scan what you have been learning at a glance. No tagging, no folders to maintain. Lumen handles it in the background. PRIVATE BY DEFAULT Lumen has no server. There is quite literally nothing to send. On-device LLM: a quantized Llama 3.2 model runs locally through Apple's MLX framework. Local SQLite storage: your reading history, summaries, and embeddings never leave the device. Built-in privacy: tracker blocking, third-party cookie blocking, and fingerprint resistance. Secure: HTTPS-only by default, with mixed-content blocking. No strings attached: no accounts, no sync, no telemetry, no ads. The AI weights download once on first launch (~700 MB). After that, everything works fully offline: browsing, reading, asking, answering. BUILT FOR iOS Lumen is written from scratch in Swift and SwiftUI, designed specifically for iPhone and iPad. It uses Apple's own frameworks wherever it can: NLEmbedding for semantic search, WKWebView for browsing, SQLite with FTS5 for full-text queries, and MLX Swift for on-device inference. Zero third-party trackers. Zero external services. WHO IT'S FOR While most browsers treat the web as a feed to scroll past, Lumen treats it as a library worth keeping. If you read a lot online and constantly think "I know I saw something about this recently but I cannot find it again," Lumen is for you. Researchers, students, writers, developers, and lifelong learners. You do not need to change how you browse. Browse normally, and Lumen takes care of the rest. REQUIREMENTS iOS 18 or later. iPhone with Apple Silicon recommended for the fastest on-device AI performance. ## Key features - On-device AI knowledge base - Plain English questioning - Automatic content organization - Private and offline browsing - Tracker blocking - Source citation for answers ## Recent user reviews (1 of 1) All indexed reviews: https://appshunter.io/ios/app/lumen-knowledge-browser/id6762682475/reviews.md ### 5/5 — Fast and efficient *2026-05-25* Fast and efficient. Pleasant to use! ## Frequently asked questions about Lumen ### Does Lumen have ads? No, Lumen is completely ad-free. The app is built with a focus on privacy and user experience, ensuring no advertisements disrupt your browsing or knowledge recall. ### What are the system requirements for Lumen? Lumen requires iOS 18 or later. An iPhone with Apple Silicon is recommended for optimal on-device AI performance. The AI model weights download once on first launch, approximately 700 MB. ### How does Lumen ensure user privacy? Lumen prioritizes privacy by running its AI model entirely on your device, with no data leaving your phone. It also includes built-in privacy features like tracker blocking, third-party cookie blocking, and fingerprint resistance. ### Can I use Lumen offline? Yes, Lumen works fully offline after the initial AI model download. This includes browsing, reading, asking questions, and receiving answers, making it a reliable tool even without an internet connection. ### How does Lumen organize my reading? Lumen automatically organizes your reading into a hierarchy of Topics, Websites, and Pages. Each level features an AI-generated summary, allowing you to quickly scan and understand what you've been learning without manual tagging or folder management. ### What is the age rating for Lumen? Lumen has an age rating of 17+. This is likely due to the advanced AI capabilities and the nature of content that users might engage with and store. ### How often is Lumen updated? Lumen was last updated on June 19, 2026, with version 1.4.1. This indicates a relatively frequent update schedule, suggesting ongoing development and improvements. ### What devices does Lumen support? Lumen is designed for iOS devices and currently supports iPhones. It is built using Apple's native frameworks for a seamless experience on the platform. ## Version history (last 4 releases) ### 1.4.1 — 2026-06-19 - Answers about your saved pages come up faster - AI replies now stay steady on screen as it's being written - Search results pages won't get saved anymore, so your folders stay tidy - Fixed going back through your Topics, Websites, and Pages - Fixed the dates and grouping on your reading history - Made the app start up more reliably and run a bit smoother ### 1.4.0 — 2026-05-27 - Ask a question and Lumen now reaches for the saved pages that actually match it, so answers line up better with what you were reading. - Made a typo in your question? Lumen quietly fixes it for you, so a small slip won't throw off the answer. - When there's more than one thing to say, answers come back as a short bulleted list instead of one long paragraph. - Your saved pages sort into topics more sensibly, and there's a new Anime category. - The "thinking" indicator now sits right above the text box while Lumen works, instead of drifting elsewhere on screen. ### 1.3.3 — 2026-05-16 - Tab switching is smoother. No more flicker when jumping between tabs. - The URL bar now resizes with a clean, fluid animation instead of snapping. - Tapping Go always plays the slide-in animation. - Keyboard pops up faster the first time you tap the URL bar. - Lumen opens quicker, meaning your history loads in the background instead of blocking launch. - Animations across the app now share the same feel, so motion looks consistent everywhere. - The URL pill looks cleaner and softer on light-colored websites. ### 1.2.2 — 2026-05-05 No release notes. ## More apps by Daniel Kosukhin - [Speedrail](https://appshunter.io/ios/app/speedrail/id6755214601) All apps by Daniel Kosukhin: https://appshunter.io/developer/1852657475 --- *Data collected daily from the US App Store and indexed by [AppsHunter](https://appshunter.io/). User reviews are verbatim App Store reviews. Ratings, prices and chart positions refresh continuously; this snapshot is from 2026-06-28.*