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.
- 12k
- Python
- MIT
- 1 d ago
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.
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.
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
What's in your data? Extract schema, statistics and entities from datasets
AI gets the context. Not your private data. Local-first privacy proxy for browser chat, AI APIs, and coding agents.
A powerful scanner to scan your Filesystem, S3, MySQL, Redis, Google Cloud Storage and Firebase storage for PII and sensitive data.
Filter sensitive information from free text before sending it to external services or APIs, such as chatbots and LLMs.
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.
OpenAI's privacy filter NER model architecture implemented in a minimal C++/GGML runtime
Token classification model, used with transformers.
Local privacy proxy for AI coding agents. Keep PII and secrets out of LLMs with deterministic pseudonymization.
Never give AI companies your secrets! A local LLM-based privacy filter for LLM users. Seamless integration with your existing AI tools as a Python library / OpenAI SDK replacement / API Gatetway / Web Server.
Native macOS PII removal software with on device Vision OCR and OpenAI privacy filter model
純前端文件去識別化工具:PDF/Word/Excel/TXT/Markdown 自動偵測個資、遮罩預覽、人工覆核、CSV 編碼表可還原,資料不出電腦
Discover, mask, and verify sensitive data in SQL databases — an auditable scan → mask → validate workflow for safe database copies.
Go library for masking sensitive data via struct tags — passwords, emails, IDs, credit cards, and more
🛡️ PII Guard is an LLM-powered tool that detects and manages Personally Identifiable Information (PII) in logs — designed to support data privacy and GDPR compliance
Token classification model, used with gliner2.
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.
Offline PII firewall for AI agents and LLM apps: fast local detection and redaction, Claude Code hook, LiteLLM guardrail. Zero network calls, one dependency.
Real-time, one-way CDC from production MongoDB, MySQL, MariaDB, PostgreSQL and Redis to secondary databases or GCS, with PII masking and encryption. Built for analytics, cold storage and disaster recovery.
Redact PDF/image-based documents, Word, or CSV/XLSX files using a graphical user interface. Demo with local VLMs: https://huggingface.co/spaces/seanpedrickcase/document_redaction_vlm
Token classification model, used with transformers.
Text extraction with Jev: field extraction, PII detection and exact quotes, built on TypeSafe's Jev.
Application and python script to identify, remove, and/or recode personally identifiable information (PII) from field experiment datasets.
Swap the personal details out of your AI prompts before they are sent. On-device detection, no server, no account.
Reversible PII masking for LLM calls and RAG, Polish-first: checksum-validated PESEL, NIP and IBAN, Polish names in every case, stable tokens, streaming restore and Haystack components.
Personal Identifiable Information (PII) entity detection and performance enhancement with synthetic data generation
An anonymizer tool for replacing PII and similar data in dev/test databases copied from production
Claude Code hooks that guard secrets and PII before they reach the Anthropic API
Token classification model, used with transformers.
Caido's passive workflow to find potential leaked secrets, PII, and sensitive fields.
Local-first tool that strips emails, secrets, paths, and other identifying content out of your prompts before they reach a cloud LLM — and rehydrates the response locally.
🛡️ Claude Code plugin that blocks prompts containing secrets, API keys, and PII before they reach Claude.
Self-hosted AI gateway for small teams: a key per person, budgets that fall back to local models, PII masking and free SSO.
Token classification model, used with transformers.
Keep secrets and personal data on your Mac while you use Claude Code, Codex, pi or opencode. A local proxy masks them before a request leaves, and restores them in the reply.
Token classification model, used with transformers.
Token classification model, used with transformers.
Truly redact PDFs: flatten, verify, in-browser
Runs in the browser on Hugging Face
Which tool removes personal data from Turkish documents?
Runs in the browser on Hugging Face
Mask secrets & PII in logs, .env, JSON & HAR, in-browser
Runs in the browser on Hugging Face
Redact API keys, PII & faces in screenshots, in-browser
Runs in the browser on Hugging Face
Redact keys, names & faces in screen recordings
Runs in the browser on Hugging Face
Bleep names, numbers & secrets in audio, in-browser
Runs in the browser on Hugging Face