# modAL-python/modAL

A modular active learning framework for Python

Repository: https://github.com/modAL-python/modAL
Canonical: https://ross.abutalabs.com/products/modal
Homepage: https://modAL-python.github.io/
Language: Python
License: MIT
License Family: permissive
Topics: scikit-learn, machine-learning, python, active-learning, machine-learning-library, machine-learning-algorithms, machine-learning-api, active-learning-module, bayesian-optimization
Last push: 2024-02-26T15:38:11+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 3214, "days_push": 919, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2362, forks 325 (observed 2026-08-28T04:06:40.923012+00:00)

## What it is
modAL is a modular active learning framework for Python 3, built on top of scikit-learn. It lets users rapidly assemble active learning workflows with interchangeable query strategies, uncertainty measures, and custom components.

## Use cases
- reduce labeling costs by selecting the most informative samples to annotate
- run uncertainty sampling on a scikit-learn classifier
- implement custom query strategies for active learning research
- perform active regression with limited labeled data
- prototype Bayesian optimization-style sample selection loops

## When to choose
- you use scikit-learn estimators and want to add active learning with minimal code
- you need modular, replaceable components to experiment with novel AL algorithms
- you want a well-documented Python library for labeling-efficiency experiments

## When to avoid
- you need deep learning or GPU-based active learning out of the box
- you need a framework with frequent releases and active maintenance
- you want a turnkey annotation platform rather than a Python library

## Facets
- artifact type: framework
- maturity: maintenance
- function: machine-learning
- domain: machine-learning, data-science
- platform: python
- tags: active-learning, scikit-learn, bayesian-optimization, query-strategies

## Member repositories
- modAL-python/modAL (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:40.923012+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 2026-08-30T02:36:04.490926+00:00, confidence not recorded.
  - readme: https://github.com/modAL-python/modAL (fetched 2026-08-28T04:06:40.923012+00:00, sha 52bc24993579)
  - homepage: https://modAL-python.github.io/ (fetched 2026-08-29T10:16:35.853847+00:00, sha 44136fa355b3)
- Data as of 2026-08-30T08:39:29.467469+00:00.