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.
Presidio is an open-source privacy framework that finds sensitive personal information in text, images, and structured data, then redacts, masks, or anonymizes it. Developers use it to build customizable data-protection and de-identification pipelines.
Latest release 2.2.365 — Release 2.2.365 · 25 Oct 2026
5 files for GitHub Copilot, Codex, OpenCode and Claude Code: presidio copilot-instructions.md, presidio recognizers.instructions.md, presidio yaml-config.instructions.md, presidio AGENTS.md and 1 more — 6,710 tokens loaded in every session.
.github/copilot-instructions.md A 1,679 tok .github/instructions/recognizers.instructions.md A 2,195 tok .github/instructions/yaml-config.instructions.md A 1,345 tok AGENTS.md A 1,478 tok CLAUDE.md A 13 tok These files are data-privacy-stack/presidio's own configuration — they tell GitHub Copilot, Codex, OpenCode and Claude Code how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.