shadowbrook by hampton.io

One moment.

This project researches how to personify your AI chats. A richer human experience, using voice and vision. A face, a voice, and a memory let people say things they will not type into a box, and stay. The same person can take a different part. A language tutor who remembers the words you keep missing. A help desk that stays with one question. A check-in that already knows the names. Someone to learn with. Or a rehearsal for a conversation you are not ready to have yet.

A voice you can look at.

A voice that looks back.

Shadowbrook is a Hampton.io research project. A realtime voice model, OpenAI or Gemini, speaks as a three-dimensional person in the browser. Her mouth follows the words. She can remember what you ask her to keep, and, if you allow the camera, notice how you seem.

Someone to be with.

A face, a voice, and a memory make the model into a person. People will say things to someone who is there that they will not type into a box, and they will stay. The same person can take a different part each time. The parts do not run out.

Help us make this a reality.

It is early. If you want this to exist, say which part you can take.