A NumPy-only toolkit for auditing attribute decodability and potential data leakage in frozen medical-image features.
-
Updated
Sep 16, 2026 - Python
A NumPy-only toolkit for auditing attribute decodability and potential data leakage in frozen medical-image features.
A minimal, reproducible explainable-AI demo using SHAP values on tabular data. Trains RandomForest or LogisticRegression models, computes global and local feature importances, and visualizes results through summary and dependence plots, all in under 100 lines of Python.
Laravel Boilerplate for building REST APIs
GlassAlpha is an open-source toolkit for deterministic, regulator-ready ML audit reports. One command generates comprehensive, reproducible audits with TreeSHAP explainability, fairness metrics, calibration analysis, and robustness testing for XGBoost, LightGBM, and logistic regression models (binary classification, tabular data only).
Model audit software
🔬 Drop in any ML model → get SHAP explainability, fairness audit & drift detection in seconds
A conservation-honest diagnostic framework for auditing early-universe models and separating physical dynamics from descriptive bookkeeping.
Promptfoo is an open-source CLI and TypeScript/Node.js library for evaluating, red-teaming, and security-testing LLM applications, agents, and RAG pipelines. It runs deterministic prompt evals with model-graded and rule-based assertions, generates dynamic adversarial attack probes across 50+ vulnerability categories (prompt injection, jailbreaks…
A lightweight and framework-native audit log package for Laravel applications.
Leakage-resistant audit of an interpretable weather-symptom-disease cascade.
CLI framework for auditing LLM providers and detecting model substitution.
A Claude skill for everyone who inherited an Excel model and got told "the guy who built it left". type /sheet-happens in any chat, or simply say 'map this Excel model and get one interactive HTML: how every sheet, block and line item connects, plus an audit of hardcodes, error cells and circular refs. Runs 100% on your machine.
To associate your repository with the model-audit topic, visit your repo's landing page and select "manage topics."