Microsoft Presidio
VerifiedMicrosoft's open-source framework for detecting, redacting, masking, and anonymizing PII across text, images, and structured data. 10,000+ GitHub stars.
Frameworks Covered
GDPRCCPAHIPAA
Services
pii-detectiondata-anonymizationdata-redactionimage-redaction
About Microsoft Presidio
Presidio is an open-source data protection and de-identification SDK by Microsoft. It provides fast identification and anonymization modules for private entities in text and images — credit card numbers, names, locations, SSNs, phone numbers, financial data, and more.
Features
- Predefined and custom PII recognizers (NER, regex, rule-based, checksum)
- Multi-language support
- Text, image (including DICOM), and structured data PII detection
- Anonymization operators (replace, encrypt, redact, mask)
- Image redaction via OCR + PII identification
- Deployable via Python, Docker, or Kubernetes
- LLM-based PII/PHI detection via LangExtract
Installation
pip install presidio-analyzer presidio-anonymizer
Loading reviews...