Pii Detection 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.

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.

argus-redact

Encrypt PII, not meaning. Locally.

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.

pii-codex

A research python package for detecting, categorizing, and assessing the severity of personal identifiable information (PII)

pygarble

Local Python text screening: PII, secrets, profanity, gibberish and redaction. No LLM calls; zero-dependency base with optional local backends.

ferret-scan

Find and redact sensitive data before it leaks — a fast, offline CLI and Go library that detects PII, secrets, and credentials in files and streams, scores them with context-aware confidence, and redacts them format-preserving. Nothing leaves your host.

arcjet

Runtime security for AI apps and agents: prompt injection detection, tool-call authorization, sensitive-data redaction, bot protection, and rate limiting. Drop it into your Python code.

privacyfence

Open-source privacy and approval gateway between AI assistants and your business systems (MCP): human approval, local PII checks and audit for Gmail, Drive, Slack, Salesforce, Jira and more.

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.

ferrogw

Unified AI Gateway for 30+ LLMs (OpenAI, Anthropic, Bedrock, Azure etc) with Caching, Guardrails, A/B test & cost controls. Go-native Fastest & Scalable AI Gateway LiteLLM & Kong AI Gateway alternative.

piighost

Reversible PII masking for LLM agents: piighost replaces personal data with placeholders before the model sees it, then restores the real values in replies and tool calls. LangChain, Pydantic AI, LlamaIndex and Claude Code integrations, plus an OpenAI/Anthropic-compatible proxy.

deutsches-ki-toolkit

Deutschsprachige KI-Infrastruktur für Dokumente, Datenschutz, Suche und RAG: deutsche PII-Erkennung mit Prüfsummen, Komposita-Zerlegung, strukturtreues Chunking, hybrides Retrieval und RAG mit geprüften Quellenangaben. Live-Demo im Browser.

privaite

Self-hosted PII redaction proxy for LLM APIs and agent CLIs. Scrubs names, emails and secrets from Claude Code, Codex and any OpenAI-compatible app before requests leave your machine, tool-call arguments included, then restores them in the reply. Local detection, zero telemetry.

arcjet-sensitive-info-rampart

Runtime security for AI apps and agents: prompt injection detection, tool-call authorization, sensitive-data redaction, bot protection, and rate limiting. Drop it into your Python code.

shim

Local traffic visibility and privacy controls for coding agents. See what Claude Code, Codex and Copilot actually send to the model, and mask secrets and personal data before they leave your machine.

tarja

Detect and mask Brazilian personal identifiers (CPF, CNPJ, CNS, CNJ, título, CNH) in Portuguese text, with check-digit validation. For LGPD work, DLP pipelines, and stripping PII before text reaches an LLM or a RAG index. Apache 2.0, no dependencies.

overwing

Overwing SDK for Python: guardrails for LLM output. Typed client + OpenAI Agents SDK guardrails that score every message before it ships.

maskops

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

declaw

Python SDK for Declaw — security-first sandboxing for AI agents

bedrock-guardrail-firewall

Stop unsafe AI traffic before it spreads with enterprise PII redaction, prompt-injection defense, grounding checks, tamper-evident auditing, and optional Amazon Bedrock plus Presidio controls in one Python file.

proofframe

Ruff for data — Arrow-native data quality in Rust + Python: contracts, canonical fingerprints, keyed diffs, PII & leakage scans, and Ed25519 proof receipts