> ## Documentation Index
> Fetch the complete documentation index at: https://pasteguard.com/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Introduction

> AI gets the context. Not your private data. PasteGuard protects Browser Chat, Apps & APIs, and Coding Agents.

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.

<Frame>
  <img className="block dark:hidden" src="https://mintcdn.com/pasteguard/n91bKVZxJdh1QbnG/images/comparison-light.png?fit=max&auto=format&n=n91bKVZxJdh1QbnG&q=85&s=8833f1686f7cad83c78ec9283fd0105f" alt="PasteGuard masks names, emails, and API keys before they reach AI" width="1816" height="768" data-path="images/comparison-light.png" />

  <img className="hidden dark:block" src="https://mintcdn.com/pasteguard/n91bKVZxJdh1QbnG/images/comparison-dark.png?fit=max&auto=format&n=n91bKVZxJdh1QbnG&q=85&s=cdda0d068e2a8dd168b6e45b9781ef45" alt="PasteGuard masks names, emails, and API keys before they reach AI" width="1816" height="768" data-path="images/comparison-dark.png" />
</Frame>

## One Privacy Layer

<CardGroup cols={3}>
  <Card title="Browser Chat" icon="comment" href="/use-cases/chat">
    ChatGPT, Claude, and Gemini. Experimental browser extension.
  </Card>

  <Card title="Apps & APIs" icon="plug" href="/use-cases/api-integration">
    Apps, SDKs, and internal AI products.
  </Card>

  <Card title="Coding Agents" icon="code" href="/use-cases/coding-tools">
    Codex, Claude Code, Cursor, Windsurf, and other coding agents.
  </Card>
</CardGroup>

## 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.

<CardGroup cols={2}>
  <Card title="Regulated Teams" icon="shield-check" href="/use-cases/regulated-teams">
    Patterns for finance, legal, healthcare, consulting, and other sensitive work.
  </Card>

  <Card title="Local-First Privacy" icon="lock" href="/concepts/local-first-privacy">
    What stays local, what reaches providers, and how placeholders are restored.
  </Card>
</CardGroup>

## Privacy Modes

| Mode      | How it works                                                                                                               |
| --------- | -------------------------------------------------------------------------------------------------------------------------- |
| **Mask**  | Replace PII and secrets with placeholders, send to the upstream AI service, restore supported placeholders in the response |
| **Route** | Requests with sensitive data stay on your local LLM; other requests go to the configured cloud provider                    |

## Next Steps

<CardGroup cols={2}>
  <Card title="Quickstart" icon="rocket" href="/quickstart">
    Run PasteGuard as a local proxy
  </Card>

  <Card title="Installation" icon="box" href="/installation">
    Configure Docker, persistent logs, and detector settings
  </Card>
</CardGroup>