Ellen Art School
Native macOS & iOS

Sanitize AI

Stop leaking critical PII to cloud models. Intercept sensitive text, soft PII, and raw face pixels on-device before uploading to ChatGPT or Gemini—then rehydrate outputs seamlessly.

100% On-Device ProcessingZero Server Data Collection
Sanitize AI Icon

Sanitize AI

Zero-Trust PII & Soft Data Barrier

Local SLM & RegEx Engine

How Sanitize AI Works

A secure bidirectional firewall between your private information and cloud AI providers.

1

Intercept & Redact

Paste text or drop files/images into Sanitize AI. Local RegEx and local SLMs swap sensitive terms (e.g., John Doe) for placeholder tokens like [Client A].

2

Safely Query Cloud AI

Copy the redacted prompt into ChatGPT, Gemini, or Claude without risking leaks of personal records, medical data, or identity clues.

3

Rehydrate Outputs

Paste the AI’s answer back into Sanitize AI. Token mappings automatically restore original terms back into your text locally.

Built for Security & Speed

Combining high-speed rule matching with contextual Small Language Models running on Apple Silicon.

Fast RegEx Engine

Scrub standard PII like emails, phone numbers, and SSNs with near-zero latency using configurable rule presets.

Soft PII & Context AI

Catches obfuscated phone numbers ("One-Two-Three...") and subtle "Soft PII" (like job titles combined with company names) that could deanonymize you.

True Pixel Face Anonymization

Unlike simple overlays or blurs, Sanitize AI detects faces in images and permanently zeroes out raw face pixels so models can't reconstruct identities.

Biometric Vaults

Store reusable prompt templates and token mapping history in an encrypted vault locked behind Face ID or macOS authentication.

Batch File Processing

Drag and drop PDFs, TXT, or CSV files into the drop zone for bulk local scrubbing before uploading to external workflows.

RAM-Only Test Chat

Test redacted prompts against the local SLM to verify model comprehension. Chat runs entirely in volatile RAM and purges when closed.

Local SLM Hardware Requirements

To utilize the optional Local Small Language Model features (Plus & Pro tiers), devices require at least 8 GB of RAM and 4 GB of available storage. Models are downloaded on-demand directly inside the app and can be removed at any time.

Simple, Transparent Tiering

Download for free and subscribe directly within the macOS or iOS App Store.

MonthlyYearly (Save up to 18%)

Free

Basic Protection

$0 / forever
  • Basic PII scrubbing (email, SSN, etc.)
  • Fast RegEx Engine
  • Basic Rule Setting
  • Encrypted Prompt Storage
  • Token Mapping
Get Free App
Popular

Plus

For Power Users

$69.99 / year

★ Includes 1-Week Free Trial

  • Local SLM Contextual AI Scrubbing
  • Soft PII Context Detection
  • Local Face Pixel Anonymization
  • Single PDF, TXT & CSV Drop Zone
  • Persistent Token Mapping Vault
Get App to Subscribe

Pro

Maximum Privacy

For Power Users & Professionals

$139.99 / year
  • Everything in Plus
  • Batch PDF, TXT & CSV Drop Zone
  • Custom RegEx Ruleset Builder
  • Custom AI Redaction Instructions
  • RAM-Only Sandbox Chat
Get App to Subscribe

Subscriptions are handled through Apple in-app purchases and can be canceled anytime via the App Store.

Frequently Asked Questions

Everything you need to know about Sanitize AI and local privacy protection.

No single tool or automated system can guarantee 100% complete anonymity. Language models and statistical tools are designed to catch standard PII, obfuscated patterns, soft PII, and facial features. However, unique phrasing or niche context could potentially be re-identified.

Sanitize AI gives you an aggressive defense-in-depth layer on your own hardware before your data ever touches cloud AI, significantly reducing your risk profile.