Data Privacy Python Packages

presidio-analyzer

An open-source framework for detecting, redacting, masking, and anonymizing sensitive data (PII) across text, images, and structured data. Supports NLP, pattern matching, and customizable pipelines.

presidio-anonymizer

An open-source framework for detecting, redacting, masking, and anonymizing sensitive data (PII) across text, images, and structured data. Supports NLP, pattern matching, and customizable pipelines.

datafog

Offline PII firewall for AI agents and LLM apps: fast local detection and redaction, Claude Code hook, LiteLLM guardrail. Zero network calls, one dependency.

presidio-image-redactor

An open-source framework for detecting, redacting, masking, and anonymizing sensitive data (PII) across text, images, and structured data. Supports NLP, pattern matching, and customizable pipelines.

presidio-structured

An open-source framework for detecting, redacting, masking, and anonymizing sensitive data (PII) across text, images, and structured data. Supports NLP, pattern matching, and customizable pipelines.

ethyca-fides

The Privacy Engineering & Compliance Framework

maskops

High-speed PII masking as a Polars plugin — powered by Rust

diffprivlib

Diffprivlib: The IBM Differential Privacy Library

presidio

An open-source framework for detecting, redacting, masking, and anonymizing sensitive data (PII) across text, images, and structured data. Supports NLP, pattern matching, and customizable pipelines.

cloakpii

PII masking + AES-256-GCM encryption + PIPL/PDPA/GDPR compliance reporting for cross-border data transfers. Python CLI.

pycanon

pyCANON is a Python library and CLI to assess the values of the parameters associated with the most common privacy-preserving techniques.

armos

Open source PII masking middleware for OpenAI and Anthropic SDKs

pydantic-prism

Tag pydantic fields once; derive API/storage/audit/LLM faces with PII classification and a ref graph that survives projection.

clip-protocol

This repository contains an adaption of differential privacy algorithms on learning analitics

acro

Tools for the Semi-Automatic Checking of Research Outputs. These are tools for researchers to use as drop-in replacements for common analysis commands.

tabayyan

Saudi-aware PII detection & redaction for LLM pipelines. Checksum-validates National ID, Iqama, IBAN, CR, VAT, +966 numbers, passport & more; evasion-resistant; redacts before OpenAI/Anthropic with PDPL/NDMO audit. Local-first, zero telemetry.

preserve-pii

Privacy-preserving PII detection & scrubbing for LLM prompts — local-first, reversible, 15+ countries. Python library, CLI, OpenAI-compatible API gateway, and a 100% in-browser demo.

enterprise-rag-patterns

FERPA/HIPAA/GDPR-compliant RAG patterns: identity-scoped retrieval, audit logging, and framework adapters for regulated enterprise AI

nightfall

Python Data Loss Prevention (DLP) SDK - Nightfall Developer Platform

apii

Keep Arabic & Gulf personal data off the LLM — local-first, reversible PII tokenization (CLI, proxy, and a Claude Code hook).

tabulus

Postgres MCP server that redacts PII & secrets before your AI agent sees them. Read-only, agent-first.

trasgodp

Local differential privacy mechanisms

aisdc

Tools for the statistical disclosure control of machine learning models

carnaval

Reversible PII anonymization for LLM pipelines: mask names, emails and bank details before text reaches a cloud LLM, then restore them in the response. Local-first, encrypted vault, 6 languages. Python, Apache-2.0.