Comparison
autokeras vs mmengine
Verdict
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+; pick mmengine if mMEngine, part of OpenMMLab, serves as a foundational library for training deep learning models with PyTorch in Python.
Markdown twin · autokeras alternatives · mmengine alternatives
GraphCanon updated 3w
vs
Trust & integrity
| Signal | autokeras | mmengine |
|---|---|---|
| Maintenance | Slowing (251d since push) As of 3w · github_public_v1 | Active (18d since push) As of 3w · github_public_v1 |
| Provenance | Not a fork · Organization account As of 3w · github_public_v1 | Not a fork · Organization account As of 3w · github_public_v1 |
| OSV dependency advisories | No lockfile (source not queried) As of 1mo · osv@v1 | No published findings from this source as of 2026-07-11 As of 1mo · osv@v1 |
| deps.dev advisories | Not queried deps.dev@v1 | Not queried deps.dev@v1 |
| OpenSSF Scorecard | Not queried openssf-scorecard@v1 | Not queried openssf-scorecard@v1 |
Tagline
- autokeras
- AutoML library for deep learning
- mmengine
- OpenMMLab Foundational Library for Training Deep Learning Models
Stars
- autokeras
- 9.3k
- mmengine
- 1.5k
Forks
- autokeras
- 1.4k
- mmengine
- 455
Open issues
- autokeras
- 161
- mmengine
- 260
Language
- autokeras
- Python
- mmengine
- Python
Adopt for
- autokeras
- AutoKeras simplifies deep learning model design through automated neural architecture search and is compatible with Python 3.7+ and TensorFlow 2.8.0+.
- mmengine
- MMEngine, part of OpenMMLab, serves as a foundational library for training deep learning models with PyTorch in Python.
Persona
- autokeras
- -
- mmengine
- -
Runtime
- autokeras
- -
- mmengine
- -
License
- autokeras
- Apache-2.0
- mmengine
- MMEngine is distributed under the Apache 2.0 License.
Last pushed
- autokeras
- Nov 25, 2025
- mmengine
- Jul 13, 2026
Categories
- autokeras
- Developer Tools, Model Training
- mmengine
- Model Training
Trust and health
Maintenance
- autokeras
- Slowing (36%)
- mmengine
- Active (82%)
Days since push
- autokeras
- 251d
- mmengine
- 18d
Open issues (now)
- autokeras
- 161
- mmengine
- 260
OSV dependency advisories
- autokeras
- No lockfile (source not queried)
- mmengine
- No published findings from this source as of 2026-07-11
Full report
- autokeras
- Trust report
- mmengine
- Trust report
Shared compatibility
- Python · autokeras: Python runtime · mmengine: Python runtime
Choose autokeras if…
- Tags unique to autokeras: autodl, automl, keras, neural-architecture-search.
- Also covers Developer Tools.
- When your project involves deep learning tasks requiring minimal manual intervention in designing models.
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.
Choose mmengine if…
- Pricing: The core functionality for model training offered through MMEngine is accessible without cost due to its licensing terms (Apache 2.0)..
- Tags unique to mmengine: ai, computer-vision, python, pytorch.
- - Use MMEngine when you are leveraging PyTorch and require a solid foundation for your deep learning model training processes.
When NOT to use mmengine
- - Avoid using MMEngine if your project requires a Python version outside of the supported range (e.g., Python 3.12+).
- - If you are working with frameworks other than PyTorch, MMEngine might not be suitable as it is specifically optimized for PyTorch support.
- - Consider an alternative if you are looking for more flexibility beyond the specific use cases catered to by OpenMMLab and do not want to be tied into their ecosystem.
Explore
Sources
Every stat on this page traces to a dated GitHub sync, license file, enrichment field, or trust scan.
- GitHub stars (keras-team/autokeras) · observed Aug 4, 2026
- GitHub forks (keras-team/autokeras) · observed Aug 4, 2026
- Last push (keras-team/autokeras) · observed Nov 25, 2025
- License file (Apache-2.0) · observed Aug 4, 2026
- Decision facts (enrichment) · observed Jul 17, 2026
- Trust scan (lockfile / OSV) · observed Jul 11, 2026
- GitHub stars (open-mmlab/mmengine) · observed Jul 31, 2026
- GitHub forks (open-mmlab/mmengine) · observed Jul 31, 2026
- Last push (open-mmlab/mmengine) · observed Jul 13, 2026
- License file (Apache-2.0) · observed Jul 31, 2026
- Decision facts (enrichment) · observed Jul 12, 2026
- Trust scan (lockfile / OSV) · observed Jul 11, 2026
GitHub stars on cards: autokeras 9.3k · mmengine 1.5k (synced Aug 4, 2026).
Common questions
- What is the difference between autokeras and mmengine?
- autokeras: AutoML library for deep learning. mmengine: OpenMMLab Foundational Library for Training Deep Learning Models. See the comparison table for live GitHub stats and shared categories.
- When should I choose autokeras over mmengine?
- Choose autokeras over mmengine when Tags unique to autokeras: autodl, automl, keras, neural-architecture-search; Also covers Developer Tools; When your project involves deep learning tasks requiring minimal manual intervention in designing models.
- When should I choose mmengine over autokeras?
- Choose mmengine over autokeras when Pricing: The core functionality for model training offered through MMEngine is accessible without cost due to its licensing terms (Apache 2.0).; Tags unique to mmengine: ai, computer-vision, python, pytorch; - Use MMEngine when you are leveraging PyTorch and require a solid foundation for your deep learning model training processes.
- 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.
- When should I avoid mmengine?
- - Avoid using MMEngine if your project requires a Python version outside of the supported range (e.g., Python 3.12+). - If you are working with frameworks other than PyTorch, MMEngine might not be suitable as it is specifically optimized for PyTorch support. - Consider an alternative if you are looking for more flexibility beyond the specific use cases catered to by OpenMMLab and do not want to be tied into their ecosystem.
- Is autokeras or mmengine more popular on GitHub?
- autokeras has more GitHub stars (9,328 vs 1,482). Stars measure visibility, not whether either tool fits your constraints.
- Are autokeras and mmengine open source?
- Yes - both are open-source projects on GitHub (autokeras: Apache-2.0, mmengine: Apache-2.0).
- Where can I find alternatives to autokeras or mmengine?
- GraphCanon lists graph-backed alternatives at autokeras alternatives and mmengine alternatives (autokeras markdown twin, mmengine markdown twin), 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 mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers.
- Which is better maintained, autokeras or mmengine?
- autokeras: Slowing. mmengine: Active. 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 autokeras and mmengine?
- GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: autokeras trust report; mmengine trust report.