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.

python nlp privacy transformers spacy named-entity-recognition data-privacy phi sensitive-data anonymization pii data-anonymization de-identification data-masking personally-identifiable-information data-obfuscation guardrails pii-detection data-redaction image-redactor

• Updated Nov 12, 2026
• Python

Local-first healthcare AI: clinical NER and HIPAA PII de-identification on hardware you control. 2,200+ medical models, 35 model-backed PII languages, and Python, MLX, Android and browser runtimes. Apache-2.0 SDK.

javascript android python nlp swift ios skills healthcare hipaa ner mlx pii on-premise on-device swiftui clinical-nlp pii-detection llm local-llm sovereign-ai

• Updated Nov 11, 2026
• Python

Document (PDF, Word, PPTX ...) extraction and parse API using state of the art modern OCRs + Ollama supported models. Anonymize documents. Remove PII. Convert any document or picture to structured JSON or Markdown

api pdf json ocr extract anonymization pii ocr-python llm

• Updated Dec 8, 2025
• Python

What's in your data? Extract schema, statistics and entities from datasets

python nlp security data-science machine-learning privacy csv avro tabular-data pandas dataset data-analysis graph-data gdpr npi sensitive-data pii network-data dataprofiling data-labels

• Updated Sep 14, 2026
• Python

Secure Vault for Customer PII/PHI/PCI/KYC Records

security privacy encryption database vault application-server compliance passportjs tokenization gdpr data-protection legaltech anonymization pii data-anonymization secure-storage privacy-by-design user-consent piidata ccpa

• Updated Nov 10, 2026
• Go

Local-first privacy guard: anonymize your documents before sharing with LLMs.

privacy transformers named-entity-recognition italian gdpr anonymization pii local-first legal-tech token-classification llm mmbert

• Updated Oct 23, 2026
• Python

AI gets the context. Not your private data. Local-first privacy proxy for browser chat, AI APIs, and coding agents.

security privacy secrets self-hosted openai browser-extension codex data-protection claude pii pii-detection local-first secret-scanning llm chatgpt anthropic llm-privacy privacy-proxy

• Updated Nov 8, 2026
• TypeScript

An AI-powered Personal Identifiable Information (PII) scanner.

python nlp machine-learning cloud ocr image-processing blackhat cybersecurity optical-character-recognition pii pii-detection

• Updated Jan 22, 2025
• Python

A powerful scanner to scan your Filesystem, S3, MySQL, Redis, Google Cloud Storage and Firebase storage for PII and sensitive data.

auditing scanner audit cybersecurity infosec grc pii secrets-management datasecurity

• Updated Oct 23, 2026
• Python

PII2PW turns a target's personal information — name, birthday, phone number, places and so on — into a ranked wordlist of the passwords that person is most likely to have chosen.

password-generator password social-engineering pii

• Updated Nov 2, 2026
• Python

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

ruby redaction privacy named-entity-recognition data-privacy ner anonymization pii data-anonymization personally-identifiable-information data-obfuscation pii-detection data-redaction llm

• Updated May 14, 2026
• Ruby

The local runtime control layer for OpenClaw/Hermes-agent, PII & sensitive credentials protection.

rust ai credentials hermes harness pii secuirty moltbot openclaw hermes-agent

• Updated Jul 13, 2026
• Rust

Scan databases and data warehouses for PII data. Tag tables and columns in data catalogs like Amundsen and Datahub

python data database catalog snowflake data-catalog aws-athena aws-redshift phi pii aws-glue

• Updated Jan 5, 2024
• Python

数据面具 Data Maskit — 专为大模型打造的本地隐私脱敏网关（请求自动打码，回复流式还原；支持 Cursor / Claude Code / Codex / Pi 等任意可配 Base URL 工具）

security privacy proxy openai cursor mitmproxy pii tauri data-masking llm anthropic claude-code

• Updated Nov 12, 2026
• Python

This package features data-science related tasks for developing new recognizers for Presidio. It is used for the evaluation of the entire system, as well as for evaluating specific PII recognizers or PII detection models.

nlp machine-learning natural-language-processing privacy deep-learning transformers spacy named-entity-recognition ner flair pii

• Updated Nov 10, 2026
• Jupyter Notebook

OpenAI's privacy filter NER model architecture implemented in a minimal C++/GGML runtime

ner pii ggml

• Updated Oct 29, 2026
• C++

繁體中文（台灣）個人資料去識別化工具，讓業務文件可以安全地送進 AI 處理 / Reversible Traditional-Chinese (Taiwan) PII de-identification for LLM workflows — fully local

privacy taiwan traditional-chinese gdpr anonymization pii presidio llm ollama claude-code

• Updated Oct 25, 2026
• Python

🚨 slog: Attribute formatting

go golang middleware formatter formatting handler logger logging error structured-logging anonymization pii slog log-level

• Updated Nov 1, 2026
• Go

Native macOS PII removal software with on device Vision OCR and OpenAI privacy filter model

macos swift privacy ai mlx pii

• Updated May 5, 2026
• Swift

Local privacy proxy for AI coding agents. Keep PII and secrets out of LLMs with deterministic pseudonymization.

mcp data-privacy ai-agents pii data-loss-prevention data-masking database-security local-first pseudonymization pii-redaction prompt-injection llm-security privacy-proxy

• Updated Oct 31, 2026
• Python