--- title: "Auto-PyTorch vs devol" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/automl-auto-pytorch-vs-joeddav-devol" tools: ["automl-auto-pytorch", "joeddav-devol"] --- # Auto-PyTorch vs devol *GraphCanon updated Aug 4, 2026* ## Verdict Pick Auto-PyTorch if auto-PyTorch specializes in automatic architecture search and hyperparameter optimization for deep-learning models using PyTorch; pick devol if devolution of neural network architectures through genetic algorithms in Keras for automating design. [Auto-PyTorch](https://github.com/automl/Auto-PyTorch) reports 2.5k GitHub stars, 303 forks, and 75 open issues, last pushed Apr 9, 2024. [devol](https://github.com/joeddav/devol) has 951 stars, 114 forks, and 7 open issues, last pushed May 25, 2023. Figures are from public GitHub metadata via [Auto-PyTorch's repository](https://github.com/automl/Auto-PyTorch) and [devol's repository](https://github.com/joeddav/devol). | | [Auto-PyTorch](/tools/automl-auto-pytorch.md) | [devol](/tools/joeddav-devol.md) | | --- | --- | --- | | Tagline | Automatic architecture search and hyperparameter optimization for PyTorch | Genetic neural architecture search for deep learning models | | Stars | 2,541 | 951 | | Forks | 303 | 114 | | Open issues | 75 | 7 | | Language | Python | Python | | Adopt for | Auto-PyTorch specializes in automatic architecture search and hyperparameter optimization for deep-learning models using PyTorch. | Devolution of neural network architectures through genetic algorithms in Keras for automating design. | | Persona | - | - | | Runtime | - | - | | License | Apache-2.0 | MIT | | Categories | Data & Retrieval, Model Training | Model Training | ## Trust and health _Sourced signals - not a safety guarantee. No winner column._ | | [Auto-PyTorch](/tools/automl-auto-pytorch.md) | [devol](/tools/joeddav-devol.md) | | --- | --- | --- | | Days since push | 846d | 1166d | | Open issues (now) | 75 | 7 | | Owner type | Organization | User | | Full report | [trust report](/tools/automl-auto-pytorch/trust.md) | [trust report](/tools/joeddav-devol/trust.md) | ## Decision facts: Auto-PyTorch - **Adopt for:** Auto-PyTorch specializes in automatic architecture search and hyperparameter optimization for deep-learning models using PyTorch. ## Decision facts: devol - **Pricing:** freemium - Available under MIT license meaning it is free for personal and commercial use but the author cannot be held responsible or liable from damages caused by using DEvol. - **Adopt for:** Devolution of neural network architectures through genetic algorithms in Keras for automating design. ## Choose when ### Choose Auto-PyTorch if… - License: Auto-PyTorch is Apache-2.0, devol is MIT. - Tags unique to Auto-PyTorch: pytorch, tabular-data, time-series-forecasting. - Also covers Data & Retrieval. - Auto-PyTorch ships Docker support for self-hosted deployment. - Use when you need to automate both architectural searches and hyperparameter tuning specifically for PyTorch-based deep learning models. ### Choose devol if… - License: devol is MIT, Auto-PyTorch is Apache-2.0. - Pricing: Available under MIT license meaning it is free for personal and commercial use but the author cannot be held responsible or liable from damages caused by using DEvol.. - Tags unique to devol: computer-vision, genetic-algorithm, keras, machine-learning. - Use DEvol when you need an early proof-of-concept tool to automate the design of neural network architectures with limited parameters, focusing specifically on classification problems. ## When NOT to use Auto-PyTorch - Avoid using it if your AI development focuses on frameworks other than PyTorch. - Do not use when the requirements do not involve deep learning models or you are not interested in automating architecture search and hyperparameter tuning. ## When NOT to use devol - Avoid using DEvol in situations requiring deep or highly complex architectures due to the significant computational expense associated with evolutionary search over such a large parameter space. - Do not use if you lack the infrastructure for parallel processing or do not want to optimize for shorter training epochs, as this can affect model accuracy and fitness evaluations. ## Common questions ### What is the difference between Auto-PyTorch and devol? Auto-PyTorch: Automatic architecture search and hyperparameter optimization for PyTorch. devol: Genetic neural architecture search for deep learning models. See the comparison table for live GitHub stats and shared categories. ### When should I choose Auto-PyTorch over devol? Choose Auto-PyTorch over devol when License: Auto-PyTorch is Apache-2.0, devol is MIT; Tags unique to Auto-PyTorch: pytorch, tabular-data, time-series-forecasting; Also covers Data & Retrieval; Auto-PyTorch ships Docker support for self-hosted deployment; Use when you need to automate both architectural searches and hyperparameter tuning specifically for PyTorch-based deep learning models. ### When should I choose devol over Auto-PyTorch? Choose devol over Auto-PyTorch when License: devol is MIT, Auto-PyTorch is Apache-2.0; Pricing: Available under MIT license meaning it is free for personal and commercial use but the author cannot be held responsible or liable from damages caused by using DEvol.; Tags unique to devol: computer-vision, genetic-algorithm, keras, machine-learning; Use DEvol when you need an early proof-of-concept tool to automate the design of neural network architectures with limited parameters, focusing specifically on classification problems. ### When should I avoid Auto-PyTorch? Avoid using it if your AI development focuses on frameworks other than PyTorch. Do not use when the requirements do not involve deep learning models or you are not interested in automating architecture search and hyperparameter tuning. ### When should I avoid devol? Avoid using DEvol in situations requiring deep or highly complex architectures due to the significant computational expense associated with evolutionary search over such a large parameter space. Do not use if you lack the infrastructure for parallel processing or do not want to optimize for shorter training epochs, as this can affect model accuracy and fitness evaluations. ### Is Auto-PyTorch or devol more popular on GitHub? Auto-PyTorch has more GitHub stars (2,541 vs 951). Stars measure visibility, not whether either tool fits your constraints. ### Are Auto-PyTorch and devol open source? Yes - both are open-source projects on GitHub (Auto-PyTorch: Apache-2.0, devol: MIT). ### Where can I find alternatives to Auto-PyTorch or devol? GraphCanon lists graph-backed alternatives at [Auto-PyTorch alternatives](/tools/automl-auto-pytorch/alternatives) and [devol alternatives](/tools/joeddav-devol/alternatives) ([Auto-PyTorch markdown twin](/tools/automl-auto-pytorch/alternatives.md), [devol markdown twin](/tools/joeddav-devol/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-pytorch-vs-joeddav-devol.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers. ### Which is better maintained, Auto-PyTorch or devol? Auto-PyTorch: Dormant. devol: Dormant. 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-PyTorch and devol? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [Auto-PyTorch trust report](/tools/automl-auto-pytorch/trust); [devol trust report](/tools/joeddav-devol/trust). --- **Machine-readable endpoints** - JSON: [`/api/graphcanon/graph?tool=automl-auto-pytorch`](/api/graphcanon/graph?tool=automl-auto-pytorch) - 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/_