Overview & Getting Started

Overview

The HarmonEyes Unity SDK turns raw eye-tracking data from a supported headset or webcam into four real-time cognitive-state metrics: Mental Workload, Fatigue, Attention, and Mental Readiness. The SDK is delivered as a Unity package that ships a native theia library, a C# wrapper, three platform sample scenes (Meta Quest Pro, HTC Vive Focus Vision, and a headset-free Mock playback), and editor scripts for inspector ergonomics.

What it produces

See API Reference for the per-field type and range.

Real-world use cases

• Reading performance — line-by-line attention tracking, comprehension monitoring, detecting reading-difficulty patterns.
• Clinical diagnostics — screening for Parkinson’s, TBI, Lyme disease, MCI, MS via eye-movement biomarkers.
• Visual search and driving — monitoring attention, decision-making, situational awareness.
• Biometric ID — eye-movement signatures for real-time user authentication.
• Developer testing — user testing during app development.
• Market research — interface usability and user-behavior insight.

Supported hardware

*to set up any eye tracker not listed, select the nearest lower Hz preset from this list

Get a license key

A license key is required. Contact sales@harmoneyes.com to obtain one. The same key is entered on the AnalyzeEyeTrackingData component in each sample scene.

Three ways to use the SDK

Pick whichever matches your situation.

Manual Integration Overview

A custom integration is three steps.

1. Initialise

• Add the AnalyzeEyeTrackingData component to a GameObject in your scene.
• Enter the License Key on the component inspector.
• Pick the Tracker preset that matches your hardware (or the closest sample-rate match, rounding down).

The component handles native SDK creation, license validation, and session start automatically on Start. Read AnalyzeEyeTrackingData.Instance.EyeTrackingInitCompleted to know when initialisation has completed.

2. Capture — submit one sample per tracker frame

Write a collector MonoBehaviour that reads your platform’s eye data, builds a Sample via the factory, and submits it.

using UnityEngine;
using HarmonEyes.EyeTracking.Common;

public class MyCollector : MonoBehaviour
{
    [SerializeField] private Camera headCamera;

    void FixedUpdate()
    {
        var analyze = AnalyzeEyeTrackingData.Instance;
        if (analyze == null || !analyze.EyeTrackingInitCompleted) return;

        long timestampNs = (long)(Time.timeAsDouble * 1e9);

        // Pull per-eye origin, orientation, closed-weight, and a blink decision
        // from your platform's API.
        Vector3    leftEyeOrigin       = /* head-local metres */ Vector3.zero;
        Quaternion leftEyeOrientation  = /* gaze rotation */ Quaternion.identity;
        float      leftEyeClosed       = /* 0..1 */ 0f;
        Vector3    rightEyeOrigin      = Vector3.zero;
        Quaternion rightEyeOrientation = Quaternion.identity;
        float      rightEyeClosed      = 0f;
        bool       isBlinking          = /* your platform's blink criterion */ false;

        Sample s = GazeDataSampleFactory.CreateGazeSample(
            analyze.SessionId, timestampNs,
            leftEyeOrigin,  leftEyeOrientation,  leftEyeClosed,
            rightEyeOrigin, rightEyeOrientation, rightEyeClosed,
            headCamera.fieldOfView,
            isBlinking);

        analyze.SubmitGazeSample(s);
    }
}

3. Process — read results

Two access patterns. Pick whichever fits your code.

Polling — read the latest payload on demand:

var mw = analyze.EyeTrackingAnalyzer.CurrentMentalWorkload;
if (mw != null) Debug.Log($"MW: {mw.LevelName} (conf {mw.confidence:F2})");

Event-driven — subscribe once, react to each new prediction:

analyze.EyeTrackingAnalyzer.OnMentalWorkloadResult += mw =>
    Debug.Log($"MW: {mw.LevelName} (conf {mw.confidence:F2})");

The four result properties and matching events are listed in API Reference.

Where to go next