OpenIntelligence vs Solair AI

Ask a question about your own PDFs, contracts, lecture recordings or code, and get an answer with the exact passage it came from. Nothing you import leaves your device unless you allow it. Free to start, no account, no API key. OpenIntelligence reads what you import and answers in plain language, with citations you can tap to see where each claim came from. When your files don't contain the answer, it says so instead of guessing. ANSWERS START IN YOUR FILES Not in a chatbot's imagination. OpenIntelligence searches your library first, pulls the exact passages that matter, and only then writes, using Apple's on-device Apple Intelligence models. Requires an Apple Intelligence-capable device: iPhone 15 Pro or later, or an M1-or-later iPad or Mac, on iOS/iPadOS/macOS 26. Your device already had the intelligence. This gives it your knowledge, and rules of evidence. WHAT YOU CAN DO - Summarize long documents, recordings, or entire libraries. - Compare claims and details across multiple sources. - Find exact facts, dates, specifications, measurements, and table values. - Ask follow-up questions without losing the sources or the thread. - Choose Standard for quick factual work, Deep Think for multi-step questions, or Maximum for broader evidence synthesis. BRING YOUR OWN MATERIAL Import PDFs, Office documents, text and Markdown files, CSVs, code, images and scans, audio, or video. Pages, Numbers and Keynote files need to be exported to PDF first. OpenIntelligence extracts text, uses Vision OCR where needed, transcribes speech, and builds a searchable index for each library. HOW ANSWERS ARE BUILT Exact keyword matching and semantic search work together to retrieve the passages that matter. Apple Foundation Models turn those passages into a natural-language response. Then the app checks its own answer against the passages it actually used, so you can inspect what it's standing on instead of taking its word. If the sources do not establish an answer, the app flags weak support or abstains. No confident filler. WHERE YOUR FILES GO (AND DON'T) Reading your files, searching them, and choosing what to cite all happen on your device, start to finish, before anything is written. On-device answers need no connection at all. On a plane, in a dead zone, in a locked-down office, your library still works. For longer, evidence-heavy questions on iOS, iPadOS or macOS 27, you can optionally allow Apple Private Cloud Compute to do the writing. The app shows you how much would be sent and why, and asks you first. Apple says its servers keep nothing afterwards. Your material is never sent to a third-party AI provider. ANSWERS YOU CAN INSPECT Inline citations connect answers to their supporting pages and passages, one tap from claim to source. If you want more, response details go deeper: source snippets, retrieval quality, verification warnings, timing, and the route that actually produced the answer. The optional telemetry interface goes deeper when you want it and stays out of the way when you don't. LIBRARIES THAT FIT YOUR WORK Keep different subjects, projects, or clients in separate libraries. Choose Local Only or iCloud Drive (paid plans) for each library, and organize ongoing research in saved conversation threads. Siri and Shortcuts actions are available for common document and library workflows. PLANS Every plan runs the same model: Apple Intelligence on your device, Deep Think, and Private Cloud Compute after you approve what is sent. Free: 5 documents, one library, Maximum mode three times a day. Pro lifts that cap and grows to 1,000 documents and 10 libraries, monthly or yearly. Lifetime: one payment, unlimited documents, 20 libraries, Maximum every day, no renewal. OpenIntelligence is built and maintained by one developer. Pro and Lifetime support directly fund continued development. To everyone already supporting the app: thank you. It has been a wild journey. Privacy Policy: https://gunzino.me/openintelligence/privacy

Private by default. Frontier when you want it. Solair puts every kind of AI in your pocket, and keeps it private. Run powerful models fully on-device with no account and no internet, or connect Claude, ChatGPT, Grok and more when you want the frontier. Create images along the way, and keep every one in a gallery of your own. RUN AI ON YOUR DEVICE • 100% on-device models, no account, no sign-up, no tracking. Once a model downloads, everything works offline. • Your conversations, photos, health data, and documents are processed locally and never leave your device. • Auto Mode picks the right model for each message: Fast for quick questions, Smart for deep reasoning, Vision for photos and documents. • A duress code and fully local processing mean no one can read your data, not even us. BRING YOUR FAVORITE AI • Connect Claude, ChatGPT, Grok, Kimi, DeepSeek, Mistral, and more in one tap, just paste your API key. • Send photos, PDFs, and videos, watch reasoning models think, and generate images where supported. • Real web research: cloud models search the web themselves and show every source they read. • With your permission, they can read your health, calendar, and weather, and chart it for you. • Tokens, estimated spend, and voice minutes tracked per provider. • Your memory and past chats stay on your device unless you choose to share them. CREATE IMAGES, AND KEEP THEM ALL • Generate images right in your conversation. Choose the quality, the shape, and how many, and see what each option costs before you create. • Every image you make lands in a gallery of your own: folders you name, favorites, and full-screen browsing. • Pinch to zoom, swipe to move through them, and see them in real HDR that glows on your display. • Jump from any image straight back to the conversation that created it. TALK TO IT • Live voice conversations with ChatGPT and Grok, interrupt anytime, and the whole talk lands in your chat as a transcript. • Every other provider gets a voice on-device, only text ever leaves your phone, never audio, and live transcription types your words as you speak. MORE TO LOVE • Build your own apps (beta): describe one in a sentence and Solair makes a real, working app that runs offline. Four finished apps are included. • Scheduled tasks: give Solair a job and a time, and the answer arrives as a notification, all on your device. • Personas: chat with friends, historical figures, or build your own. • Personal memory that learns your preferences, and document analysis with instant summaries. • Health intelligence, ask about steps, sleep, and workouts from Apple Health, all on-device. Informational only, not medical advice. • Connect to your own server (Ollama and more) securely over Tailscale. • A beautiful Liquid Glass interface for iOS 26, with an engine switcher, sidebar search, and customizable themes. • Models included: Qwen3 & 3.5, Llama 3.2, Mistral, Gemma 3, plus coding, lightweight, and vision models like Qwen VL and LFM2.5. WHY SOLAIR Most AI apps send everything to the cloud. Solair runs on your device first, so your private data stays private, and reaches for the cloud only when you choose. REQUIREMENTS • iPhone A14 or newer, iPad A12 or newer, Mac with Apple Silicon. iOS 26 or later. 500MB to 5GB per on-device model. Solair is free with no ads. Optional tips support development but never lock features. EULA: https://www.apple.com/legal/internet-services/itunes/dev/stdeula/