Filter sensitive information from free text before sending it to external services or APIs, such as chatbots and LLMs.

Uses just 1% memory while protecting 99% of your personal privacy.

A collection of samples demonstrating techniques for processing documents with Azure AI including AI Foundry, OpenAI, Document Intelligence, etc.

PDF Rendering and Viewing API in Java

The open source PII and PHI redaction and de-identification engine

Examples scripts that showcase how to use Private AI Text to de-identify, redact, hash, tokenize, mask and synthesize PII in text.

VFRAME: Visual Forensics and Metadata Extraction

This solution provides an automated, serverless way to redact sensitive data from PDF files using Google Cloud Services like Data Loss Prevention (DLP), Cloud Workflows, and Cloud Run.

Redux reducers without constants and dispatching!

Python CLI tool to redact and un-redact sensitive data from text files. 🔐📝

Remove content from your digital documents irretrievably instead of just covering it up. Redact text, images, parts of images or drawings for complete confidentiality. iText pdfSweep complies with GDPR for data redaction.

A scrubbing utility to hide sensitive fields from a struct prior to logging

Redact PDF/image-based documents, Word, or CSV/XLSX files using a graphical user interface. Demo: https://huggingface.co/spaces/seanpedrickcase/document_redaction or with try with VLMs: https://huggingface.co/spaces/seanpedrickcase/document_redaction_vlm

A TypeScript library providing a set of guards for LLM (Large Language Model) applications

Philter redacts sensitive information such as PII and PHI in text.

:black_large_square: Classified text? No problem! Sanitize it with ██████ ███ or redact it with [REDACTED]

法律文件脱敏/还原工具 - 智能识别敏感 信息，支持批量处理

Remove content from your digital documents irretrievably instead of just covering it up. Redact text, images, parts of images or drawings for complete confidentiality. iText pdfSweep complies with GDPR for data redaction.

Rust derive macro for redacting sensitive data in std::fmt::Debug

Simple yet powerful tool for identifying and anonymizing personal information in various formats.

.net pdf parsing library

A python client used to interact with the Private AI's API

Easily redact your ActiveRecord Models. Great for use when you use production data in staging or dev.

A lightweight tool that converts directory contents into structured output optimized for LLM interpretation, featuring Git-aware file ordering, secret detection/redaction, token counting, and customizable filtering.

CLI tool to easily redact sensitive information from PDF files.

Reliability gateway for AI tool output: schema-stable, secret-safe, pagination-complete JSON for MCP and CLI agents.

Deterministic LLM contract checks for CI. Replays recorded fixtures, enforces schema/regex/budget rules, generates HTML/JUnit/JSON reports, and comments on PRs. Zero live model calls in CI.

PDF Flattener - Secure PDF documents by making floating redactions and form entries permanent.

Safely redact secrets and optionally anonymise network identifiers in pfSense config.xml exports for secure sharing

A flexible tool to redact JS objects' data