Meet Kynd.

An AI of your very own.

It remembers you, researches for you, and builds real software with you — entirely on your Mac. Even with the internet off.

Download free for 30 days Full product · no account, no card

Apple Silicon (M1 or later) · macOS 13+ · 16 GB memory or more

Rented intelligence

Big AI is brilliant.
It's also borrowed.

The cloud models are extraordinary — and none of them are yours. They live in a data centre, behind a meter. The price can rise. The model you rely on can be retired on a Tuesday. The service can go down in the middle of a sentence. And everything you type makes the journey to a server you will never see, governed by terms you didn't write.

None of that is a scandal. It's just what renting is.

prices changemodels get retiredoutages happenyour words travelterms shiftaccess can be revoked

Kynd answers to you.

Kynd's model is a file on your disk. Its memory is a folder in your home directory. Its thinking happens on your Mac's own silicon — which means nobody can raise the price of using it, retire it while you sleep, or read what you said to it.

Pull the Wi-Fi out mid-sentence and it finishes the thought.

works in airplane modeyours after one paymentnothing to revoke

01 — The companion

Someone to think
out loud with.

You've given Kynd the files you never quite get through — the survey on the house, the pension statement, your own notes. One evening you ask it, out loud, what the survey actually said about the roof. Whisper does the listening, running on your Mac. Kynd checks its library of your files and answers back in a voice. At no point does any of it touch the internet.

It remembers you between sessions — what you've told it carries forward, so you're not reintroducing yourself every week. And for conversations you'd rather weren't kept at all, there's a private chats mode.

The built-in macOS voice is free, forever. The licence adds four neural engines, including voice cloning from a short recording — still entirely on-device.

Voices

  • Systembuilt into macOS · free forever
  • Kokoro0.5 GB · warm and natural, best on 16 GB Macs
  • Qwen3 TTS1.7 GB · more expressive range
  • Chatterbox3.5 GB · clones from a recording
  • Fish Audio S27 GB · the most faithful cloning

02 — The researcher

A researcher you
can watch work.

You need the real picture on something — a grant you might qualify for, a market you're sizing, a decision currently spread across fourteen open tabs. You switch web search on for this one conversation, hand the question to Deep Research, and then you do the good part: you watch.

A live panel shows the agents at work — the searches they run, the pages they visit, the notes stacking up as the dig goes deeper. It is not a black box that hands back a paragraph; it is a researcher you can look over the shoulder of. Like watching a good librarian at speed.

Web search is opt-in, per conversation. Every other conversation stays in the room.

Deep Research — live

searchsmall business energy grants UK 2026

visitgov.uk — business energy advice service

noteeligibility: under 250 staff, meter type…

searchregional variants · Scotland / Wales

visitofgem.gov.uk — non-domestic tariffs

notewriting summary — 2 sources conflict, flagging…

The shape of the live panel: every search, visit and note, as it happens.

03 — The builder

A builder that fixes
its own mistakes.

You describe the app you keep meaning to make. Kynd plans the work as a checklist you can read, then gets on with it — writing files, running commands, reading its own error messages and fixing them. Live Preview renders the page while it's still being written, so you watch the thing take shape. And every change it makes has a one-button Undo.

When you'd rather point than describe, WebDesigner lets you edit the page visually. When you'd rather type, there's a real code editor and a shared shell — you and the agent work in the same place instead of passing notes.

A marketplace of agent tool packs extends what it can do, with audio and video generation add-ons to follow.

Quick Start templates

  • iOS AppSwiftUI
  • iOS GameSpriteKit
  • macOS Appnative
  • Web AppReact + TypeScript
  • Web GameCanvas
  • Mobile AppCapacitor · builds iOS and Android
  • Landing PageHTML/CSS
A real Build session: the agent's completed checklist beside the app it built, running in Live Preview.
A real session — the checklist on the left built the app running on the right.

The subscription maths

Put a number on the rent.

Tick what you pay for now, drag the years, and watch what renting intelligence costs against owning it once.

What you're renting

Everyday plans

Power-user plans

Over how long

3 years

$720

spent on subscriptions

$79Kynd, once
$621you keep

Individual plans on monthly billing, checked against each provider's own pricing page on 31 July 2026. A couple offer an annual discount, which would shave a little off. The honest caveat: frontier cloud models are more capable at raw reasoning — see the FAQ for where Kynd wins and where it doesn't.

