--- title: "FEDOT vs autokeras" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/aimclub-fedot-vs-keras-team-autokeras" tools: ["aimclub-fedot", "keras-team-autokeras"] --- # FEDOT vs autokeras *GraphCanon updated Aug 4, 2026* ## Verdict Pick FEDOT if fEDOT: auto-generates ML pipelines using evolutionary algorithms, supports various tasks including classification, regression, clustering, time series prediction; pick autokeras if autoKeras simplifies deep learning model design through automated neural architecture search and is compatible with Python 3.7+ and TensorFlow 2.8.0+. [FEDOT](https://fedot.readthedocs.io) reports 709 GitHub stars, 94 forks, and 82 open issues, last pushed Jul 27, 2026. [autokeras](http://autokeras.com/) has 9.3k stars, 1.4k forks, and 161 open issues, last pushed Nov 25, 2025. Figures are from public GitHub metadata via [FEDOT's repository](https://github.com/aimclub/FEDOT) and [autokeras's repository](https://github.com/keras-team/autokeras). | | [FEDOT](/tools/aimclub-fedot.md) | [autokeras](/tools/keras-team-autokeras.md) | | --- | --- | --- | | Tagline | Automated modeling and machine learning framework FEDOT | AutoML library for deep learning | | Stars | 709 | 9,328 | | Forks | 94 | 1,393 | | Open issues | 82 | 161 | | Language | Python | Python | | Adopt for | FEDOT: auto-generates ML pipelines using evolutionary algorithms, supports various tasks including classification, regression, clustering, time series prediction. | AutoKeras simplifies deep learning model design through automated neural architecture search and is compatible with Python 3.7+ and TensorFlow 2.8.0+. | | Persona | - | - | | Runtime | - | - | | License | BSD-3-Clause | Apache-2.0 | | Categories | Model Training | Developer Tools, Model Training | ## Trust and health _Sourced signals - not a safety guarantee. No winner column._ | | [FEDOT](/tools/aimclub-fedot.md) | [autokeras](/tools/keras-team-autokeras.md) | | --- | --- | --- | | Maintenance | Active (82%) | Slowing (36%) | | Days since push | 7d | 251d | | Open issues (now) | 82 | 161 | | Full report | [trust report](/tools/aimclub-fedot/trust.md) | [trust report](/tools/keras-team-autokeras/trust.md) | ## Shared compatibility - **Python**: [FEDOT](/tools/aimclub-fedot.md) - Python runtime; [autokeras](/tools/keras-team-autokeras.md) - Python runtime ## Decision facts: FEDOT - **Adopt for:** FEDOT: auto-generates ML pipelines using evolutionary algorithms, supports various tasks including classification, regression, clustering, time series prediction. ## Decision facts: autokeras - **Adopt for:** AutoKeras simplifies deep learning model design through automated neural architecture search and is compatible with Python 3.7+ and TensorFlow 2.8.0+. ## Choose when ### Choose FEDOT if… - License: FEDOT is BSD-3-Clause, autokeras is Apache-2.0. - Tags unique to FEDOT: evolutionary-algorithms, genetic-programming, hyperparameter-optimization, structural-learning. - For projects requiring automated generative design of machine-learning pipelines suitable for a wide range of tasks and data types ### Choose autokeras if… - License: autokeras is Apache-2.0, FEDOT is BSD-3-Clause. - Tags unique to autokeras: autodl, deep-learning, keras, machine-learning. - Also covers Developer Tools. - When your project involves deep learning tasks requiring minimal manual intervention in designing models. ## When NOT to use FEDOT - In scenarios with strict real-time requirements due to its optimization time - For environments where only specific ML libraries are acceptable and FEDOT's integrations do not meet those needs - When the project specifically requires a non-evolutionary approach for pipeline design ## When NOT to use autokeras - When working with Python versions older than 3.7 or TensorFlow versions older than 2.8.0, as AutoKeras is not compatible. - If your project emphasizes transparent, understandable model architecture over automated generation without human oversight. ## Common questions ### What is the difference between FEDOT and autokeras? FEDOT: Automated modeling and machine learning framework FEDOT. autokeras: AutoML library for deep learning. See the comparison table for live GitHub stats and shared categories. ### When should I choose FEDOT over autokeras? Choose FEDOT over autokeras when License: FEDOT is BSD-3-Clause, autokeras is Apache-2.0; Tags unique to FEDOT: evolutionary-algorithms, genetic-programming, hyperparameter-optimization, structural-learning; For projects requiring automated generative design of machine-learning pipelines suitable for a wide range of tasks and data types. ### When should I choose autokeras over FEDOT? Choose autokeras over FEDOT when License: autokeras is Apache-2.0, FEDOT is BSD-3-Clause; Tags unique to autokeras: autodl, deep-learning, keras, machine-learning; Also covers Developer Tools; When your project involves deep learning tasks requiring minimal manual intervention in designing models. ### When should I avoid FEDOT? In scenarios with strict real-time requirements due to its optimization time For environments where only specific ML libraries are acceptable and FEDOT's integrations do not meet those needs When the project specifically requires a non-evolutionary approach for pipeline design ### When should I avoid autokeras? When working with Python versions older than 3.7 or TensorFlow versions older than 2.8.0, as AutoKeras is not compatible. If your project emphasizes transparent, understandable model architecture over automated generation without human oversight. ### Is FEDOT or autokeras more popular on GitHub? autokeras has more GitHub stars (9,328 vs 709). Stars measure visibility, not whether either tool fits your constraints. ### Are FEDOT and autokeras open source? Yes - both are open-source projects on GitHub (FEDOT: BSD-3-Clause, autokeras: Apache-2.0). ### Where can I find alternatives to FEDOT or autokeras? GraphCanon lists graph-backed alternatives at [FEDOT alternatives](/tools/aimclub-fedot/alternatives) and [autokeras alternatives](/tools/keras-team-autokeras/alternatives) ([FEDOT markdown twin](/tools/aimclub-fedot/alternatives.md), [autokeras markdown twin](/tools/keras-team-autokeras/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/aimclub-fedot-vs-keras-team-autokeras.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers. ### Which is better maintained, FEDOT or autokeras? FEDOT: Active. autokeras: 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 FEDOT and autokeras? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [FEDOT trust report](/tools/aimclub-fedot/trust); [autokeras trust report](/tools/keras-team-autokeras/trust). --- **Machine-readable endpoints** - JSON: [`/api/graphcanon/graph?tool=aimclub-fedot`](/api/graphcanon/graph?tool=aimclub-fedot) - 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/_