# jeeliz/jeelizFaceFilter

🎭 Lightweight WebGL & JavaScript library for real-time multi-face detection, tracking and augmented-reality face filters. Supports rotation, mouth-opening and integrates with Three.js, Babylon.js, Canvas2D and CSS3D

Repository: https://github.com/jeeliz/jeelizFaceFilter
Canonical: https://ross.abutalabs.com/products/jeelizfacefilter
Homepage: https://jeeliz.com
Language: JavaScript
License: Apache-2.0
License Family: permissive
Topics: face, tracking, detection, javascript, snapchat, 3d, webgl, deep-learning, face-detection, face-tracking, threejs, faceswap, augmented-reality, face-filters, face-detect, lightweight, multiple-faces, camera, webar
Last push: 2025-11-14T13:50:59+00:00

## Health v2 (maintenance only)
Score: 46/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 52, release rhythm 8, longevity 100
- inputs: {"age_days": 3120, "days_push": 292, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2928, forks 546 (observed 2026-08-28T04:07:30.494641+00:00)

## What it is
A lightweight JavaScript/WebGL library for real-time face detection and tracking from a camera feed via WebRTC, designed for building augmented reality face filters. It outputs raw face position, scale, and rotation data and integrates with 3D engines like Three.js and Babylon.js.

## Use cases
- add snapchat-style face filters to a web app
- track face position and rotation in real time from webcam
- overlay 3D glasses or masks on a user's face in the browser
- build a virtual try-on experience for eyewear
- detect multiple faces simultaneously in a video feed
- detect mouth opening for avatar animation
- swap faces in real time in the browser

## When to choose
- you need a lightweight, framework-agnostic face tracking library that runs in the browser
- you want to build AR face filters with Three.js, Babylon.js, or Canvas2D
- you need multi-face tracking without heavy dependencies
- you want a permissively licensed (Apache-2.0) solution for web AR

## When to avoid
- you need server-side or native mobile face tracking
- you require full body or hand tracking rather than faces
- you need a complete turnkey filter platform rather than a tracking library
- your target browsers lack WebGL support

## Facets
- artifact type: library
- maturity: active
- function: computer-vision, machine-learning, graphics, image-processing
- domain: computer-vision, web-development, artificial-intelligence
- platform: browser, cross-platform
- tags: face-tracking, face-detection, face-filters, augmented-reality, webgl, webrtc, threejs, snapchat-style-filters, real-time, lightweight, javascript

## Member repositories
- jeeliz/jeelizFaceFilter (main) score 46

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:30.494641+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 2026-08-30T07:33:28.106017+00:00, confidence not recorded.
  - readme: https://github.com/jeeliz/jeelizFaceFilter (fetched 2026-08-28T04:07:30.494641+00:00, sha 8567569d28e7)
  - homepage: https://jeeliz.com (fetched 2026-08-29T09:49:00.451621+00:00, sha eb6118484e6a)
- Data as of 2026-08-30T08:39:29.467469+00:00.