# autogluon/autogluon

Fast and Accurate ML in 3 Lines of Code

Repository: https://github.com/autogluon/autogluon
Canonical: https://ross.abutalabs.com/products/autogluon
Homepage: https://auto.gluon.ai/
Language: Python
License: Apache-2.0
License Family: permissive
Topics: automl, machine-learning, data-science, deep-learning, ensemble-learning, computer-vision, natural-language-processing, structured-data, object-detection, gluon, transfer-learning, pytorch, automated-machine-learning, scikit-learn, autogluon, tabular-data, hyperparameter-optimization, time-series, forecasting, python
Last push: 2026-08-26T16:36:58+00:00

## Health v2 (maintenance only)
Score: 90/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 72, longevity 100
- inputs: {"age_days": 2592, "days_push": 7, "days_rel": 27, "gap_med": 105.0, "n_releases_24m": 7}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 10617, forks 1181 (observed 2026-08-28T04:10:42.570858+00:00)

## What it is
AutoGluon is an AutoML library that automates machine learning on tabular data, time series, text, and images with just a few lines of Python code. It automatically selects and ensembles models—from classic ML algorithms to deep learning foundation models—to achieve strong predictive performance.

## Use cases
- train accurate models on tabular data with minimal code
- forecast time series automatically
- classify text and images without tuning hyperparameters
- build ensembles of ML models automatically
- quickly prototype predictive models on a CSV dataset
- automate model selection and hyperparameter optimization

## When to choose
- you want strong predictive accuracy without ML expertise or manual tuning
- you need fast baselines on tabular, time series, text, or image data
- you want automated ensembling and hyperparameter search out of the box

## When to avoid
- you need full control over individual model architectures and training pipelines
- you require minimal dependencies or very lightweight deployment
- you need real-time low-latency inference with strict resource constraints

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, deep-learning, data-science, nlp, computer-vision
- domain: machine-learning, data-science, computer-vision, time-series
- platform: python, windows
- tags: automl, ensemble-learning, hyperparameter-optimization, tabular-data, time-series-forecasting, transfer-learning, pytorch, scikit-learn, natural-language-processing, linux, macos, gpu

## Member repositories
- autogluon/autogluon (main) score 90

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:42.570858+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 2026-08-29T17:18:28.208523+00:00, confidence not recorded.
  - readme: https://github.com/autogluon/autogluon (fetched 2026-08-28T04:10:42.570858+00:00, sha 32ea86d6a2b6)
  - homepage: https://auto.gluon.ai/ (fetched 2026-08-29T08:17:36.288951+00:00, sha eb9ae665bf76)
- Data as of 2026-08-30T08:39:29.467469+00:00.