--- title: "nas-env vs devol" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/gomerudo-nas-env-vs-joeddav-devol" tools: ["gomerudo-nas-env", "joeddav-devol"] --- # nas-env vs devol *GraphCanon updated Aug 4, 2026* ## Verdict Pick nas-env if nas-env offers an OpenAI Gym environment for Neural Architecture Search in Python under MIT license; pick devol if devolution of neural network architectures through genetic algorithms in Keras for automating design. [nas-env](https://github.com/gomerudo/nas-env) reports 31 GitHub stars, 3 forks, and 0 open issues, last pushed May 4, 2020. [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 [nas-env's repository](https://github.com/gomerudo/nas-env) and [devol's repository](https://github.com/joeddav/devol). | | [nas-env](/tools/gomerudo-nas-env.md) | [devol](/tools/joeddav-devol.md) | | --- | --- | --- | | Tagline | Simple OpenAI Gym environment for Neural Architecture Search (NAS) | Genetic neural architecture search for deep learning models | | Stars | 31 | 951 | | Forks | 3 | 114 | | Open issues | 0 | 7 | | Language | Python | Python | | Adopt for | nas-env offers an OpenAI Gym environment for Neural Architecture Search in Python under MIT license. | Devolution of neural network architectures through genetic algorithms in Keras for automating design. | | Persona | - | - | | Runtime | - | - | | License | MIT | MIT | | Categories | Model Training | Model Training | ## Trust and health _Sourced signals - not a safety guarantee. No winner column._ | | [nas-env](/tools/gomerudo-nas-env.md) | [devol](/tools/joeddav-devol.md) | | --- | --- | --- | | Days since push | 2282d | 1166d | | Open issues (now) | 0 | 7 | | Full report | [trust report](/tools/gomerudo-nas-env/trust.md) | [trust report](/tools/joeddav-devol/trust.md) | ## Decision facts: nas-env - **Adopt for:** nas-env offers an OpenAI Gym environment for Neural Architecture Search in Python under MIT license. ## 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 nas-env if… - Tags unique to nas-env: openai-gym, python, reinforcement-learning. - When you need to implement NAS algorithms using reinforcement learning with compatibility to OpenAI Gym - Leaner open-issue backlog (0). ### 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: automl, computer-vision, deep-learning, genetic-algorithm. - 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 nas-env - If you require a fully documented package as documentation for nas-env remains under development - During production phases when stability is crucial because nas-env is still undergoing architectural changes ## 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 nas-env and devol? nas-env: Simple OpenAI Gym environment for Neural Architecture Search (NAS). devol: Genetic neural architecture search for deep learning models. See the comparison table for live GitHub stats and shared categories. ### When should I choose nas-env over devol? Choose nas-env over devol when Tags unique to nas-env: openai-gym, python, reinforcement-learning; When you need to implement NAS algorithms using reinforcement learning with compatibility to OpenAI Gym; Leaner open-issue backlog (0). ### When should I choose devol over nas-env? Choose devol over nas-env 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: automl, computer-vision, deep-learning, genetic-algorithm; 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 nas-env? If you require a fully documented package as documentation for nas-env remains under development During production phases when stability is crucial because nas-env is still undergoing architectural changes ### 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 nas-env or devol more popular on GitHub? devol has more GitHub stars (951 vs 31). Stars measure visibility, not whether either tool fits your constraints. ### Are nas-env and devol open source? Yes - both are open-source projects on GitHub (nas-env: MIT, devol: MIT). ### Where can I find alternatives to nas-env or devol? GraphCanon lists graph-backed alternatives at [nas-env alternatives](/tools/gomerudo-nas-env/alternatives) and [devol alternatives](/tools/joeddav-devol/alternatives) ([nas-env markdown twin](/tools/gomerudo-nas-env/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/gomerudo-nas-env-vs-joeddav-devol.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers. ### Which is better maintained, nas-env or devol? nas-env: 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 nas-env and devol? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [nas-env trust report](/tools/gomerudo-nas-env/trust); [devol trust report](/tools/joeddav-devol/trust). --- **Machine-readable endpoints** - JSON: [`/api/graphcanon/graph?tool=gomerudo-nas-env`](/api/graphcanon/graph?tool=gomerudo-nas-env) - 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/_