keras-team/keras
Deep Learning for humans
Multi-backend framework supporting JAX, TensorFlow, PyTorch, and OpenVINO, enabling developers to write backend-agnostic code and switch implementations for optimal performance gains (20-350% speedups depending on architecture). Provides high-level APIs for computer vision, NLP, audio, and time-series tasks while maintaining seamless interoperability with existing tf.keras code, tf.data pipelines, and PyTorch DataLoaders. Custom components remain portable across backends, avoiding framework lock-in while scaling from laptops to distributed GPU/TPU clusters.
63,968 stars and 16,934,477 monthly downloads. Used by 80 other packages. Actively maintained with 160 commits in the last 30 days. Available on PyPI.
Stars
63,968
Forks
19,732
Language
Python
License
Apache-2.0
Category
Last pushed
Mar 13, 2026
Monthly downloads
16,934,477
Commits (30d)
160
Dependencies
8
Reverse dependents
80
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/keras-team/keras"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
pytorch/pytorch
Tensors and Dynamic neural networks in Python with strong GPU acceleration
Lightning-AI/pytorch-lightning
Pretrain, finetune ANY AI model of ANY size on 1 or 10,000+ GPUs with zero code changes.
Lightning-AI/torchmetrics
Machine learning metrics for distributed, scalable PyTorch applications.
lanpa/tensorboardX
tensorboard for pytorch (and chainer, mxnet, numpy, ...)
huggingface/autotrain-advanced
🤗 AutoTrain Advanced