--- title: "autogluon vs autokeras" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/autogluon-autogluon-vs-keras-team-autokeras" tools: ["autogluon-autogluon", "keras-team-autokeras"] --- # autogluon vs autokeras *GraphCanon updated Aug 4, 2026* ## Verdict Pick autogluon if autoGluon: an automated ML library for Python that promises accuracy in model training with minimal effort, supporting tabular data, time-series forecasting, vision tasks, and NLP; 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+. [autogluon](https://auto.gluon.ai/) reports 11k GitHub stars, 1.2k forks, and 388 open issues, last pushed Aug 3, 2026. [autokeras](http://autokeras.com/) has 9.3k stars, 1.4k forks, and 161 open issues, last pushed Nov 25, 2025. Figures are from public GitHub metadata via [autogluon's repository](https://github.com/autogluon/autogluon) and [autokeras's repository](https://github.com/keras-team/autokeras). | | [autogluon](/tools/autogluon-autogluon.md) | [autokeras](/tools/keras-team-autokeras.md) | | --- | --- | --- | | Tagline | Fast and Accurate ML in 3 Lines of Code | AutoML library for deep learning | | Stars | 10,576 | 9,328 | | Forks | 1,171 | 1,393 | | Open issues | 388 | 161 | | Language | Python | Python | | Adopt for | AutoGluon: an automated ML library for Python that promises accuracy in model training with minimal effort, supporting tabular data, time-series forecasting, vision tasks, and NLP. | AutoKeras simplifies deep learning model design through automated neural architecture search and is compatible with Python 3.7+ and TensorFlow 2.8.0+. | | Persona | - | - | | Runtime | - | - | | License | Apache-2.0 License allows for both commercial and private use with attribution required but no warranty provided by contributors or authors. | Apache-2.0 | | Categories | Developer Tools, Model Training | Developer Tools, Model Training | ## Trust and health _Sourced signals - not a safety guarantee. No winner column._ | | [autogluon](/tools/autogluon-autogluon.md) | [autokeras](/tools/keras-team-autokeras.md) | | --- | --- | --- | | Maintenance | Very active (96%) | Slowing (36%) | | Days since push | 0d | 251d | | Open issues (now) | 388 | 161 | | Full report | [trust report](/tools/autogluon-autogluon/trust.md) | [trust report](/tools/keras-team-autokeras/trust.md) | ## Shared compatibility - **Python**: [autogluon](/tools/autogluon-autogluon.md) - Python runtime; [autokeras](/tools/keras-team-autokeras.md) - Python runtime ## Decision facts: autogluon - **Adopt for:** AutoGluon: an automated ML library for Python that promises accuracy in model training with minimal effort, supporting tabular data, time-series forecasting, vision tasks, and NLP. - **License detail:** Apache-2.0 License allows for both commercial and private use with attribution required but no warranty provided by contributors or authors. ## 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+. ## Choose when ### Choose autogluon if… - Tags unique to autogluon: automated-machine-learning, computer-vision, data-science, ensemble-learning. - When you need quick setup of complex ML workflows involving CV, NLP, or structured data analysis. - More GitHub stars (11k vs 9.3k) - visibility, not fit. ### Choose autokeras if… - Tags unique to autokeras: autodl, keras, machine-learning, neural-architecture-search. - When your project involves deep learning tasks requiring minimal manual intervention in designing models. - Leaner open-issue backlog (161). ## When NOT to use autogluon - If your environment does not support Python versions 3.10-3.13 as AutoGluon requires these specific versions for operation. - For custom model developments where low-level control over every aspect of the ML process is a priority, given that AutoGluon automates significant parts of this. ## 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. ## Common questions ### What is the difference between autogluon and autokeras? autogluon: Fast and Accurate ML in 3 Lines of Code. autokeras: AutoML library for deep learning. See the comparison table for live GitHub stats and shared categories. ### When should I choose autogluon over autokeras? Choose autogluon over autokeras when Tags unique to autogluon: automated-machine-learning, computer-vision, data-science, ensemble-learning; When you need quick setup of complex ML workflows involving CV, NLP, or structured data analysis; More GitHub stars (11k vs 9.3k) - visibility, not fit. ### When should I choose autokeras over autogluon? Choose autokeras over autogluon when Tags unique to autokeras: autodl, keras, machine-learning, neural-architecture-search; When your project involves deep learning tasks requiring minimal manual intervention in designing models; Leaner open-issue backlog (161). ### When should I avoid autogluon? If your environment does not support Python versions 3.10-3.13 as AutoGluon requires these specific versions for operation. For custom model developments where low-level control over every aspect of the ML process is a priority, given that AutoGluon automates significant parts of this. ### 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. ### Is autogluon or autokeras more popular on GitHub? autogluon has more GitHub stars (10,576 vs 9,328). Stars measure visibility, not whether either tool fits your constraints. ### Are autogluon and autokeras open source? Yes - both are open-source projects on GitHub (autogluon: Apache-2.0, autokeras: Apache-2.0). ### Where can I find alternatives to autogluon or autokeras? GraphCanon lists graph-backed alternatives at [autogluon alternatives](/tools/autogluon-autogluon/alternatives) and [autokeras alternatives](/tools/keras-team-autokeras/alternatives) ([autogluon markdown twin](/tools/autogluon-autogluon/alternatives.md), [autokeras markdown twin](/tools/keras-team-autokeras/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/autogluon-autogluon-vs-keras-team-autokeras.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers. ### Which is better maintained, autogluon or autokeras? autogluon: Very active. autokeras: Slowing. 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 autogluon and autokeras? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [autogluon trust report](/tools/autogluon-autogluon/trust); [autokeras trust report](/tools/keras-team-autokeras/trust). --- **Machine-readable endpoints** - JSON: [`/api/graphcanon/graph?tool=autogluon-autogluon`](/api/graphcanon/graph?tool=autogluon-autogluon) - 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/_