Search Packages

holisticai

This is an open-source tool to assess and improve the trustworthiness of AI systems.

optipfair

Structured pruning and bias visualization for Large Language Models. Tools for LLM optimization and fairness analysis.

agorai

Democratic AI: Multi-agent opinion aggregation with fairness guarantees

oracle-guardian-ai

Oracle Guardian AI Open Source Project

the-fairly-project

Bias detection Toolkit: Chrome Extension, Python Package, SOTA research paper docs.

equalityml

Algorithms for evaluating fairness metrics and mitigating unfairness in supervised machine learning

demv

Debiaser for Multiple Variables, a model- and data- agnostic method to improve fairness in binary and multi-class classification tasks

posnoise

POSNoise: An Effective Countermeasure Against Topic Biases in Authorship Analysis

equalityml-fork2

Evidence-based tools and community collaboration to end algorithmic bias, one data scientist at a time.