Under the bonnet

Tested on your Mac,
by your Mac.

If you've ever stared at a page of quantisation options and sampler settings and quietly closed the tab, this is the part built for you. None of that is intelligence. It is plumbing — and Kynd ships with the plumbing done.

Setup reads your Mac's memory and chooses accordingly. A 16 GB Mac gets a quick 9-billion-parameter model. A 32 GB Mac gets a 35B. A 64 GB Mac gets the same 35B at higher quality. The context window scales with memory too, from 16k to 128k.

Then Kynd measures rather than assumes: it benchmarks the actual machine — real generation speed, real memory headroom, real tool calls — and sets its own limits from those measurements. You can race two models head-to-head, graded against fixed expected answers — not vibes.

The defaults are defaults because the alternatives failed. Models squeezed below 4-bit precision pass quizzes but fall apart at real agent work — we measured it, and we don't ship them. We tested the models so you don't have to.

The Calibration panel comparing local models on this machine, with parameters, quantisation and size on disk for each.

Privacy

Private in ways you
can check.

Most privacy pages ask for your trust. This one would rather you checked.

Every claim on this list is checkable on your own machine. Not a policy promise — just how it's built.

Price

One payment. Yours for good.

The trial is the full product, free for 30 days. After that, a genuinely useful tier stays free forever — and nothing is ever taken away at the thirty-day mark: your chats, projects and memory are plain files on your Mac and stay exactly where they are. The app simply settles into the free tier until you decide.

The first hundred licences are $79 instead of $149. That is a real hundred, not a rolling banner — when they are gone the price is $149 and stays there. Buying early is worth something because you are taking a chance on a new app from one person; the discount is the thanks.

 FreeLicence
Chat with a local modelyesyes
Web search and web fetchyesyes
Calibration and benchmarksyesyes
Knowledge — files it can draw onup to 10 filesunlimited
Memory — what it recalls about youa rolling 30 dayskept for good
VoicemacOS system voicefour neural engines, plus cloning
Build — writes files, runs commandsyes
WebDesigner — edit a page visuallyyes
Deep Researchyes
Image generationyes
Workflows and multi-agent runsyes
Workflow and tool buildersyes

Founding licence · first 100 only

$79

Then $149, and it stays there

  • One payment. Not a subscription. No meter.
  • Twelve months of updates included.
  • The version you buy is yours and works forever.
  • The free tier never expires, whatever you decide.
Download and start the 30 days

919 MB · Apple Silicon · the model downloads separately on first run

Questions

Before you download.

Will it run well on a 16 GB MacBook Air?

If you have an Apple Silicon Mac with 16 GB of memory or more, you're in. A 16 GB machine gets the 9B model — tested for exactly this tier — and Calibration tunes the limits to what your specific Mac measures, not what a spec sheet guesses.

Is it as good as Claude or GPT-5?

On raw reasoning, no — a local model is not going to match a frontier model on someone's server rack, and anyone telling you otherwise is selling something. What it is good at is the large middle of daily work: reading your files, researching, making the edits you describe, fixing its own errors. And it does that on a plane, on a train, and on things you are not allowed to paste into a browser.

How big is the download, really?

The app is 919 MB, because the runtime it needs is bundled — that is what makes the no-terminal setup possible. The model is separate and downloads on first run: 7.7 GB for the 16 GB tier, more for the larger models. There's a progress bar, and it doesn't need you to watch it.

Does it work offline?

Yes — that is the point. Once the model is downloaded, chat, voice, memory, and building all run with no connection at all. Web search and Deep Research are the two features that reach the internet, and both are opt-in, per conversation.

What happens when my 30 days are up?

It does not stop. Chat, web search, calibration and the system voice keep working for as long as you have the app, with nothing throttled and no countdown in the corner. What locks is the agent side — Build, WebDesigner, Deep Research, image generation, workflows, the builders and the neural voices — and your knowledge library settles back to ten files while memory returns to a rolling thirty days. Nothing is deleted when that happens: older memories move to the archive on your own disk and come straight back if you ever unlock them.

Thirty days. On the house.

No account, no card, and one app in your Applications folder if you decide it isn't for you.