Media
1 item
Description
Automatically redacts Personally Identifiable Information before it reaches web-based LLMs, and restores it in responses. π‘οΈ Private Guard β Your PII Never Leaves Your Browser Private Guard automatically detects and redacts Personally Identifiable Information before it's sent to ChatGPT, Gemini, Claude, or Copilot β and seamlessly restores the original values in the AI's responses. π 3-LAYER DETECTION PIPELINE: β’ 30+ regex patterns β emails, phone numbers, credit cards, IBANs, SSNs, API keys, JWTs, crypto wallets, and more β’ AI-powered NER β on-device Named Entity Recognition detects names, organizations, and locations β’ Active Learning MLP β a neural network that learns YOUR company-specific jargon and project names in real-time π AUTOMATIC RESTORATION: When the AI responds with tags like [PERSON_1], Private Guard instantly restores them to the original values β you see the real answer, the AI never saw the real data. ποΈ LIVE PREVIEW: Before sending, a floating panel shows all detected PII with type icons, editable labels, and one-click dismiss for false positives. π PRIVACY-FIRST: β’ 100% on-device β zero data sent to external servers β’ No tracking, no telemetry, no analytics β’ Per-tab isolation β each tab has its own redaction state β’ Open source β inspect the code yourself β SUPPORTED SITES: β’ ChatGPT (chatgpt.com) β’ Google Gemini (gemini.google.com) β’ Claude (claude.ai) β’ Microsoft Copilot (copilot.microsoft.com) β‘ CUSTOM PROTECTION: β’ Add your own watchlist terms with custom labels β’ Mark any word as sensitive via right-click context menu β’ The built-in neural network learns and remembers your custom terms Built with β€οΈ for your privacy. Free and open source.