# auduno/clmtrackr

Javascript library for precise tracking of facial features via Constrained Local Models

Repository: https://github.com/auduno/clmtrackr
Canonical: https://ross.abutalabs.com/products/clmtrackr
Language: JavaScript
License: MIT
License Family: permissive
Last push: 2020-01-10T15:02:27+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 5128, "days_push": 2427, "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 6500, forks 1134 (observed 2026-08-28T04:09:43.870894+00:00)

## What it is
clmtrackr is a JavaScript library for fitting facial models to faces in videos or images using Constrained Local Models with regularized landmark mean-shift. It tracks faces in the browser and outputs coordinate positions of facial feature points, supporting applications like face substitution, masking, and emotion detection.

## Use cases
- track facial landmarks in browser video
- detect face feature points in images with javascript
- build face substitution or masking effects in the browser
- realtime face deformation in web apps
- emotion detection from facial expressions
- overlay caricatures or masks on a webcam feed

## When to choose
- you need client-side facial landmark tracking without a server
- you want a lightweight, MIT-licensed browser library for face tracking
- you need coordinate positions of facial features for creative or analytical effects

## When to avoid
- you need state-of-the-art accuracy or modern deep-learning-based face tracking
- you need server-side or Node.js face tracking
- you need active development and recent updates - the last release was in 2020

## Facets
- artifact type: library
- maturity: maintenance
- function: computer-vision, image-processing, machine-learning
- domain: computer-vision, browser-extensions, web-development
- platform: browser
- tags: face-tracking, facial-landmarks, constrained-local-models, webgl, emotion-detection, face-masking, face-recognition, javascript, web

## Member repositories
- auduno/clmtrackr (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:43.870894+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 2026-08-29T17:44:29.801013+00:00, confidence not recorded.
  - readme: https://github.com/auduno/clmtrackr (fetched 2026-08-28T04:09:43.870894+00:00, sha 0125441744b8)
  - registry_npm: https://registry.npmjs.org/clmtrackr (fetched 2026-08-29T08:41:05.457968+00:00, sha c10363dd81bd)
- Data as of 2026-08-30T08:39:29.467469+00:00.