#152152nd of 168 in ML frameworks and libraries
mlkit
Kotlin Android library wrapping Google ML Kit vision APIs with camera-scan helpers
- Stars
- 1.2k
- License
- Apache-2.0
- Last commit
- Jun 2026
- Last release
- Jun 2026
- Language
- Kotlin
1,141 on 21 Apr 20261,177 on 10 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
MLKit is a set of Android Gradle modules built on Google ML Kit and the CameraScan library. They cover barcode and QR scanning, face detection, face mesh, image labeling, object detection, pose detection, selfie segmentation and text recognition. Each module provides an Analyzer plus ready-made camera scan Activity and Fragment base classes. The project is published to Maven Central and JitPack, and a sample app is included.
Who it is for: Android developers adding scanning or on-device vision features to apps
Strengths
- Separate modules per feature, so apps pull in only the ML Kit parts they use
- Each module ships an Analyzer plus Activity and Fragment base classes for camera scanning
- Published on Maven Central and JitPack, with API docs and a sample APK
- Supports 13 barcode formats, including QR Code, Data Matrix, PDF417 and EAN-13
Weaknesses
- Android only; minimum API level 23
- Version 2.4.0 and later require compileSdk 35 or higher
- Depends on the separate CameraScan library, whose package names differ from 1.x
- README and docs are mostly in Chinese
What it needs
- Needs Google ML Kit, CameraScan, ViewfinderView, Android compileSdk 35+ (v2.4.0+), JDK 8+
- Models: Google ML Kit on-device vision models
Quick answers
Is mlkit open source?
Yes. Its code is on GitHub under the Apache-2.0 license.
Also in ML frameworks and libraries
See all 168| Rank | Project | Score |
|---|---|---|
| 1 | transformersPython library defining open models for text, vision, audio and multimodal tasks | 94 out of 100 |
| 2 | pytorchPython tensor library with GPU support and tape-based autograd | 93 out of 100 |
| 3 | ultralyticsPython library and CLI for training and running YOLO vision models | 93 out of 100 |
| #4 | pytorch-image-modelsPyTorch library of image models, pretrained weights and training scripts | 93 out of 100 |
| #5 | supervisionPython toolkit for loading, annotating and counting computer vision detections | 92 out of 100 |