AgentOS vs Lumen

AgentOS transforms your iPhone into a powerful AI Agent host. Use your own key with a supported cloud provider, or choose an on-device model that needs no API key, and let your AI agent answer messages, search the web, manage files, and connect to external services. KEY FEATURES ◆ 10 Messaging Channels Receive and respond to messages across Telegram, Discord, LINE, WhatsApp, Slack, Teams, Matrix, Signal, and built-in chat — all handled by a single AI agent. Voice channel supported. ◆ Agentic AI Loop With supported cloud or on-device models, AgentOS runs a full tool-use loop: analyze your request, call the right tools, and keep going until the task is done. Up to 50 tool calls per turn. ◆ 165+ Built-in Tools - Web search & content extraction - Camera capture & image analysis - Speech recognition & text-to-speech - File management (save, read, search, organize) - Google Drive & Gmail integration - GitHub operations (10 tools) - Calendar & contacts management - Photo library search & analysis - Weather, navigation, music, health data - HomeKit smart home control - Bluetooth BLE & NFC interaction - Cloud browser automation (Browserbase) - Cloud code execution (E2B) - AI image generation (DALL-E) - Voice synthesis (ElevenLabs TTS) - Market data tracking (TW/US stocks, crypto) ◆ 30 Specialized Agents Personal assistant, GitHub agent (plan→code→review), market agent (TW/US/crypto), Threads publisher, schedule manager, photo manager, automation agent, cloud dev agent, Notion/Trello project management, channel hub monitor, and more. ◆ 26 Skills Customizable skill profiles that focus the agent on specific tasks. Each skill configures available tools and MCP servers. Supports skill creation wizard and import/export. ◆ Always-On Background Operation (Premium) AgentOS Premium adds background relay for connected channels and scheduled tasks, including silent push notification wake-up. ◆ MCP Integration Connect to any MCP (Model Context Protocol) server via Streamable HTTP. Add custom servers in Settings. ◆ Activity Journal Every interaction is logged. Browse daily activity, filter by type, and generate AI-powered daily summaries. ◆ File Manager Organized file storage with categorized folders. Import files, share via iOS share sheet, and sync to Google Drive. ◆ iOS Widgets & Siri Shortcuts Home screen widgets for real-time agent status and market data. 6 voice-activated Siri shortcuts. ◆ Semantic Memory System AI automatically remembers important conversation context, learning across sessions. Vector search for similar memories. PRIVACY FIRST - All API keys stored in iOS Keychain (encrypted) - No data leaves your phone except to your configured AI provider - Per-channel user ID allowlists (closed access) - You own your API key — no intermediary SUPPORTED AI PROVIDERS - Anthropic (Claude Opus 4.6 / Sonnet 4.6 / Haiku 4.5) - z.ai (GLM-5 / GLM-4.7 + Claude proxy) - OpenRouter (200+ models) - Gemini (Google AI) - MLX local inference (offline use) REQUIREMENTS - Cloud AI uses your own provider API key; supported on-device models require no key - iOS 17.0 or later AGENTOS PREMIUM (OPTIONAL) Premium includes 12 AI-callable market-data tools, background relay, and 5 GB storage (500 MB without Premium). The Market dashboard remains available without Premium. Market timing and availability vary by source. Cloud AI provider usage is billed separately and is not included. Monthly auto-renewable subscription; the price is shown before purchase. Cancel anytime. AgentOS is built with pure Swift and SwiftUI. No tracking, no ads — use your own cloud API key or a supported on-device model. Terms of Use (EULA): https://agent.lucas-futures.com/terms Privacy Policy: https://agent.lucas-futures.com/privacy

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.