TrustyAI

TrustyAI is an open source toolkit for explainability, bias detection, and monitoring in machine learning workflows.

TrustyAI delivers a specialized suite of tools for Explainable AI (XAI) and model monitoring within the KIE ecosystem. It implements industry standard algorithms (LIME and SHAP) to provide local and global explanations for model predictions. The platform tracks fairness through specific metrics: Statistical Parity Difference (SPD) and Disparate Impact (DI) identify bias in real time. Designed for Kubernetes native environments, TrustyAI integrates with OpenShift and Quarkus to ensure enterprise models remain transparent and compliant.

https://trustyai.ai/