--- title: "Awesome-AutoDL vs devol" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/d-x-y-awesome-autodl-vs-joeddav-devol" tools: ["d-x-y-awesome-autodl", "joeddav-devol"] --- # Awesome-AutoDL vs devol *GraphCanon updated Aug 4, 2026* ## Verdict Pick Awesome-AutoDL if a curated list of resources and links for Automated Deep Learning including AutoDL, NAS, HPO techniques; pick devol if devolution of neural network architectures through genetic algorithms in Keras for automating design. [Awesome-AutoDL](https://github.com/D-X-Y/Awesome-AutoDL) reports 2.3k GitHub stars, 319 forks, and 2 open issues, last pushed Sep 26, 2022. [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 [Awesome-AutoDL's repository](https://github.com/D-X-Y/Awesome-AutoDL) and [devol's repository](https://github.com/joeddav/devol). | | [Awesome-AutoDL](/tools/d-x-y-awesome-autodl.md) | [devol](/tools/joeddav-devol.md) | | --- | --- | --- | | Tagline | Curated list of automated deep learning resources covering AutoDL, NAS, HPO | Genetic neural architecture search for deep learning models | | Stars | 2,339 | 951 | | Forks | 319 | 114 | | Open issues | 2 | 7 | | Language | Python | Python | | Adopt for | A curated list of resources and links for Automated Deep Learning including AutoDL, NAS, HPO techniques. | Devolution of neural network architectures through genetic algorithms in Keras for automating design. | | Persona | - | - | | Runtime | - | - | | License | MIT license provides flexibility in usage and modification, subject to inclusion of the copyright notice and permission notice. | MIT | | Categories | Developer Tools, Model Training | Model Training | ## Trust and health _Sourced signals - not a safety guarantee. No winner column._ | | [Awesome-AutoDL](/tools/d-x-y-awesome-autodl.md) | [devol](/tools/joeddav-devol.md) | | --- | --- | --- | | Days since push | 1408d | 1166d | | Open issues (now) | 2 | 7 | | Full report | [trust report](/tools/d-x-y-awesome-autodl/trust.md) | [trust report](/tools/joeddav-devol/trust.md) | ## Decision facts: Awesome-AutoDL - **Adopt for:** A curated list of resources and links for Automated Deep Learning including AutoDL, NAS, HPO techniques. - **License detail:** MIT license provides flexibility in usage and modification, subject to inclusion of the copyright notice and permission notice. ## 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 Awesome-AutoDL if… - Tags unique to Awesome-AutoDL: autodl, awesome, hyper-parameter-optimization, nas. - Also covers Developer Tools. - Use this resource when you require an exhaustive compilation of AutoDL tools that include Hyper-parameter Optimization (HPO) and Neural Architecture Search (NAS). ### Choose devol if… - 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 Awesome-AutoDL - Avoid using Awesome-AutoDL if you are looking for hands-on code implementation examples or tutorials specific to each tool mentioned. - Do not rely on this repository alone for practical use cases in AutoDL without further investigation into the individual libraries listed, as it primarily serves as a reference guide. ## 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 Awesome-AutoDL and devol? Awesome-AutoDL: Curated list of automated deep learning resources covering AutoDL, NAS, HPO. devol: Genetic neural architecture search for deep learning models. See the comparison table for live GitHub stats and shared categories. ### When should I choose Awesome-AutoDL over devol? Choose Awesome-AutoDL over devol when Tags unique to Awesome-AutoDL: autodl, awesome, hyper-parameter-optimization, nas; Also covers Developer Tools; Use this resource when you require an exhaustive compilation of AutoDL tools that include Hyper-parameter Optimization (HPO) and Neural Architecture Search (NAS). ### When should I choose devol over Awesome-AutoDL? Choose devol over Awesome-AutoDL when 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 Awesome-AutoDL? Avoid using Awesome-AutoDL if you are looking for hands-on code implementation examples or tutorials specific to each tool mentioned. Do not rely on this repository alone for practical use cases in AutoDL without further investigation into the individual libraries listed, as it primarily serves as a reference guide. ### 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 Awesome-AutoDL or devol more popular on GitHub? Awesome-AutoDL has more GitHub stars (2,339 vs 951). Stars measure visibility, not whether either tool fits your constraints. ### Are Awesome-AutoDL and devol open source? Yes - both are open-source projects on GitHub (Awesome-AutoDL: MIT, devol: MIT). ### Where can I find alternatives to Awesome-AutoDL or devol? GraphCanon lists graph-backed alternatives at [Awesome-AutoDL alternatives](/tools/d-x-y-awesome-autodl/alternatives) and [devol alternatives](/tools/joeddav-devol/alternatives) ([Awesome-AutoDL markdown twin](/tools/d-x-y-awesome-autodl/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/d-x-y-awesome-autodl-vs-joeddav-devol.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers. ### Which is better maintained, Awesome-AutoDL or devol? Awesome-AutoDL: 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 Awesome-AutoDL and devol? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [Awesome-AutoDL trust report](/tools/d-x-y-awesome-autodl/trust); [devol trust report](/tools/joeddav-devol/trust). --- **Machine-readable endpoints** - JSON: [`/api/graphcanon/graph?tool=d-x-y-awesome-autodl`](/api/graphcanon/graph?tool=d-x-y-awesome-autodl) - 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/_