#103103rd of 105 in ML frameworks and libraries
autokeras
AutoML library that searches Keras models with a fit/predict API
Documentation ↗
(opens in a new tab)Website ↗
(opens in a new tab)Repository on GitHub ↗
(opens in a new tab)
- Stars
- 9.3k
- License
- Apache-2.0
- Last commit
- Nov 2025
- Last release
- Nov 2025
- Language
- Python
9,266 on 1 Apr 20269,337 on 21 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
AutoKeras is a Python AutoML library built on Keras. It exposes task classes such as ImageClassifier with a fit/predict interface and searches for a suitable model. It is developed by DATA Lab at Texas A&M University and has a JMLR paper, tutorials and a book.
Who it is for: Python developers who want automated model search on Keras/TensorFlow
Strengths
- Three-line API: ak.ImageClassifier(), fit(), predict()
- Installs with pip3 install autokeras
- Official tutorials, a JMLR paper and a book are available
- Apache-2.0 licensed, latest release 2025-11-12
Weaknesses
- README states support only for Python >= 3.7 and TensorFlow >= 2.8.0
- README lists no supported tasks beyond the image classifier example
- README gives no hardware requirements or search-time guidance
- Not aimed at LLMs or generative models
What it needs
- Docker
- Needs Python >= 3.7, TensorFlow >= 2.8.0
- Models: Keras
Also in ML frameworks and libraries
See all 105| 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 for deep learning | 94 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 reference training scripts | 92 out of 100 |
| #5 | supervisionPython toolkit for loading, annotating and counting computer vision detections | 91 out of 100 |