--- title: "AutoGL vs awesome-AutoML" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/thumnlab-autogl-vs-windmaple-awesome-automl" tools: ["thumnlab-autogl", "windmaple-awesome-automl"] --- # AutoGL vs awesome-AutoML *GraphCanon updated Aug 4, 2026* ## Verdict 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; pick awesome-AutoML if curates AutoML research across neural architecture search, hyperparameter optimization, and meta-learning. [AutoGL](http://mn.cs.tsinghua.edu.cn/AutoGL/) reports 1.1k GitHub stars, 123 forks, and 20 open issues, last pushed Nov 20, 2025. [awesome-AutoML](https://github.com/windmaple/awesome-AutoML) has 941 stars, 156 forks, and 1 open issues, last pushed Mar 24, 2026. Figures are from public GitHub metadata via [AutoGL's repository](https://github.com/THUMNLab/AutoGL) and [awesome-AutoML's repository](https://github.com/windmaple/awesome-AutoML). | | [AutoGL](/tools/thumnlab-autogl.md) | [awesome-AutoML](/tools/windmaple-awesome-automl.md) | | --- | --- | --- | | Tagline | AutoML framework & toolkit for machine learning on graphs | Curating AutoML research and resources | | Stars | 1,138 | 941 | | Forks | 123 | 156 | | Open issues | 20 | 1 | | Language | Python | - | | 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. | Curates AutoML research across neural architecture search, hyperparameter optimization, and meta-learning. | | Persona | - | - | | Runtime | - | - | | License | Apache-2.0 | GPL-3.0 | | Categories | Model Training | Model Training | ## Trust and health _Sourced signals - not a safety guarantee. No winner column._ | | [AutoGL](/tools/thumnlab-autogl.md) | [awesome-AutoML](/tools/windmaple-awesome-automl.md) | | --- | --- | --- | | Days since push | 256d | 133d | | Open issues (now) | 20 | 1 | | Owner type | Organization | User | | Full report | [trust report](/tools/thumnlab-autogl/trust.md) | [trust report](/tools/windmaple-awesome-automl/trust.md) | ## 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. ## Decision facts: awesome-AutoML - **Adopt for:** Curates AutoML research across neural architecture search, hyperparameter optimization, and meta-learning. ## Choose when ### Choose AutoGL if… - License: AutoGL is Apache-2.0, awesome-AutoML is GPL-3.0. - 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. ### Choose awesome-AutoML if… - License: awesome-AutoML is GPL-3.0, AutoGL is Apache-2.0. - Tags unique to awesome-AutoML: hyperparameter-optimization, meta-learning. - When seeking comprehensive resources on diverse AutoML topics from recent and impactful research. ## 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. ## When NOT to use awesome-AutoML - If looking for direct implementation advice as the repository focuses more on linking to resources rather than providing specific how-to guides. - When requiring real-time or interactive AutoML features, since it's a curation hub rather than an application tool. ## Common questions ### What is the difference between AutoGL and awesome-AutoML? AutoGL: AutoML framework & toolkit for machine learning on graphs. awesome-AutoML: Curating AutoML research and resources. See the comparison table for live GitHub stats and shared categories. ### When should I choose AutoGL over awesome-AutoML? Choose AutoGL over awesome-AutoML when License: AutoGL is Apache-2.0, awesome-AutoML is GPL-3.0; 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 choose awesome-AutoML over AutoGL? Choose awesome-AutoML over AutoGL when License: awesome-AutoML is GPL-3.0, AutoGL is Apache-2.0; Tags unique to awesome-AutoML: hyperparameter-optimization, meta-learning; When seeking comprehensive resources on diverse AutoML topics from recent and impactful research. ### 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. ### When should I avoid awesome-AutoML? If looking for direct implementation advice as the repository focuses more on linking to resources rather than providing specific how-to guides. When requiring real-time or interactive AutoML features, since it's a curation hub rather than an application tool. ### Is AutoGL or awesome-AutoML more popular on GitHub? AutoGL has more GitHub stars (1,138 vs 941). Stars measure visibility, not whether either tool fits your constraints. ### Are AutoGL and awesome-AutoML open source? Yes - both are open-source projects on GitHub (AutoGL: Apache-2.0, awesome-AutoML: GPL-3.0). ### Where can I find alternatives to AutoGL or awesome-AutoML? GraphCanon lists graph-backed alternatives at [AutoGL alternatives](/tools/thumnlab-autogl/alternatives) and [awesome-AutoML alternatives](/tools/windmaple-awesome-automl/alternatives) ([AutoGL markdown twin](/tools/thumnlab-autogl/alternatives.md), [awesome-AutoML markdown twin](/tools/windmaple-awesome-automl/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/thumnlab-autogl-vs-windmaple-awesome-automl.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers. ### Which is better maintained, AutoGL or awesome-AutoML? AutoGL: Slowing. awesome-AutoML: 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 AutoGL and awesome-AutoML? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [AutoGL trust report](/tools/thumnlab-autogl/trust); [awesome-AutoML trust report](/tools/windmaple-awesome-automl/trust). --- **Machine-readable endpoints** - JSON: [`/api/graphcanon/graph?tool=thumnlab-autogl`](/api/graphcanon/graph?tool=thumnlab-autogl) - 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/_