# handtracking-io/yoha

A practical hand tracking engine.

Repository: https://github.com/handtracking-io/yoha
Canonical: https://ross.abutalabs.com/products/yoha
Language: TypeScript
License: MIT
License Family: permissive
Topics: hand-tracking, ai, web, hand-recognition, typescript, javascript
Last push: 2024-03-30T22:11:01+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 1863, "days_push": 886, "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 2117, forks 149 (observed 2026-08-28T04:06:16.325023+00:00)

## What it is
Yoha is a browser-based hand tracking engine built on TensorFlow.js that detects 21 2D hand landmarks, hand presence, left/right orientation, and predefined hand poses. It ships as an npm package for JavaScript/TypeScript web applications.

## Use cases
- track hand landmarks from a webcam in the browser
- detect hand gestures and poses for interactive web apps
- build drawing or painting apps controlled by hand movements
- detect whether a left or right hand is visible on camera
- add touchless hand-based interaction to a website

## When to choose
- you need in-browser hand tracking without a backend server
- you want built-in detection of useful hand poses for interactions
- your project is JavaScript/TypeScript on the web

## When to avoid
- you need active maintenance or long-term support (the project is unmaintained)
- you need 3D landmarks or multi-hand tracking
- you target platforms other than the web

## Facets
- artifact type: library
- maturity: abandoned
- function: machine-learning, computer-vision, image-processing
- domain: computer-vision, machine-learning, web-development, artificial-intelligence
- platform: browser
- tags: hand-tracking, hand-pose-detection, landmark-detection, tensorflowjs, webcam, gesture-recognition, unmaintained, nodejs, web-server, javascript

## Member repositories
- handtracking-io/yoha (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:16.325023+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 2026-08-30T02:53:13.845854+00:00, confidence not recorded.
  - readme: https://github.com/handtracking-io/yoha (fetched 2026-08-28T04:06:16.325023+00:00, sha 4193530d0def)
- Data as of 2026-08-30T08:39:29.467469+00:00.