--- title: "autokeras vs AutoGL" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/keras-team-autokeras-vs-thumnlab-autogl" tools: ["keras-team-autokeras", "thumnlab-autogl"] --- # autokeras vs AutoGL *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 AutoGL if autoGL is an AutoML framework for machine learning on graphs, specializing in automated hyperparameter optimization and neural architecture search for various graph data tasks. [autokeras](http://autokeras.com/) reports 9.3k GitHub stars, 1.4k forks, and 161 open issues, last pushed Nov 25, 2025. [AutoGL](http://mn.cs.tsinghua.edu.cn/AutoGL/) has 1.1k stars, 123 forks, and 20 open issues, last pushed Nov 20, 2025. Figures are from public GitHub metadata via [autokeras's repository](https://github.com/keras-team/autokeras) and [AutoGL's repository](https://github.com/THUMNLab/AutoGL). | | [autokeras](/tools/keras-team-autokeras.md) | [AutoGL](/tools/thumnlab-autogl.md) | | --- | --- | --- | | Tagline | AutoML library for deep learning | AutoML framework & toolkit for machine learning on graphs | | Stars | 9,328 | 1,138 | | Forks | 1,393 | 123 | | Open issues | 161 | 20 | | 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+. | AutoGL is an AutoML framework for machine learning on graphs, specializing in automated hyperparameter optimization and neural architecture search for various graph data tasks. | | Persona | - | - | | Runtime | - | - | | License | Apache-2.0 | Apache-2.0 | | 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) | [AutoGL](/tools/thumnlab-autogl.md) | | --- | --- | --- | | Days since push | 251d | 256d | | Open issues (now) | 161 | 20 | | Full report | [trust report](/tools/keras-team-autokeras/trust.md) | [trust report](/tools/thumnlab-autogl/trust.md) | ## Shared compatibility - **Python**: [autokeras](/tools/keras-team-autokeras.md) - Python runtime; [AutoGL](/tools/thumnlab-autogl.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: AutoGL - **Requirements:** Min 8 GB RAM; Requires Python version >= 3.6.0.; Must include a backend library for graph processing; either PyTorch Geometric (>=1.7.0) or Deep Graph Library (DGL, >=0.7.0).; PyTorch version should be >=1.6.0. - **Adopt for:** AutoGL is an AutoML framework for machine learning on graphs, specializing in automated hyperparameter optimization and neural architecture search for various graph data tasks. ## Choose when ### Choose autokeras if… - Tags unique to autokeras: autodl, keras, tensorflow. - Also covers Developer Tools. - When your project involves deep learning tasks requiring minimal manual intervention in designing models. ### Choose AutoGL if… - Requirements: Min 8 GB RAM; Requires Python version >= 3.6.0.; Must include a backend library for graph processing; either PyTorch Geometric (>=1.7.0) or Deep Graph Library (DGL, >=0.7.0).; PyTorch version should be >=1.6.0.. - Tags unique to AutoGL: graph-neural-networks, hyper-parameter-optimization, pytorch, pytorch-geometric. - When you need to automate the process of optimizing hyperparameters and searching through different neural architectures for complex graph-based datasets. ## 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 AutoGL - For scenarios where the dataset does not involve graph structures, as AutoGL is specifically designed to handle such data types, potentially leading to suboptimal results on non-graph datasets. - If your project relies heavily on frameworks other than PyTorch or backends outside of PyTorch Geometric or Deep Graph Library, considering it may pose integration challenges or inefficiencies. ## Common questions ### What is the difference between autokeras and AutoGL? autokeras: AutoML library for deep learning. AutoGL: AutoML framework & toolkit for machine learning on graphs. See the comparison table for live GitHub stats and shared categories. ### When should I choose autokeras over AutoGL? Choose autokeras over AutoGL when Tags unique to autokeras: autodl, keras, tensorflow; Also covers Developer Tools; When your project involves deep learning tasks requiring minimal manual intervention in designing models. ### When should I choose AutoGL over autokeras? Choose AutoGL over autokeras when Requirements: Min 8 GB RAM; Requires Python version >= 3.6.0.; Must include a backend library for graph processing; either PyTorch Geometric (>=1.7.0) or Deep Graph Library (DGL, >=0.7.0).; PyTorch version should be >=1.6.0.; Tags unique to AutoGL: graph-neural-networks, hyper-parameter-optimization, pytorch, pytorch-geometric; When you need to automate the process of optimizing hyperparameters and searching through different neural architectures for complex graph-based datasets. ### 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 AutoGL? For scenarios where the dataset does not involve graph structures, as AutoGL is specifically designed to handle such data types, potentially leading to suboptimal results on non-graph datasets. If your project relies heavily on frameworks other than PyTorch or backends outside of PyTorch Geometric or Deep Graph Library, considering it may pose integration challenges or inefficiencies. ### Is autokeras or AutoGL more popular on GitHub? autokeras has more GitHub stars (9,328 vs 1,138). Stars measure visibility, not whether either tool fits your constraints. ### Are autokeras and AutoGL open source? Yes - both are open-source projects on GitHub (autokeras: Apache-2.0, AutoGL: Apache-2.0). ### Where can I find alternatives to autokeras or AutoGL? GraphCanon lists graph-backed alternatives at [autokeras alternatives](/tools/keras-team-autokeras/alternatives) and [AutoGL alternatives](/tools/thumnlab-autogl/alternatives) ([autokeras markdown twin](/tools/keras-team-autokeras/alternatives.md), [AutoGL markdown twin](/tools/thumnlab-autogl/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-thumnlab-autogl.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers. ### Which is better maintained, autokeras or AutoGL? autokeras: Slowing. AutoGL: 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 autokeras and AutoGL? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [autokeras trust report](/tools/keras-team-autokeras/trust); [AutoGL trust report](/tools/thumnlab-autogl/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/_