Local by default
Extraction, entity detection, and rewriting happen on the user's machine with a bundled local model path.
Local-first anonymization for LLM workflows
Piixie
Scrub private data from documents, tables, and notes before you paste, upload, or automate anything with an LLM.
- Redact, replace, or synthesize
- Runs on your machine
- Desktop, server, and CLI workflows
- Bring your own LLM when needed
Built for LLM-era privacy reviews
Documents stay local by default
Works before your favorite AI tools
Designed for individuals and organizations
Anonymize before the prompt leaves your desk.
Piixie is for people who need the productivity of LLMs without casually handing raw PII to another service. It prepares safer copies locally so downstream tools receive only what they should see.
Flexible outputs
Choose strict redaction, stable replacement tokens, or realistic synthetic values that preserve document shape.
Automation ready
Run Piixie interactively, through the CLI, or as an internal server for repeatable workflows and team usage.
Three modes for three kinds of risk.
Different workflows need different tradeoffs. Piixie lets you decide how much context survives in the anonymized copy.
- Redaction removes sensitive values entirely.
- Replacement keeps stable placeholders for review and traceability.
- Synthetic mode keeps realistic structure for demos, tests, and model prompts.
Product screenshots for the workflows teams actually run.
Desktop review, synthetic replacement tables, and automation all share the same privacy-first pipeline.
Redaction
Mask names, emails, phone numbers, and sensitive spans with explicit redaction blocks.
Synthetic
Generate plausible substitutes that keep documents readable while removing real identities.
CLI and server
Batch documents from scripts or centralize anonymization behind an internal team endpoint.
Local-first architecture, optional external LLMs.
Piixie is designed to minimize what ever leaves the device. When teams choose external models, they can send safer material downstream.
How Piixie fits into an LLM workflow.
The same pipeline powers desktop usage, command-line batches, and organization-scale server deployments.
flowchart LR
A[Raw document] --> B[Extract locally]
B --> C[Detect PII]
C --> D{Choose mode}
D --> E[Redact]
D --> F[Replace]
D --> G[Synthesize]
E --> H[Safe copy]
F --> H
G --> H
H --> I[Prompt, share, archive, or test]
Pricing that follows local compute reality.
Start free, then scale from individual usage to centralized team deployments without forcing raw documents into a cloud anonymizer.
Free
For occasional local anonymization.
$0/ month
- 1 local anonymization per day
- Desktop app access
- Redaction, replacement, and synthetic modes
Pro
For people anonymizing documents every workday.
$10/ month
- 10 daily local anonymizations
- Short-burst local processing
- Preferred local-first workflows
Scale-up
For teams that need a shared internal service.
Talkto us
- Central Piixie server setup
- Multiple users and higher daily volume
- Reduced individual workstation load
Enterprise
For larger organizations with deeper controls.
Custompricing
- Centralized authentication
- Single sign-on and security reviews
- Custom features and support
Docs, changelog, and operating guides are live.
Use the documentation site as the source of truth for supported file types, local setup, automation, server mode, and product updates.