young startup from Stuttgart with a lot of passion for democratic processes and the necessary know-how for the future
Keras
Open-source deep learning API for building neural networks on JAX, TensorFlow or PyTorch
About Keras
Keras is a deep learning API designed around the developer, aiming for quick debugging, short readable code, easy maintenance and straightforward deployment. Since its multi-backend release it runs on JAX, TensorFlow or PyTorch, and models can move between those frameworks.
What Keras offers
- Functional API — models assembled by wiring layers together.
- Built-in training — fitting and evaluating models with standard methods such as model.fit.
- Subclassing — custom layers and models written by extending Keras classes.
- KerasHub — Keras 3 versions of popular model architectures with pretrained checkpoints on Kaggle Models, usable for training and inference on any backend.
- Guides and examples — developer guides plus code samples in computer vision, natural language processing and other areas.
Who it works with
Keras is aimed at machine learning developers and researchers who want one codebase that can run across the three main deep learning frameworks.
Key facts
- Backends: JAX, TensorFlow and PyTorch
- Model hub: KerasHub with checkpoints on Kaggle Models
Profile written by TrustList from the business's own published information, Sep 2026.
Request a demo or quote from Keras
Reviews
Questions & answers
No questions yet. Be the first to ask about Keras.
Keras alternatives
Similar listings buyers compare against this one.
Scaling advisory for start-ups covering business design, branding, OKRs, organisation design, hiring and culture
Cloud software developer serving municipal governments, grant-making nonprofits and small to mid-sized businesses
More on TrustList
Everything here links back to the same verified catalogue. Pick your next stop.
- Write a reviewHelp other buyers decide
- ProductsSoftware and SaaS with pricing, features, integrations and alternatives.
- ArticlesGuides, comparisons and research from the editorial desk and the community.
- AwardsAnnual recognition decided by verified reviews and an independent jury.
- LaunchesNew products and releases, voted up by the community every day.
- AI ModelsBenchmark scores and community ratings for every major model.
- RequestsBuyers describe what they need; vendors respond directly.
- PeopleReviewers, authors and makers with public profiles.
- ComparePut up to four listings side by side before you shortlist.