Bias Python Packages

interpret-core

Fit interpretable models. Explain blackbox machine learning.

interpret

Fit interpretable models. Explain blackbox machine learning.

aif360

A comprehensive set of fairness metrics for datasets and machine learning models, explanations for these metrics, and algorithms to mitigate bias in datasets and models.

cade

Compass-aligned Distributional Embeddings. Align embeddings from different corpora

langfair

LangFair is a Python library for conducting use-case level LLM bias and fairness assessments

dbias

Detecting Bias and ensuring Fairness in AI solutions

debiai-gui

Bias detection and contextual evaluation tool for your AI projects

xai

XAI - An eXplainability toolbox for machine learning

daindex

Quantifying Health Inequalities Induced by Data and AI Models

risk-of-bias

AI enabled risk of bias assessment tools

aequitas-lite

Bias Auditing & Fair ML Toolkit

equiaudit

Agentic AI framework for fairness auditing of tabular datasets. Offers a Streamlit GUI, headless CLI, and Python API. Installable via pip install equiaudit.

explainx

Explain & debug any blackbox machine learning model with a single line of code.

insurance-fairness

Proxy discrimination auditing for insurance pricing — FCA EP25/2, Consumer Duty, bias metrics

privyfilter

Privy filter is made to give the method for removing/accommodating for unethical bias in data.

powerlift

Fit interpretable models. Explain blackbox machine learning.

ytdebunk

This project aims to automate the extraction of MP3 audio from a given YouTube video link, transcribe the audio content, and analyze the transcriptions using Agentic AI to identify logical fallacies and incorrect claims made by YouTubers.

nlpguard

NLPGuard: A Framework for Mitigating the use of Protected Attributes in NLP

fmm-fairness-eval

Foundation Model for Medicine — fairness/bias evaluation CLI for medical AI (research)

canonical-sets

Exposing Algorithmic Bias with Canonical Sets

fairlens

Identify bias and measure fairness of your data

judge-bench

Probe judge behavior for position, verbosity, self-preference, paraphrase, anchoring, and calibration failures.

demoparity

Python package for demographic auditing of LLM prompts and responses

indoctrine-ai

Agent Indoctrination – AI Safety, Bias, Fairness, Ethics & Compliance Testing Framework 🚀