Transparency Python Packages

interpret-core

Fit interpretable models. Explain blackbox machine learning.

interpret

Fit interpretable models. Explain blackbox machine learning.

aplr

APLR builds predictive, interpretable regression and classification models using Automatic Piecewise Linear Regression. It often rivals tree-based methods in predictive accuracy while offering smoother and interpretable predictions.

accelerator

The Accelerator is a tool for fast and reproducible processing of eBay-scale datasets on a single computer.

cot-reports

cot_reports is a Python library for fetching the Commitments of Trader reports of the Commodity Futures Trading Commission (CFTC). The following COT reports are supported: Legacy Futures-only, Legacy Futures-and-Options Combined, Supplemental Futures-and-Options Combined, Disaggregated Futures-only, Disaggregated Futures-and-Options Combined, Traders in Financial Futures (TFF) Futures-only and Traders in Financial Futures (TFF) Futures-and-Options Combined.

shapash

🔅 Shapash: User-friendly Explainability and Interpretability to Develop Reliable and Transparent Machine Learning Models

raitap

Fully integrated pipeline to assess the transparency & robustness of AI models

agent-alignment-protocol

Agent Alignment Protocol — the missing trust layer for the agent stack

model-card-toolkit

A toolkit that streamlines and automates the generation of model cards

openpolicedata

The OpenPoliceData (OPD) Python library is the most comprehensive centralized public access point for incident-level police data in the United States. OPD provides easy access to 550+ incident-level datasets from 236 police agencies and 11 entire states. Types of data include traffic stops, use of force, officer-involved shootings, and complaints.

explainx

Explainable AI framework for data scientists. Explain & debug any blackbox machine learning model with a single line of code. We are looking for co-authors to take this project forward. Reach out @ ms8909@nyu.edu

lobbywatch-mcp

MCP server for the Lobbywatch.ch lobby database — Swiss parliamentarians' conflicts of interest

agentguard-eu

EU AI Act compliance middleware for AI agents. Make any LLM-powered agent legally deployable in Europe with 3 lines of code.

imf-fx

High-performance Python client for IMF SDMX 3.0 exchange-rate data (USD, EUR, SDR) for financial modeling and development finance systems.

secop-mcp-server

MCP Server para consultar contratación pública de Colombia (SECOP I y II)

theohe-epias

Energy Exchange Istanbul (EXIST) or Enerji Piyasaları İşletme A.Ş. (EPİAŞ) by its Turkish name is an energy exchange company.

django-public-project

Custom CMS for making public projects, political processes or enquiry commission work more transparent

copilot-usage

Local-first Copilot usage analytics — token tracking, premium estimates, and dashboard

themis-ml

A library that implements fairness-aware machine learning algorithms

ai-provenance-protocol

Official Python SDK for the AI Provenance Protocol

powerlift

Interactive Benchmarking for Machine Learning.

shantay

investigating the EU's DSA transparency database

hyperassist

A modular tool for analyzing machine learning training logs and hyperparameters. It helps developers and researchers gain insight into training dynamics, surface anomalies, and improve model performance through informed tuning.

npdi-oas

A national archive of police data collected by journalists, lawyers, and activists around the country.