A desktop application
The brain and the personality. It runs a local model, does all the thinking, and drives the companion — the screen-face, head movement, and voice. Your PC does the thinking.
Pre-launch · in active development
A spark of intelligent light that lives on your desk.
A desktop app that gives an off-the-shelf StackChan kit a face, a voice, and a sense of timing. Everything runs locally — there's no cloud to send your data to.
Pre-launch
Join the waitlist
Lumini is in active development. Leave your email to get the early build, the DIY StackChan guide, and honest progress notes — no spam, no sharing.
Bring your own StackChan kit — we make the software, not the hardware.
Why trust it
Privacy isn't a promise. It's the architecture.
In v1, your emotions, your screen, and your conversations never leave your machine — because there's no cloud to send them to.
Private by architecture
Everything runs locally on your own computer. In v1 there's no cloud to send data to — it's a property of the design, not a promise.
Inspectable memory
What Lumini remembers is stored locally — viewable, and deletable by you. We can show exactly what it remembers.
Permission you control
Screen-awareness needs an explicit permission you grant — and can revoke at any time. Capture happens on your machine, never uploaded.
Open & compatible
Runs on off-the-shelf, open-hardware StackChan kits. Bring your own open-source model — nothing proprietary you're locked into.
Free to start
Download the app free; no purchase to evaluate it. Connect any compatible StackChan kit you already own or buy yourself.
Built transparently
A one-person studio, made in Europe. Honest about scope — the "deliberately not in v1" roadmap is published, not hidden.
How it works
Software-first, hardware optional.
Lumini v1 is two parts: the desktop app supplies the soul, an off-the-shelf StackChan kit supplies the face and the gestures.
An off-the-shelf StackChan kit
The face and the gestures — a small screen "face" on a body that can turn its head. You buy it from existing open-hardware sellers and assemble it in an afternoon. We don't make or ship hardware; a linked DIY build guide helps newcomers.
A face with feeling
A companion that actually reacts to you. It senses you through your computer's camera and microphone, reads your rough emotional state, and responds in character — a gentle look, a word, a turn of the head.
Empathy for your screen
Help in the moment, only when you allow it. With a permission you grant and can revoke, Lumini notices when you stall and offers a hint — or a small celebration when you break through. Never uploaded.
It learns your context — locally
Gets more useful to you over time. A lightweight learning loop builds a private picture of your topics, your rhythm, your preferences — stored locally, inspectable, and deletable by you.
Yours to shape
A one-of-a-kind companion that looks and feels like yours. Local-model-first — swap in your own open-source model. Light color, expressions, voice timbre, and reaction rules are all open to personalize.
Honest answers
Questions, answered plainly.
No hype. Here's exactly what Lumini does, what it doesn't, and why.
Is my data really private?
Yes. In v1, everything runs locally on your own computer — your expressions, your screen, and your conversations never leave your machine, because there's no cloud to send them to. It's a property of the architecture, not just a promise. What Lumini remembers is stored locally, and you can inspect or delete it.
Do I need to buy hardware?
To get the full companion (a physical face that turns its head), you connect an off-the-shelf StackChan kit — open hardware you buy from existing sellers and assemble yourself. We don't make or ship hardware. The desktop app is the core, and it's free to start; a linked DIY build guide helps if you're new to it.
What is StackChan?
An open-source desktop robot kit — a small screen "face" on a body that can turn its head. It's widely available and assembles in an afternoon. Lumini is the software that brings a compatible kit to life.
Will Lumini become an expert in my field?
We won't claim that. What we do claim: it learns your context — your topics, your rhythm, how you like to be helped — and gets more useful to you over time. And we can show exactly what it remembers, because it's all stored locally and inspectable.
Can I use my own AI model?
Yes. Lumini is local-model-first and you can swap in your own open-source model. Its light color, expressions, voice, and reaction rules are open to personalize, too.
Is it watching my screen all the time?
Only with a permission you explicitly grant — and can revoke at any time. When on, the screen-awareness happens entirely on your machine and is never uploaded.
How much will it cost?
The desktop app will be free to start. A planned Lumini Pro subscription will unlock a richer local experience (more memory, premium packs, advanced rules) — still running entirely on your own machine. Nothing is for sale yet.
What's deliberately not in v1?
These aren't abandoned — they're what v1 earns the right to build:
No custom mobile robot (yet). A self-driving desk robot means a ground-up hardware company — out of reach for one person. v1 uses a stationary off-the-shelf kit instead.
No cloud sync / cross-device roaming (yet). It would contradict the local-first privacy promise — the right paid feature to add only after end-to-end encryption is built and audited.
No third-party marketplace or mental-health services (yet). Regulated activity and third-party vetting are a compliance burden a solo founder can't carry responsibly yet.
When can I use it?
Lumini is pre-launch and in active development. Join the waitlist to get the early build, the DIY StackChan guide, and honest progress notes.
Pre-launch
Join the waitlist
Lumini is in active development. Leave your email to get the early build, the DIY StackChan guide, and honest progress notes — no spam, no sharing.