How it worksPrivacyExperts RoutinesThe chipRequest an expert FeedbackGet the app← Back to T3ISC
Free · no account · nothing leaves your phone
T3ni

A private AI assistant that runs entirely on your phone — powered by ternary. Ask it anything offline, in airplane mode. A working taste of the ternary future.

0 bytes to the cloud by default 0+ on-device experts · growing 0+ one-tap routines · growing runs on most modern phones · 3 GB+ RAM

Store links are placeholders while we finish review. Android first; iPhone follows.

T3nioffline
Ask anything — it stays on your phone
▶ live demo · running on-device, in airplane mode
Why it can live on your phone

Ternary is radically lighter compute.

Ordinary AI does its sums in fine-grained numbers — expensive to store, expensive to move, expensive in energy. Ternary models think in just three states: +1, 0, −1. That makes the model small enough, and cheap enough, to run offline on a phone — no data centre, no bill, no waiting on a network.

🪶

Small by design

A whole assistant in under a gigabyte. It loads into a phone's memory and answers there — nothing to upload, nothing to download per question.

🔋

Energy-frugal

Three-state maths moves and stores far less data per answer. That efficiency is exactly what lets a battery-powered device do the thinking.

📴

Works in airplane mode

The model is on the device. Turn off Wi-Fi and mobile data and it still answers — on a train, on a plane, off-grid.

How we did it

A small model, given the right information at the right time.

A tiny model doesn't know everything — so we don't ask it to. T3ni's trick is augmentation over size: efficient routing and retrieval put curated facts and live tools in front of the model exactly when a question needs them. On real questions, that lifts a 1-billion-parameter model to the quality of something many times larger.

You ask — typed or spoken
On-device speech-to-text, or just type. Nothing is sent anywhere.
Route — the app decides where the answer should come from
Maths? A fact? A live tool? A step-by-step problem? Each takes a different path — chosen in code, not left to the model to guess.
Ground — pull the exact facts that fit
The best-matching expert rows, a device connector, or a web lookup you approved — each answer shows its source.
Answer — the model writes it from those facts only
And when it genuinely doesn't know, it says so and offers to search — instead of making something up.
🎯

Honest by construction

Exact arithmetic is computed, not guessed. Questions about your private data, your history, or the future are declined rather than invented. Every grounded answer is cited.

🧭

Two-tier thinking

A fast compact model handles most things; harder questions escalate to a larger one automatically. You always see which model — and which experts — produced the answer.

🔎

Search, on your terms

Every reply can reach out to the web for a cited summary — but only when you tap it. Offline is the default; online is opt-in, and only your query ever leaves.

Privacy & on-device

Your phone is the whole computer.

T3ni is private by construction, not by promise. There's no account to create, no profile to build, and no server that sees your conversations, your notes, or your files. In airplane mode it works exactly the same.

🔒

Offline by default

Everything runs on the device. A single toggle turns web lookups on, with a clear prompt — and only the query leaves, never your chat or your data.

🙅

No account, no tracking

Download and run. No sign-up, no ads, no analytics profile. What's on your phone stays on your phone.

🗄️

Encrypted at rest

Your session, notes and settings are stored encrypted on the device. You can wipe them any time.

A panel in your pocket

Experts, downloaded only if you want them.

Knowledge lives in small, curated expert packs — one per subject. The app carries a light footprint and you add the packs you care about; each is a few kilobytes and installs in a tap. New packs appear over time, with no app update needed.

MathematicsPhysicsChemistryBiology Medicine & HealthComputer ScienceEngineeringHistory GeographyLawLegislationEconomics & Finance PsychologyPhilosophyCooking & FoodHow-To Writing & LanguageEarth & SpaceGeneral Knowledge

Advanced: the expert room 3B model

Turn on the larger model and several experts can share one question — the model weaves their facts into a single answer and shows you which packs it drew on. A whole panel, deliberating on your device.

Simple agentic AI, on-device

Routines that do the legwork.

A routine gathers from the tools you've connected — calendar, weather, news, prices, your notes — and hands the model only the real data to summarise. No invented meetings, no made-up headlines: if it isn't there, it isn't in the briefing. One tap, a useful answer.

🌅

Morning briefing

Today's calendar, weather and headlines, in a few lines — before you're out the door.

🌙

Evening wind-down

Tomorrow's schedule and any loose ends from your inbox, tied off for the night.

🧾

Receipt → CSV

Point it at a receipt; it reads the text on-device and gives you clean rows.

📰

News digest

Top headlines from your chosen feed, condensed to the bullets that matter.

📈

Market check

Your watchlist prices with a one-line read — no dashboards to open.

💡

Fact of the day

A genuine nugget pulled from one of your experts, explained simply.

The point of all this
This is ternary on a binary phone.
Imagine it on a ternary one.

T3ni runs today on the ordinary binary chips already in your pocket — and it's genuinely useful. But those chips weren't built for three-state maths. On a true ternary chip — the silicon T3ISC is building — the same phone could hold and run a 35-billion-parameter model: a superagent, in your hand, offline, on a battery.

1–3B
on a phone today, on binary silicon — that's what you're downloading
35B
a mixed-expert model on a true ternary chip — big-model intelligence, ~3B-model energy

Here's the trick ternary unlocks. A 35B model normally needs ~70 GB and a data centre; in three states it shrinks to about 7 GB — small enough for a phone's memory. And because it's a mixture-of-experts, it thinks like a 35B model while only computing a few billion parameters per answer — so it stays fast and frugal enough for a battery. With a new wave of 35B-class models landing, picture that intelligence running privately in your hand. T3ni is the free, working preview — the chip is where it goes next.

See the ternary advantage → Invest in the chip →
Shape the panel

Request an expert.

Want a pack we don't have yet — beekeeping, tax, a language, your trade? Tell us. Because experts are just downloadable packs, we can add a new one for everyone without an app update.

Thanks — opening your email app to send it.

We're listening

Feedback, bugs & requests.

Found a bug? Want a new routine, or a feature? T3ni gets better from what real people ask for. Tell us what happened or what you'd love to see.

🐛 Bug report⚡ Routine idea✨ Feature request💬 Just thoughts

Thanks — opening your email app to send it.

Free forever

Try ternary now.

A private AI in your pocket — and a first look at the efficiency ternary brings. Download, and see what a phone can do on three states.