# pycaret/pycaret

Open-source, low-code AutoML platform for Python. PyCaret 4.0: sklearn-native engine + React control plane.

Repository: https://github.com/pycaret/pycaret
Canonical: https://ross.abutalabs.com/products/pycaret
Homepage: https://pycaret.org
Language: Python
License: NOASSERTION
License Family: other
Topics: data-science, python, machine-learning, pycaret, ml, regression, classification, anomaly-detection, clustering, automl, fastapi, mlops, open-source, react, scikit-learn
Last push: 2026-07-23T00:34:25+00:00

## Health v2 (maintenance only)
Score: 83/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 93, release rhythm 60, longevity 100
- inputs: {"age_days": 2475, "days_push": 42, "days_rel": 132, "gap_med": 0, "n_releases_24m": 2}
- flags: prerelease_only, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 9834, forks 1845 (observed 2026-08-28T04:10:37.427458+00:00)

## What it is
PyCaret is an open-source, low-code AutoML library for Python that wraps scikit-learn to automate training, tuning, and comparison of models for classification, regression, clustering, and anomaly detection. Version 4.0 expands it into a self-hosted ML platform with a FastAPI control plane and React UI for experiments, model registry, deployments, and monitoring.

## Use cases
- train and compare machine learning models with a few lines of code
- automate model selection and hyperparameter tuning
- run classification, regression, clustering, and anomaly detection experiments
- deploy and monitor ML models from a self-hosted web UI
- track experiments and manage a model registry
- detect data drift in production ML models

## When to choose
- you want low-code AutoML without writing boilerplate scikit-learn code
- you need a self-hosted alternative to managed ML platforms that runs locally via docker compose
- you want experiment tracking, model registry, and deployment tooling in one package
- you are a data scientist prototyping models quickly in Python notebooks

## When to avoid
- you need fine-grained manual control over every training step - the abstraction may hide details
- you require a battle-tested production platform - the 4.0 control plane is explicitly work in progress
- you need distributed training on large-scale data beyond scikit-learn's single-node limits
- you depend on the stable 3.x API - that line is frozen with no further commits

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, data-science, workflow-automation, monitoring, api-framework, web-framework
- domain: machine-learning, data-science, artificial-intelligence, developer-tools, self-hosted
- platform: python, self-hosted, cross-platform
- tags: automl, low-code, mlops, scikit-learn, model-training, model-deployment, fastapi, react-ui, model-registry, drift-monitoring, docker, web-server

## Member repositories
- pycaret/pycaret (main) score 83

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:37.427458+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 2026-08-29T17:20:55.380564+00:00, confidence not recorded.
  - readme: https://github.com/pycaret/pycaret (fetched 2026-08-28T04:10:37.427458+00:00, sha 0a463d3eb544)
  - registry_pypi: https://pypi.org/pypi/pycaret/json (fetched 2026-08-29T08:20:25.785678+00:00, sha 525fef19b950)
- Data as of 2026-08-30T08:39:29.467469+00:00.