Algorithmic Fairness Python Packages

fairmedfm

Fairness metrics for any classification or segmentation model (pip install fairmedfm) and a fairness benchmark of medical imaging foundation models.

ethicml

Package for evaluating the performance of methods which aim to increase fairness, accountability and/or transparency

fixout

Algorithmic inspection for trustworthy ML models

agorai

AgorAI: A Python package for fair, transparent decision-making and democratic synthesis that combines social choice theory, welfare-economics aggregation, and LLM-driven opinion synthesis

riskaudit

A Python toolkit (riskaudit) to audit any healthcare risk-stratification model for label-choice bias - how much real need it leaves behind when trained on cost. Reproduces the Obermeyer et al. (2019) audit; worked example on MEPS.

fairsearchcore

Python library with the core algorithms used to do FA*IR ranking.

fairsearchdeltr

Disparate Exposure in Learning To Rank for Python