Privacy-first AI assistant
One app. Every model. Zero compromises. The intelligence runs on your phone — and stays there.
No account. No tracking. No servers in between.
On-device intelligence
A quantized Llama 3.2 1B model ships separately on first launch — kept off the install size, kept on your device. From then on, it answers without a single network call.
Open the app on a flight, in a tunnel, in a country your provider doesn't reach — the local model is already there. No hand-off. No fallback to a server. The conversation simply happens.
Local Llama 3.2 · 1B · q4_K_M
When you want the cloud
Your API key talks to the provider. Nothing routes through us — there's nothing to route through. Bring whichever brain you trust today, swap it for another tomorrow.
InApps
More than a chat box — a suite of productivity apps that plug straight into the model you're using, online or offline. Every credential, note, and task stays on your device.
Real-time job postings from across Oman, in one place. Smart-search by title, company, or skill, get AI-powered insights on requirements, and let the assistant help you prepare and apply with confidence — right beside the listings.
Learn any subject with a personal AI tutor — upload your own notes (PDF/DOCX) for grounded lessons, or run realistic mock interviews tailored to your resume and target role.
AI-powered search that works online and offline. Concise summaries of live web results — or fully on-device answers when there's no connection at all.
Describe a game in a few words and the AI builds a complete, playable game you can start instantly — created and run right on your device.
View and summarise recent mail, generate AI replies, and compose new emails with AI help. Gmail, Outlook, Yahoo, iCloud, or any custom IMAP/SMTP mailbox — connected with an app password, never your real one.
Capture quickly and let the AI rewrite, structure, and enhance. Organise everything in one place and export as TXT, PDF, or DOCX when you're done.
Manage tasks with dates and times, and let the assistant treat your list as context — so its answers know what you're actually working on.
Real-time speech-to-text with AI summaries, and one tap to turn any transcript into a note. Meetings, memos, 3am ideas — captured on the device.
Discover AI-generated images fetched right inside the app, and browse them in a clean, full-screen viewer built for exploring.
Privacy architecture
Most assistants route through their own servers — to bill, to log, to "improve". We don't have any. Your phone talks to your provider. That's the whole diagram.
More than chat
Point at anything. ML Kit handles labels and OCR locally; vision-capable models do the deeper read.
Press to talk. The transcript hits the model — your voice never leaves the device.
Drop in a paper, a contract, a manual. It gets parsed locally, then summarised, queried, drafted against.
Search the web, news, locations, images, and videos from the chat — or open a page and have the assistant summarise it. Filtered, citation-aware.
Tell the AI how to respond once and it sticks — tone, format, role. Your rules travel with every conversation.
Attach images, camera photos, files, and documents to any chat — so the AI answers with the full picture, not just the prompt.
Side by side
Most "AI apps" are a thin shell over someone else's cloud — your conversations live on their servers, indexed and retained at their discretion. DigitalOman runs on yours.
“Privacy isn't a Feature. It's the Foundation.”
Free. Offline-capable. No account. No tracking.