← Browse tools

AI security & guardrails

Presidio

Extensible PII recognition and configurable de-identification without depending on a particular LLM provider.

Overview

Research summary

Presidio detects and transforms personally identifiable information using named-entity recognition, patterns, checksums, context and custom recognizers. Its analyzer and anonymizer can be embedded in Python workflows or deployed as services, with companion modules for images and structured data. Teams can use it to remove or replace sensitive fields before sending information to an LLM or storing application traces.

Presidio is a data de-identification component, not a general prompt-injection firewall. Originally created at Microsoft, the MIT-licensed project has moved to the independent Data Privacy Stack organization; the current repository and documentation reflect that transition.

Repository summary

Stars
Unavailable
Open issues
Unavailable
Last push
Unavailable
Commits, 90 days
Unavailable
Repository activity
Not scored
Version
Unavailable

Recorded catalogue figures. View repository data and provenance →

Classification

Pricing & services

Paid services unknown

Whether the provider offers paid products or services has not been established.

Licence scope

Implementation

Recorded implementation details and interfaces for Presidio.

Implementation details

Python analyzer, anonymizer, image-redaction and structured-data packages, with service deployment examples.

Languages
Python
Repository type
source

Recorded interfaces and capabilities

Licence scope

Repository

Repository snapshots, release information and recorded maintenance signals.

Repository snapshot

data-privacy-stack/presidio ↗

Stars
Unavailable
Open issues
Unavailable
Last push
Unavailable
Commits, 90 days
Unavailable
Repository activity
Not scored
Archived
Not recorded

Repository activity is a snapshot, not a quality or popularity ranking. It combines recent-push freshness (50%), 90-day commits (30%) and issue pressure (20%).

Maintenance and provenance

Catalogue snapshot
2026-10-06

Documentation

Recorded references and research provenance for this entry.

Recorded sources 4

Research metadata

Research date
2026-10-01
Catalogue snapshot
2026-10-06