--- title: "auto-sklearn vs AutoGL" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/automl-auto-sklearn-vs-thumnlab-autogl" tools: ["automl-auto-sklearn", "thumnlab-autogl"] --- # auto-sklearn vs AutoGL *GraphCanon updated Aug 4, 2026* ## Verdict Pick auto-sklearn if auto-sklearn is an automated machine learning toolkit designed to automate hyperparameter optimization and function seamlessly with scikit-learn workflows; 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. [auto-sklearn](https://automl.github.io/auto-sklearn) reports 8.1k GitHub stars, 1.3k forks, and 209 open issues, last pushed Jun 29, 2026. [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 [auto-sklearn's repository](https://github.com/automl/auto-sklearn) and [AutoGL's repository](https://github.com/THUMNLab/AutoGL). | | [auto-sklearn](/tools/automl-auto-sklearn.md) | [AutoGL](/tools/thumnlab-autogl.md) | | --- | --- | --- | | Tagline | Automated Machine Learning with scikit-learn | AutoML framework & toolkit for machine learning on graphs | | Stars | 8,127 | 1,138 | | Forks | 1,327 | 123 | | Open issues | 209 | 20 | | Language | Python | Python | | Adopt for | auto-sklearn is an automated machine learning toolkit designed to automate hyperparameter optimization and function seamlessly with scikit-learn workflows. | 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 | BSD-3-Clause | Apache-2.0 | | Categories | Model Training | Model Training | ## Trust and health _Sourced signals - not a safety guarantee. No winner column._ | | [auto-sklearn](/tools/automl-auto-sklearn.md) | [AutoGL](/tools/thumnlab-autogl.md) | | --- | --- | --- | | Maintenance | Steady (60%) | Slowing (36%) | | Days since push | 35d | 256d | | Open issues (now) | 209 | 20 | | Full report | [trust report](/tools/automl-auto-sklearn/trust.md) | [trust report](/tools/thumnlab-autogl/trust.md) | ## Shared compatibility - **Python**: [auto-sklearn](/tools/automl-auto-sklearn.md) - Python runtime; [AutoGL](/tools/thumnlab-autogl.md) - Python runtime ## Decision facts: auto-sklearn - **Adopt for:** auto-sklearn is an automated machine learning toolkit designed to automate hyperparameter optimization and function seamlessly with scikit-learn workflows. ## 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 auto-sklearn if… - License: auto-sklearn is BSD-3-Clause, AutoGL is Apache-2.0. - Tags unique to auto-sklearn: automated-machine-learning, bayesian-optimization, hyperparameter-optimization, hyperparameter-search. - auto-sklearn ships Docker support for self-hosted deployment. - When you need a drop-in replacement estimator for your existing scikit-learn pipeline that can handle the complexity of hyperparameter tuning automatically. ### Choose AutoGL if… - License: AutoGL is Apache-2.0, auto-sklearn is BSD-3-Clause. - 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: deep-learning, graph-neural-networks, hyper-parameter-optimization, machine-learning. - 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 auto-sklearn - If extensive customization or control over individual machine learning components is required beyond what auto-sklearn's automation offers. - In cases requiring non-scikit-learn model ensembles, as the toolkit primarily supports models that are part of the scikit-earn library. ## 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 auto-sklearn and AutoGL? auto-sklearn: Automated Machine Learning with scikit-learn. AutoGL: AutoML framework & toolkit for machine learning on graphs. See the comparison table for live GitHub stats and shared categories. ### When should I choose auto-sklearn over AutoGL? Choose auto-sklearn over AutoGL when License: auto-sklearn is BSD-3-Clause, AutoGL is Apache-2.0; Tags unique to auto-sklearn: automated-machine-learning, bayesian-optimization, hyperparameter-optimization, hyperparameter-search; auto-sklearn ships Docker support for self-hosted deployment; When you need a drop-in replacement estimator for your existing scikit-learn pipeline that can handle the complexity of hyperparameter tuning automatically. ### When should I choose AutoGL over auto-sklearn? Choose AutoGL over auto-sklearn when License: AutoGL is Apache-2.0, auto-sklearn is BSD-3-Clause; 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: deep-learning, graph-neural-networks, hyper-parameter-optimization, machine-learning; 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 auto-sklearn? If extensive customization or control over individual machine learning components is required beyond what auto-sklearn's automation offers. In cases requiring non-scikit-learn model ensembles, as the toolkit primarily supports models that are part of the scikit-earn library. ### 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 auto-sklearn or AutoGL more popular on GitHub? auto-sklearn has more GitHub stars (8,127 vs 1,138). Stars measure visibility, not whether either tool fits your constraints. ### Are auto-sklearn and AutoGL open source? Yes - both are open-source projects on GitHub (auto-sklearn: BSD-3-Clause, AutoGL: Apache-2.0). ### Where can I find alternatives to auto-sklearn or AutoGL? GraphCanon lists graph-backed alternatives at [auto-sklearn alternatives](/tools/automl-auto-sklearn/alternatives) and [AutoGL alternatives](/tools/thumnlab-autogl/alternatives) ([auto-sklearn markdown twin](/tools/automl-auto-sklearn/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/automl-auto-sklearn-vs-thumnlab-autogl.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers. ### Which is better maintained, auto-sklearn or AutoGL? auto-sklearn: Steady. 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 auto-sklearn and AutoGL? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [auto-sklearn trust report](/tools/automl-auto-sklearn/trust); [AutoGL trust report](/tools/thumnlab-autogl/trust). --- **Machine-readable endpoints** - JSON: [`/api/graphcanon/graph?tool=automl-auto-sklearn`](/api/graphcanon/graph?tool=automl-auto-sklearn) - 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/_