Piixie Docs

Piixie creates anonymized copies of documents. The original file stays in place, and the output copy is written to the local Piixie data directory for review and export.

Open Piixie and let the local model download on first run.
Drop a document or choose it from the file picker.
Select redaction, replacement, or synthetic mode.
Review the anonymized copy and replacements table.
Send the safe copy to an LLM, ticket, test fixture, or collaborator.

Anonymization modes

Redaction

PII is replaced with visible redaction markers. Use it when the output should reveal no sensitive values at all.

Replacement

PII becomes stable tokens such as name and email placeholders. Use it when consistency matters during review.

Synthetic

PII is replaced with fake values generated locally through Piixie's bundled Faker bridge. Use it for demos, training samples, tests, and prompts that need natural-looking context.

Supported files

Current desktop support covers text files, Markdown, DOCX, PDFs, and data-table files. The goal is to support every file type that needs anonymization without CGO dependencies.

OCR is not a separate requirement for image-backed documents. Piixie's local model is vision-capable, so the anonymization pipeline can inspect rendered pages and image regions directly instead of depending on a brittle OCR preprocessing step.

Why LLMs for PII detection

PII is not always a clean token shaped like an email address, credit card number, or phone number. In real documents, private information is often implied by relationships between fields, surrounding paragraphs, tables, captions, images, and repeated references. Piixie uses a local LLM because those relationships are exactly where rule-based detection starts to break down.

A rules engine can match [email protected]. It cannot reliably decide that "the claimant", "her dependent", "the upstairs tenant", and an account row three pages later all refer to the same private person. An LLM can use context to connect those references, classify the entity, choose the right anonymization mode, and preserve consistency in the rewritten document.

Read the detection guide

Automation

Piixie runs as a server and as a CLI so privacy checks fit into existing workflows. See the automation guide for batch commands and deployment patterns.

Open automation guide

External LLMs

Local anonymization comes first. Teams can connect external providers after the raw document has been anonymized.

sequenceDiagram
  participant User
  participant Piixie
  participant LocalModel as Local model
  participant Provider as Optional external LLM
  User->>Piixie: Open raw document
  Piixie->>LocalModel: Detect and transform PII
  LocalModel-->>Piixie: Anonymized content
  Piixie-->>User: Safe copy
  User->>Provider: Send safe copy when needed

Privacy model

Piixie is local-first, not cloud-first. Extraction, model execution, and output review all happen locally. External providers are optional and only used after anonymization.