# OAID/TengineKit

TengineKit - Free, Fast, Easy, Real-Time Face Detection & Face Landmarks & Face Attributes & Hand Detection & Hand Landmarks & Body Detection & Body Landmarks &  Iris Landmarks & Yolov5 SDK On Mobile.

Repository: https://github.com/OAID/TengineKit
Canonical: https://ross.abutalabs.com/products/tenginekit
Language: C++
License: NOASSERTION
License Family: other
Topics: mobile, face-landmarks, face-detection, android, face-tracking, java, face-attributes, deep-neural-networks, ai, artificial-intelligence, facial-landmarks, tensorflow, pytorch, face-api, face-alignment, computer-vision
Last push: 2021-10-18T07:27:43+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": 2256, "days_push": 1780, "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 2321, forks 308 (observed 2026-08-28T04:06:37.152990+00:00)

## What it is
TengineKit is a mobile AI SDK by OPEN AI LAB providing real-time face detection, face 2D/3D landmarks, face attributes, iris, hand, and body detection with landmarks, plus YOLOv5 support. It is a C++ core with Android integration designed for very low latency on-device inference.

## Use cases
- detect faces in real time on android
- get face landmarks from camera feed
- estimate age gender glasses from face
- track hand landmarks on mobile
- detect human body pose landmarks
- run yolov5 object detection on phone
- add face filters to a mobile app

## When to choose
- you need fast on-device face or landmark detection on Android with a simple SDK API
- you want a small package size and low latency for mobile AR or camera effects

## When to avoid
- you need iOS or server-side support - it targets Android/Linux mobile
- you need actively maintained software - the latest release is from 2021
- you need hand/body detection on mobile - those features were not yet shipped on mobile

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, computer-vision, image-processing
- domain: computer-vision, artificial-intelligence, mobile-development, deep-learning
- platform: cpp
- tags: face-detection, face-landmarks, face-attributes, hand-landmarks, body-landmarks, iris-landmarks, yolov5, mobile-sdk, real-time-inference, on-device-ai, android, mobile, linux

## Member repositories
- OAID/TengineKit (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:37.152990+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 2026-08-30T02:38:39.343001+00:00, confidence not recorded.
  - readme: https://github.com/OAID/TengineKit (fetched 2026-08-28T04:06:37.152990+00:00, sha 6611d7d43d69)
- Data as of 2026-08-30T08:39:29.467469+00:00.