# ml5js/ml5-library

Friendly machine learning for the web! 🤖

Repository: https://github.com/ml5js/ml5-library
Canonical: https://ross.abutalabs.com/products/ml5-library
Homepage: https://ml5js.org
Language: JavaScript
License: NOASSERTION
License Family: other
Topics: lstm, deep-learning, imagenet, machine-learning, javascript, neural-network, p5xjs, p5js
Last push: 2024-10-11T02:28:01+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 3256, "days_push": 692, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- 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 6587, forks 898 (observed 2026-08-28T04:09:45.484945+00:00)

## What it is
ml5.js is a friendly, beginner-oriented JavaScript machine learning library for the browser, built on top of TensorFlow.js. It provides access to pretrained models (image classification, pose estimation, face landmarks, sound classification) and a neural network module for training custom models, aimed at artists, creative coders, and students.

## Use cases
- classify images in the browser with pretrained models
- track body pose or hand skeleton from webcam video
- detect facial landmarks for interactive art projects
- train a simple neural network in JavaScript
- add sound classification to a p5.js sketch
- teach machine learning to students without heavy math

## When to choose
- you want approachable ML in the browser with minimal setup
- you're an artist, educator, or student using p5.js or Processing-style coding
- you need pretrained models like BodyPose, HandPose, FaceMesh, or ImageClassifier
- you value educational resources and ethical computing documentation

## When to avoid
- you need production-grade performance or fine-grained control over TensorFlow.js
- you need server-side or Node.js ML training at scale
- you require a permissive, well-defined license (licensing is non-standard)
- you need the latest state-of-the-art model architectures

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, deep-learning, image-processing, audio-processing, computer-vision
- domain: machine-learning, artificial-intelligence, web-development, education
- platform: browser
- tags: tensorflowjs, p5js, creative-coding, pretrained-models, pose-estimation, image-classification, beginner-friendly, javascript, web

## Member repositories
- ml5js/ml5-library (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:45.484945+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 2026-08-29T17:43:34.923404+00:00, confidence not recorded.
  - readme: https://github.com/ml5js/ml5-library (fetched 2026-08-28T04:09:45.484945+00:00, sha fbd1e77eb805)
  - homepage: https://ml5js.org (fetched 2026-08-29T08:40:19.414644+00:00, sha 74667b814fb4)
  - site_page: https://ml5js.org/about (fetched 2026-08-29T08:40:19.417589+00:00, sha 74ee69a785e7)
  - site_page: https://docs.ml5js.org/ (fetched 2026-08-29T08:40:19.419853+00:00, sha c33ec45dbb4e)
- Data as of 2026-08-30T08:39:29.467469+00:00.