--- title: "autokeras vs keras" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/keras-team-autokeras-vs-keras-team-keras" tools: ["keras-team-autokeras", "keras-team-keras"] --- # autokeras vs keras *GraphCanon updated Aug 4, 2026* ## Verdict Pick autokeras if autoKeras simplifies deep learning model design through automated neural architecture search and is compatible with Python 3.7+ and TensorFlow 2.8.0+; pick keras if keras is a Python-based deep learning framework designed for simplicity and versatility, supporting multiple backends like TensorFlow, JAX, PyTorch, and OpenVINO. [autokeras](http://autokeras.com/) reports 9.3k GitHub stars, 1.4k forks, and 161 open issues, last pushed Nov 25, 2025. [keras](http://keras.io/) has 64k stars, 20k forks, and 208 open issues, last pushed Aug 1, 2026. Figures are from public GitHub metadata via [autokeras's repository](https://github.com/keras-team/autokeras) and [keras's repository](https://github.com/keras-team/keras). | | [autokeras](/tools/keras-team-autokeras.md) | [keras](/tools/keras-team-keras.md) | | --- | --- | --- | | Tagline | AutoML library for deep learning | Deep Learning for humans | | Stars | 9,328 | 64,217 | | Forks | 1,393 | 19,746 | | Open issues | 161 | 208 | | Language | Python | Python | | Adopt for | AutoKeras simplifies deep learning model design through automated neural architecture search and is compatible with Python 3.7+ and TensorFlow 2.8.0+. | Keras is a Python-based deep learning framework designed for simplicity and versatility, supporting multiple backends like TensorFlow, JAX, PyTorch, and OpenVINO. | | Persona | - | - | | Runtime | - | - | | License | Apache-2.0 | Keras is released under the Apache-2.0 license, allowing it to be freely used and modified in both open-source and commercial projects. | | Categories | Developer Tools, Model Training | Model Training | ## Trust and health _Sourced signals - not a safety guarantee. No winner column._ | | [autokeras](/tools/keras-team-autokeras.md) | [keras](/tools/keras-team-keras.md) | | --- | --- | --- | | Maintenance | Slowing (36%) | Very active (96%) | | Days since push | 251d | 1d | | Open issues (now) | 161 | 208 | | Full report | [trust report](/tools/keras-team-autokeras/trust.md) | [trust report](/tools/keras-team-keras/trust.md) | ## Shared compatibility - **Python**: [autokeras](/tools/keras-team-autokeras.md) - Python runtime; [keras](/tools/keras-team-keras.md) - Python runtime ## Decision facts: autokeras - **Adopt for:** AutoKeras simplifies deep learning model design through automated neural architecture search and is compatible with Python 3.7+ and TensorFlow 2.8.0+. ## Decision facts: keras - **Requirements:** Dependencies include installing a backend (like TensorFlow, JAX, PyTorch) along with the `keras` package. - **Adopt for:** Keras is a Python-based deep learning framework designed for simplicity and versatility, supporting multiple backends like TensorFlow, JAX, PyTorch, and OpenVINO. - **License detail:** Keras is released under the Apache-2.0 license, allowing it to be freely used and modified in both open-source and commercial projects. ## Choose when ### Choose autokeras if… - Tags unique to autokeras: autodl, automl, keras, neural-architecture-search. - Also covers Developer Tools. - When your project involves deep learning tasks requiring minimal manual intervention in designing models. ### Choose keras if… - Requirements: Dependencies include installing a backend (like TensorFlow, JAX, PyTorch) along with the `keras` package.. - Tags unique to keras: data-science, jax, neural-networks, python. - When you need a high-level API to build neural networks more easily with fewer lines of code. ## When NOT to use autokeras - When working with Python versions older than 3.7 or TensorFlow versions older than 2.8.0, as AutoKeras is not compatible. - If your project emphasizes transparent, understandable model architecture over automated generation without human oversight. ## When NOT to use keras - When low-level optimizations or customizations are necessary since Keras is an abstraction layer that might hide certain details. - For environments where a specific deep learning framework must be used exclusively; Keras's multi-backend support could introduce unnecessary complexity. ## Common questions ### What is the difference between autokeras and keras? autokeras: AutoML library for deep learning. keras: Deep Learning for humans. See the comparison table for live GitHub stats and shared categories. ### When should I choose autokeras over keras? Choose autokeras over keras when Tags unique to autokeras: autodl, automl, keras, neural-architecture-search; Also covers Developer Tools; When your project involves deep learning tasks requiring minimal manual intervention in designing models. ### When should I choose keras over autokeras? Choose keras over autokeras when Requirements: Dependencies include installing a backend (like TensorFlow, JAX, PyTorch) along with the `keras` package.; Tags unique to keras: data-science, jax, neural-networks, python; When you need a high-level API to build neural networks more easily with fewer lines of code. ### When should I avoid autokeras? When working with Python versions older than 3.7 or TensorFlow versions older than 2.8.0, as AutoKeras is not compatible. If your project emphasizes transparent, understandable model architecture over automated generation without human oversight. ### When should I avoid keras? When low-level optimizations or customizations are necessary since Keras is an abstraction layer that might hide certain details. For environments where a specific deep learning framework must be used exclusively; Keras's multi-backend support could introduce unnecessary complexity. ### Is autokeras or keras more popular on GitHub? keras has more GitHub stars (64,217 vs 9,328). Stars measure visibility, not whether either tool fits your constraints. ### Are autokeras and keras open source? Yes - both are open-source projects on GitHub (autokeras: Apache-2.0, keras: Apache-2.0). ### Where can I find alternatives to autokeras or keras? GraphCanon lists graph-backed alternatives at [autokeras alternatives](/tools/keras-team-autokeras/alternatives) and [keras alternatives](/tools/keras-team-keras/alternatives) ([autokeras markdown twin](/tools/keras-team-autokeras/alternatives.md), [keras markdown twin](/tools/keras-team-keras/alternatives.md)), ranked by typed relationship edges rather than popularity votes. ### Is there a machine-readable version of this comparison? Yes. The markdown twin at [this comparison](/compare/keras-team-autokeras-vs-keras-team-keras.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers. ### Which is better maintained, autokeras or keras? autokeras: Slowing. keras: Very active. Compare maintenance labels, days since push, and release cadence in the trust section below - stars alone do not measure maintenance. ### Where are the full trust reports for autokeras and keras? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [autokeras trust report](/tools/keras-team-autokeras/trust); [keras trust report](/tools/keras-team-keras/trust). --- **Machine-readable endpoints** - JSON: [`/api/graphcanon/graph?tool=keras-team-autokeras`](/api/graphcanon/graph?tool=keras-team-autokeras) - LLM index: [/llms.txt](/llms.txt) - Full corpus: [/llms-full.txt](/llms-full.txt) _GraphCanon - The knowledge graph for AI development. https://www.graphcanon.com/_