--- title: "learn2learn vs awesome-AutoML" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/learnables-learn2learn-vs-windmaple-awesome-automl" tools: ["learnables-learn2learn", "windmaple-awesome-automl"] --- # learn2learn vs awesome-AutoML *GraphCanon updated Aug 4, 2026* ## Verdict Pick learn2learn if learn2learn is a PyTorch library for conducting meta-learning research with a focus on few-shot learning tasks; pick awesome-AutoML if curates AutoML research across neural architecture search, hyperparameter optimization, and meta-learning. [learn2learn](http://learn2learn.net) reports 2.9k GitHub stars, 359 forks, and 34 open issues, last pushed Dec 16, 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 [learn2learn's repository](https://github.com/learnables/learn2learn) and [awesome-AutoML's repository](https://github.com/windmaple/awesome-AutoML). | | [learn2learn](/tools/learnables-learn2learn.md) | [awesome-AutoML](/tools/windmaple-awesome-automl.md) | | --- | --- | --- | | Tagline | A PyTorch Library for Meta-learning Research | Curating AutoML research and resources | | Stars | 2,891 | 941 | | Forks | 359 | 156 | | Open issues | 34 | 1 | | Language | Python | - | | Adopt for | Learn2learn is a PyTorch library for conducting meta-learning research with a focus on few-shot learning tasks. | Curates AutoML research across neural architecture search, hyperparameter optimization, and meta-learning. | | Persona | - | - | | Runtime | - | - | | License | MIT | GPL-3.0 | | Categories | Model Training | Model Training | ## Trust and health _Sourced signals - not a safety guarantee. No winner column._ | | [learn2learn](/tools/learnables-learn2learn.md) | [awesome-AutoML](/tools/windmaple-awesome-automl.md) | | --- | --- | --- | | Days since push | 230d | 133d | | Open issues (now) | 34 | 1 | | Owner type | Organization | User | | Full report | [trust report](/tools/learnables-learn2learn/trust.md) | [trust report](/tools/windmaple-awesome-automl/trust.md) | ## Decision facts: learn2learn - **Adopt for:** Learn2learn is a PyTorch library for conducting meta-learning research with a focus on few-shot learning tasks. ## Decision facts: awesome-AutoML - **Adopt for:** Curates AutoML research across neural architecture search, hyperparameter optimization, and meta-learning. ## Choose when ### Choose learn2learn if… - License: learn2learn is MIT, awesome-AutoML is GPL-3.0. - Tags unique to learn2learn: few-shot, finetuning, learn2learn, learning2learn. - When focusing on few-shot learning scenarios ### Choose awesome-AutoML if… - License: awesome-AutoML is GPL-3.0, learn2learn is MIT. - Tags unique to awesome-AutoML: automl, hyperparameter-optimization, neural-architecture-search. - When seeking comprehensive resources on diverse AutoML topics from recent and impactful research. ## When NOT to use learn2learn - If the project does not require PyTorch - For traditional machine learning problems without the need for meta-learning ## 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 learn2learn and awesome-AutoML? learn2learn: A PyTorch Library for Meta-learning Research. awesome-AutoML: Curating AutoML research and resources. See the comparison table for live GitHub stats and shared categories. ### When should I choose learn2learn over awesome-AutoML? Choose learn2learn over awesome-AutoML when License: learn2learn is MIT, awesome-AutoML is GPL-3.0; Tags unique to learn2learn: few-shot, finetuning, learn2learn, learning2learn; When focusing on few-shot learning scenarios. ### When should I choose awesome-AutoML over learn2learn? Choose awesome-AutoML over learn2learn when License: awesome-AutoML is GPL-3.0, learn2learn is MIT; Tags unique to awesome-AutoML: automl, hyperparameter-optimization, neural-architecture-search; When seeking comprehensive resources on diverse AutoML topics from recent and impactful research. ### When should I avoid learn2learn? If the project does not require PyTorch For traditional machine learning problems without the need for meta-learning ### 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 learn2learn or awesome-AutoML more popular on GitHub? learn2learn has more GitHub stars (2,891 vs 941). Stars measure visibility, not whether either tool fits your constraints. ### Are learn2learn and awesome-AutoML open source? Yes - both are open-source projects on GitHub (learn2learn: MIT, awesome-AutoML: GPL-3.0). ### Where can I find alternatives to learn2learn or awesome-AutoML? GraphCanon lists graph-backed alternatives at [learn2learn alternatives](/tools/learnables-learn2learn/alternatives) and [awesome-AutoML alternatives](/tools/windmaple-awesome-automl/alternatives) ([learn2learn markdown twin](/tools/learnables-learn2learn/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/learnables-learn2learn-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, learn2learn or awesome-AutoML? learn2learn: 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 learn2learn and awesome-AutoML? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [learn2learn trust report](/tools/learnables-learn2learn/trust); [awesome-AutoML trust report](/tools/windmaple-awesome-automl/trust). --- **Machine-readable endpoints** - JSON: [`/api/graphcanon/graph?tool=learnables-learn2learn`](/api/graphcanon/graph?tool=learnables-learn2learn) - 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/_