GraphCanon updated 3w · GitHub synced 3w · 26 views this month
Decision brief
TengineKit is an easy-to-integrate AI algorithm SDK targeting mobile platforms for real-time detection and recognition tasks like face and body landmarks, attributes, hand detections.
Good fit when
- You aim to integrate comprehensive real-time AI algorithms on mobile devices such as face detection, landmarks, and attributes with low latency.
- Specific device support is required for Kirin or Qualcomm processors where TengineKit shows optimized performance rates.
Avoid when
- Your project does not require features like hand or body detection/landmarks in real-time on mobile devices, as these are not fully supported yet on the mobile platform provided by this SDK.
- The necessity of using an open-source license is a critical factor for your decision since TengineKit's license is listed as 'Other', suggesting restrictions may apply.
- Requirements:
- The tool requires C++ skills to be effectively utilized in development.; Performance optimization is reported on select mobile platforms, mainly focusing on Kirin and Qualcomm series.
Observed Jul 17, 2026 · Source: enrich:decision_facts
Verify the decision
Maintenance and security
Full trust report- Maintenance
- Dormant (1746d since push)
- As of 3w
- Provenance
- Not a fork · Organization account
- As of 3w
- Security (OSV)
- No lockfile
- As of 1mo
Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.
Install
git clone https://github.com/OAID/TengineKitSimilar tools
Same-category neighbours. No typed graph edges are catalogued for this tool yet.
Evidence and technical details
Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.
Overview
A comprehensive library for real-time detection and recognition tasks targeting mobile platforms like face and body landmarks, attributes, hand detections.
Capability facts
- Languages
- c++
Source: github.language · Jul 31, 2026
Categories
Tags
README
中文版本
=======================================================================
TengineKit, developed by OPEN AI LAB.
TengineKit is an easy-to-integrate AI algorithm SDK. At present, it can run on various mobile phones at very low latency.We will continue to update this project for better results and better performance!
Effect
| Face Detection & Face 2dLandmark | Face 3dLandmark & Iris | Upper Body Detection & Uppper Body Landmark | Hand Detection & Hand Landmark |
|---|---|---|---|
 |  |  |  |
Gif
Video( YouTube | BiliBili )
Have a try
- Apk can be directly downloaded and installed on the phone to see the effect.
or
- scan code to download apk
Goals
- Provide best performance in mobile client
- Provide the simplest API in mobile client
- Provide the smallest package in mobile client
Features
- face detection
- face landmarks
- face 3dlandmarks
- face attributes for example: age, gender, smile, glasses
- eye iris & landmarks
- body detect
- hand detect(Real-time, not yet on Mobile)
- hand landmarks(Real-time, not yet on Mobile)
- body detect google(Real-time, not yet on Mobile)
- body landamrks(Real-time, not yet on Mobile)
- yolov5
Update (2021/03/25)
- Fixed Linux sample code errer
- Update Android sample code, up fps
- update Linux so file
- update Linux yolov5s
- Fixed memory(Core v0.0.6)
Performance(Face Detect & Face Landmark)
| CPU | Time consuming | Frame rate |
|---|---|---|
| Kirin 980 | 4ms | 250fps |
| Qualcomm 855 | 5ms | 200fps |
| Kirin 970 | 7ms | 142fps |
| Qualcomm 835 | 8ms | 125fps |
| Kirin 710F | 9ms | 111fps |
| Qualcomm 439 | 16ms | 62fps |
| MediaTek Helio P60 | 17ms | 59fps |
| Qualcomm 450B | 18ms | 56fps |
Landmark Points Order
Landmark Points Order
Contact
About the use of TengineKit and face-related technical exchanges, you can join the following QQ groups(Group Answer:TengineKit):
- TengineKit communication QQ group: 630836519
- Scan to join group
For agents
This page has a .md twin and JSON over the API.