For developers

Make your product
read the room

One SDK, one API, live human context.

2 files

to get started

~23 s

to a first result

0

video frames leave the device

Seconds, not sprints

A real session, replayed.

Result
Waiting for results…
  • Stress0.31
  • Arousal0.58
  • Confusion0.12
  • Valence+0.24

Illustrative values.

Try it live ↗

Write it, or delegate it

By hand

Your key stays on your server.

import { createProtocolClient } from '@neurologyca/capture'

const client = createProtocolClient({
  baseUrl: '/engine',
  taxonomy: { contextId: 'measurement' },
})
const session = await client.captureProtocol({
  userProtocolId, protocolMechanicId,
  source: { type: 'webcam' },
})
Quickstart ↗

With your AI agent

One command, and it knows the way.

npx skills add https://labs.kopernica.io -a claude-code
  • Claude Code
  • Cursor
  • Codex
  • Copilot
AI agents ↗

Three ways in

RECOMMENDED

On-device

Real time. Video stays on the device.

PREVIEW

Server-side

Upload now, results in minutes.

BACKEND

HTTP API

Any language, any stack.

The rest is in the DevLab

Explore the DevLab ↗