BlueberryML · London

The geometry AI thinks in.

BlueberryML learns the shape of human domains — how people learn, how people feel, who a character is — and licenses it, so AI systems reason over structure and know where they are.

See how it works →Work with us

The learning manifold is in production in schools across India. →

How it works

Knows where it is. Decides fast. Talks well.

A language model on its own is fluent but has no sense of place: every turn starts again from a prompt.

A manifold on its own knows exactly where someone is, but can't say a word.

Put a fast System 1-type decision layer between them, and you get a system that knows where it is, decides quickly and talks well. Neither half can do that alone.

And because the manifold does the knowing, the language model can be small: fast, cheap, and able to run on your own hardware.

How the method works →

The manifold

slow · learned · persistent

Where are we, and where should we go next?

System 1

fast · calibrated · typed

What happens now? On every turn, in milliseconds.

The language model

small · fluent · steered

How do we say it?

Every turn is evidence. Evidence moves the position.

The personality substrate

Characters that grow, feel and remember.

Most AI characters are handed notes about themselves: a long prompt, a Markdown file, a store of past conversations to retrieve. Ours live in a geometry. It's the manifold we care about most, and where BlueberryML is heading.

The personality substrate →

1. Learning gives growth.
The learning manifold already tracks a trajectory: where someone was, where they are, where they’re heading. A personality needs exactly that sense of change over time.
2. Emotion gives an inner state.
Valence, arousal, warmth and attention move turn by turn and settle back to baseline. Traits hold steady underneath.
3. Context gives memory and relationship.
What happened between this character and this person, and how it changed them both.
4. Together they form a substrate:
something a character lives in, not a description it’s handed.

The manifolds

One geometry of a whole life.

How we develop as children, who we are, how we change as we age. One method, applied domain by domain.

In production

In production

At national scale, today.

Chrysalis, our licence partner in India, runs the learning manifold across its schools there. Schools in India: Chrysalis is the place to start. Everywhere else, talk to us.

What's in production →

~600,000

children in Chrysalis schools

Sovereign by design

Your data stays in your country.

Your learners' data is stored in your jurisdiction, under your control, and it's yours. Where the AI runs is your choice: on our infrastructure, or fully in-country.

Stored where you are.

Learner records, voices, transcripts and results live in your own jurisdiction, under your control. We don’t keep copies, and we don’t train on your data without your agreement.

Run by us, or by you.

We can run the processing for you on our secure infrastructure, under a data processing agreement, with results written straight back to your store. Or the whole stack, speech and scoring models included, runs in-country on your own hardware.