Skip to main content
PasteGuard masks PII and secrets before they reach ChatGPT, Claude, Gemini, your API provider, Codex, or Claude Code. You keep the originals. Providers see placeholders. It is built for teams that want to use AI with real context but cannot send raw client, customer, production, or credential data to model providers.
PasteGuard masks names, emails, and API keys before they reach AI

​
One Privacy Layer

Browser Chat

ChatGPT, Claude, and Gemini. Experimental browser extension.

Apps & APIs

Apps, SDKs, and internal AI products.

Coding Agents

Codex, Claude Code, Cursor, Windsurf, and other coding agents.

​
Built For Raw Data Limits

PasteGuard gives teams a local or self-hosted control point before requests reach AI providers. Use it when the current options are manual redaction, no cloud AI for sensitive work, local-only models where a cloud provider would work better, or custom masking code in every app.

Regulated Teams

Patterns for finance, legal, healthcare, consulting, and other sensitive work.

Local-First Privacy

What stays local, what reaches providers, and how placeholders are restored.

​
Privacy Modes

ModeHow it works
MaskReplace PII and secrets with placeholders, send to the upstream AI service, restore supported placeholders in the response
RouteRequests with sensitive data stay on your local LLM; other requests go to the configured cloud provider

​
Next Steps

Quickstart

Run PasteGuard as a local proxy

Installation

Configure Docker, persistent logs, and detector settings