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.
Tech stack & purpose
Presidio is an open-source Python framework for detecting, redacting, masking, and anonymizing personally identifiable information (PII) across text, images, and structured data. It combines natural language processing, pattern matching, and customizable pipelines to identify sensitive data in multiple languages and domains, with particular support for German-language healthcare, legal, and financial documents through specialized recognizers and bilingual spaCy NLP models. The framework includes multiple components—an analyzer for PII detection, an anonymizer for data transformation, an image redactor, and a structured data processor—along with sample applications demonstrating integration with large language models via OpenAI for secure, privacy-preserving chat interfaces.
Community & reference links
Languages
Contributors (top 30 of 213)
- Omri Mendels339 commits
- Sharon Hart177 commits
- shiranrubin112 commits
- sharon90 commits
- Nava Vaisman Levy71 commits
- dependabot[bot]71 commits · 0 followers
- balteravishay55 commits
- Elad Iwanir52 commits
- Itye40 commits
- Shiran Rubin40 commits
- Copilot39 commits
- omri37439 commits
- Avishay39 commits
- Itye Richter35 commits
- Nile Wilson28 commits
- Tamir Kamara19 commits
- Ron Shakutai18 commits
- Avishay balter18 commits
- Tomer Rosenthal16 commits
- Bianca Furtuna13 commits
- jichaowang02-lang11 commits
- torosent7 commits
- Ilana Kantorov7 commits
- Dor Lugasi-Gal6 commits
- Siwoo Jung6 commits
- Roey Ben Chaim5 commits
- Limor Lahiani5 commits
- Tolulope Jegede4 commits
- Steve Haigh4 commits
- mark van tilburg4 commits
