The Apple Intelligence system

Your intelligence, on your own device.

The whole chanio loop — pull your day's chats down from the LLMs you already use, store them on your hard drive, derive your passions, let the models work them overnight, wake to new insight — runs on Apple's on-device stack. Your chats happen in the cloud; the synthesis happens at home. Not in a cloud that “protects” your intelligence by holding it. On the iPhone and Mac you already own. About $0 a night. The memory it builds never leaves your device.

cloud · bypassedClaudeChatGPTGeminipull the detail inyour deviceagents work overnight · $0 · on-device6:00 AMNew insighton your passions
Your LLMs → your device → overnight → you wake up smarter. Nothing leaves the device.
01 · The loop, end to end

Everything you did with AI, working for you while you sleep.

Seven beats. Each one runs on your device. You only ever see the first and the last — you use your AI, and you wake up smarter.

01
You use your AI
Claude, ChatGPT, Gemini, whatever you already pay for. Nothing changes about how you work.
02
chanio pulls the detail to your disk
Every session is captured to a repository on your own hard drive — plain files, yours, not a vendor's cloud.
03
It derives your passions from your usage
Not a form you fill out. The on-device model reads what you keep returning to and names what you actually care about.
04
It distills one small memory pack
Who you are, what you care about, where you are now — a few kilobytes. The prime a local model loads, not the whole archive.
05
Agents work your passions overnight
While you sleep, the on-device model finds the patterns you didn't name and connects sessions you had days apart.
06
You wake to new insight
A morning brief on your device — fresh angles on what you care about, computed while you slept.
07
Every AI you open is primed with you
Your context follows you to any model. The intelligence comes to your memory; your memory never leaves.
02 · What runs each part

The system, mapped to Apple's real primitives.

None of this is a metaphor. Each piece of the loop runs on a specific, shipping Apple API. The model is on your device; the overflow is cryptographic; the sync is your iCloud, not our server. Tap any of them for Apple's own documentation.

Foundation Models framework
The on-device model that runs capture, passion-derivation, and the overnight synthesis. On supported iPhone and Mac, at $0.
Apple docs →
SystemLanguageModel
Apple's on-device LLM. chanio loads your memory pack as its instructions — the local model reasons on your hard drive, fully private.
Apple docs →
Private Cloud Compute
Cryptographic overflow, used only when a step genuinely needs more. No human sees it, and it's verifiable. Your data never leaves Apple's trust boundary.
Apple docs →
@Generable
Structured output from the on-device model — the same capture schema the Mac pipeline uses, running natively on iOS.
Apple docs →
App Intents + Spotlight
Your captures and your morning brief become OS-level surfaces — Siri-callable, Spotlight-searchable, usable by any app. Your memory stops being a walled garden.
Apple docs →
iCloud Drive container
The memory pack and your captures sync across your iPhone, iPad, and Mac — with no chanio server in the middle. Sovereign and multi-device, for free.
Apple docs →
03 · Why on-device is the whole point

The model is rented. The memory is yours.

Apple itself rents a frontier model for Siri. Everyone runs the same commodity intelligence now — the value moved up, to the layer that remembers you and compounds. The cloud giants know it, so they all offer to “amplify and protect your intelligence.” Read the fine print: it lives inside their systems, and “protect” means a promise not to train on it.

chanio takes the opposite vow. Your intelligence never leaves your hard drive. There is nothing to protect it from, because we never hold it. Apple's on-device model does the work where your memory already lives — the agents come to you. No AI should eat the intelligence of the person it's deployed inside.

Sovereign
Memory lives on your disk. Exportable in one file. Outlives any model.
~$0 / night
Routine + overnight work runs on-device. Cloud only for the rare hard step.
Runs on any Mac
Decode runs on the Neural Engine — the same silicon from M-chip to iPhone. The cheapest Mac runs it as fast as the most expensive.
Private by construction
Nothing leaves your device; overflow is cryptographic, no human in the loop.
04 · Where it is today

Running now on Mac. Shipping on iPhone with iOS 27.

This is not a mockup. The full loop — capture, passion-derivation, the on-device memory pack, a local model answering from it — runs today on the founder's Mac, at $0 for everything but the one daily frontier call. And as of this week the same pack runs on Apple's own on-device model through the runtime Apple now ships in macOS 27 — fm respond, the memory pack loaded as its instructions. In about five seconds, on-device, it answered a grounded question about the person — citing what they actually care about and enforcing their own rules back — with nothing leaving the machine. We ship neither the model nor the runtime; Apple does, inside the OS. chanio just points the loop at it. Not a simulation of Apple Intelligence. Apple Intelligence, running the loop.

The memory pack, on your disk
~/.chanio/memory-pack.md   · ~5 KB

# Who you are working with
# What you care about
    curated + derived from your usage
# Where you are right now
# Open threads not to lose
# How to help

→ the on-device model loads this
   as its instructions. That's it.
A passion, derived from usage

“I care about building resilient infrastructure that silently fails rather than loudly breaks.”

Not typed into a form. Inferred by the on-device model from what the person actually returned to, across their sessions — then handed back for them to keep or promote.

The consumer version — the same system on the iPhone in your pocket, via the Apple Intelligence primitives above — ships with iOS 27. Same principle, same files, same vow: your memory, your device, your passions moving forward while you sleep.

The overnight loopSee the on-device routingJoin the waitlist