# brownhci/WebGazer

WebGazer.js: Scalable Webcam EyeTracking Using User Interactions

Repository: https://github.com/brownhci/WebGazer
Canonical: https://ross.abutalabs.com/products/webgazer
Homepage: https://webgazer.cs.brown.edu
Language: HTML
License: NOASSERTION
License Family: other
Last push: 2026-02-24T05:12:20+00:00

## Health v2 (maintenance only)
Score: 65/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 69, release rhythm 40, longevity 100
- inputs: {"age_days": 3855, "days_push": 190, "days_rel": 190, "gap_med": 222, "n_releases_24m": 2}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3888, forks 579 (observed 2026-08-28T04:08:28.277431+00:00)

## What it is
WebGazer.js is a JavaScript eye tracking library that uses a standard webcam to predict a user's gaze location on a web page in real time. It self-calibrates from user interactions like clicks and cursor movements, runs entirely client-side, and integrates into any website with a few lines of code.

## Use cases
- track where users look on a web page using only a webcam
- build gaze-controlled browser games or interfaces
- run usability studies measuring user attention without special eye tracking hardware
- add self-calibrating gaze prediction to a website with a few lines of JavaScript
- process webcam video locally in the browser without sending data to a server
- evaluate webcam eye tracker accuracy against a benchmark dataset

## When to avoid
- you need research-grade gaze accuracy from a dedicated eye tracker
- you require guaranteed ongoing updates or official support, since maintenance has ended
- your target users cannot grant webcam access or use unsupported browsers

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, computer-vision, sdk
- domain: computer-vision, web-development, artificial-intelligence, browser-extensions
- platform: browser, cross-platform
- tags: eye-tracking, webcam, gaze-prediction, javascript, real-time, client-side, self-calibration, accessibility-research, nodejs

## Member repositories
- brownhci/WebGazer (main) score 65

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:28.277431+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:25:38.526251+00:00, confidence not recorded.
  - readme: https://github.com/brownhci/WebGazer (fetched 2026-08-28T04:08:28.277431+00:00, sha 2768b75832e9)
  - homepage: https://webgazer.cs.brown.edu (fetched 2026-08-29T09:19:33.639435+00:00, sha 3b3810c36825)
  - site_page: https://webgazer.cs.brown.edu/data (fetched 2026-08-29T09:19:33.642204+00:00, sha 31156ddddb59)
- Data as of 2026-08-30T08:39:29.467469+00:00.