Bias Detection Python Packages

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.

bias-detection-mcp

AI bias detection + fairness assessment MCP. Required by EU AI Act Article 10 + NYC Local Law 144. MIT

dataeval

Python library for analyzing data quality and its impact on model performance across classification and object-detection tasks.

jurity

[ACM 2024] Jurity: Fairness & Evaluation Library

dataeval-plots

Python library for analyzing data quality and its impact on model performance across classification and object-detection tasks.

model-diagnostics

Tools for diagnostics and assessment of (machine learning) models

rai-governance-platform

Open-source bias testing framework for LLMs — detect gender, racial & cultural bias in any language model via TF-IDF divergence scoring

langfair

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

optipfair

Structured pruning, knowledge distillation, and fairness analysis for Large Language Models.

ai-safety-tester

LLM Security Testing Framework | CVE-style severity scoring, prompt injection detection, bias analysis | Strict mypy typing | Fast CI/CD with pytest markers | PyPI: ai-safety-tester

trustlens

Open-source Python library for evaluating ML model reliability beyond accuracy — with calibration, failure, and fairness diagnostics for informed deployment decisions.

daml

Python library for analyzing data quality and its impact on model performance across classification and object-detection tasks.

judgebias

Point it at your LLM judge + your judgments; get per-bias effect sizes with 95% CIs and concrete corrections.

rho-eval

Behavioral auditing toolkit for LLMs — audit any model across 8 dimensions (factual, toxicity, bias, sycophancy, reasoning, refusal, deception, over-refusal) using teacher-forced confidence probes.

wefe

WEFE: The Word Embeddings Fairness Evaluation Framework. WEFE is a framework that standardizes the bias measurement and mitigation in Word Embeddings models. Please feel welcome to open an issue in case you have any questions or a pull request if you want to contribute to the project!

judgecal

Statistically rigorous, batch-first reliability auditing for LLM judges & reward models — clustered-bootstrap CIs, McNemar, BH-FDR, power/MDE, planted-bias validation. No API key required.

unbias-plus

Bias detection and debiasing: identify segments, classify severity, get reasoning and replacements, full neutral rewrite

judicator

Judging LLM-as-a-Judge — a screening tool for bias and miscalibration.

fairsense-agentix

An agentic fairness and AI-risk analysis platform: bias detection for text, images, and datasets.

ai-fairness-toolkit

AI Fairness and Explainability Toolkit (AFET) is an open-source project aimed at providing tools and frameworks to assess, visualize, and mitigate bias in machine learning models. It supports multiple ML frameworks and offers a comprehensive suite of metrics and visualization components to enhance model transparency and fairness.

knowledge-fidelity

Compress LLMs while auditing whether they still know truth vs myths. SVD compression + false-belief detection in one toolkit.

trusteval-ai

Enterprise LLM Evaluation & Responsible AI Framework — Benchmark bias, hallucination, PII leakage, and toxicity across Healthcare, BFSI, Retail & Legal industries. Supports OpenAI, Anthropic, Gemini & HuggingFace. Python SDK + CLI + Web Dashboard. 191 tests. Compliance-ready reports.

aiscan

Scan AI models for problems

biasx

Python library detecting and explaining gender bias in face classification models