# keras-team/autokeras

AutoML library for deep learning

Repository: https://github.com/keras-team/autokeras
Canonical: https://ross.abutalabs.com/products/autokeras
Homepage: http://autokeras.com/
Language: Python
License: Apache-2.0
License Family: permissive
Topics: automl, neural-architecture-search, automated-machine-learning, python, deep-learning, machine-learning, autodl, tensorflow, keras
Last push: 2025-11-25T02:26:35+00:00

## Health v2 (maintenance only)
Score: 52/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 53, release rhythm 24, longevity 100
- inputs: {"age_days": 3209, "days_push": 282, "days_rel": 294, "gap_med": null, "n_releases_24m": 1}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 9326, forks 1389 (observed 2026-08-28T04:10:30.527785+00:00)

## What it is
AutoKeras is an AutoML library for deep learning built on Keras, developed by DATA Lab at Texas A&M University. It automates model architecture search and training for tasks like image, text, and tabular classification and regression with a simple high-level API.

## Use cases
- automatically train an image classifier without designing a CNN
- perform neural architecture search for my dataset
- build a tabular data regression model with AutoML
- find the best deep learning model without manual tuning
- classify text with automated model selection
- quickly prototype deep learning models with minimal code

## When to choose
- you want automated model selection and hyperparameter tuning on top of Keras/TensorFlow
- you lack deep learning expertise but need decent models fast
- you want a simple fit/predict API for common ML tasks

## When to avoid
- you need full manual control over architecture and training details
- you work outside TensorFlow/Keras ecosystems with strict constraints
- you need cutting-edge state-of-the-art performance rather than automated convenience

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, deep-learning, llm-training
- domain: machine-learning, deep-learning, data-science
- platform: python, cross-platform
- tags: automl, neural-architecture-search, keras, tensorflow, hyperparameter-tuning, autodl

## Member repositories
- keras-team/autokeras (main) score 52

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:30.527785+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:22:29.622837+00:00, confidence not recorded.
  - readme: https://github.com/keras-team/autokeras (fetched 2026-08-28T04:10:30.527785+00:00, sha a3e4507612d7)
  - homepage: http://autokeras.com/ (fetched 2026-08-29T08:22:30.833154+00:00, sha bd7242b4dfd0)
  - site_page: https://autokeras.com/install (fetched 2026-08-29T08:22:30.843443+00:00, sha 92d93476d54d)
  - site_page: https://autokeras.com/about (fetched 2026-08-29T08:22:30.847526+00:00, sha 774f2830feda)
  - registry_pypi: https://pypi.org/pypi/autokeras/json (fetched 2026-08-29T08:22:30.849565+00:00, sha f530d0c0a79b)
  - site_page: https://autokeras.com/tutorial/faq (fetched 2026-08-29T08:22:30.845738+00:00, sha 2966f805b180)
- Data as of 2026-08-30T08:39:29.467469+00:00.