Microsoft Presidio
Find and redact personal data before it reaches the model — or the logs.
94
sovereigntyPresidio is Microsoft's open-source PII detection and anonymisation toolkit, and it solves the guardrail problem most teams discover last: personal data flowing into prompts, and from there into a provider's logs and possibly their training data. It detects a wide range of entity types across text and images, supports custom recognisers for your own identifier formats, and offers redaction, masking and reversible pseudonymisation. MIT licensed, and it runs entirely locally — which is the only sane place to do this work.
OPEN SOURCEMITSELF-HOSTLOCAL-FIRST
LicenseMIT
PricingFree, MIT, from Microsoft's open-source organisation.
Open sourceYes
Self-hostableYes
Local-first dataYes
What it does well
- +Purpose-built for the PII problem, and best in class at it
- +Custom recognisers for your own identifier formats
- +Reversible pseudonymisation as well as redaction
- +MIT and fully local — the data never has to move
Where it falls short
- −PII only — not a general safety or injection layer
- −Detection needs tuning per domain to avoid over-redaction
- −Adds a processing step before every model call
Microsoft Presidio as an alternative to
Where Microsoft Presidio shows up in our comparisons, and how it ranked.
Microsoft Presidio head-to-head
Straight comparisons against the tools people weigh it against.