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

# Privacy and data

> Where your data lives, how it is isolated, and how Token keeps credentials out of the AI.

Token is built so it can be useful without putting your data at risk. The safety
rules are structural, enforced by the server rather than asked of the AI, so they
hold even under a message that tries to bend them.

## Your instance is your own

Your Token runs on its own server with its own storage. Your conversations,
memory, and settings live there, separate from any other customer.

## Every conversation is sandboxed

Each request Token handles runs in its own locked-down session.

<CardGroup cols={2}>
  <Card title="Isolated" icon="box">
    A session can only see its own conversation's data, never another chat's.
  </Card>

  <Card title="No open internet" icon="globe-lock">
    Sessions cannot roam the web. They reach the outside world only through the
    controlled gateway that enforces approvals.
  </Card>

  <Card title="Least privilege" icon="user-shield">
    Sessions run with minimal permissions and only read-only access to Token's own
    code.
  </Card>

  <Card title="The host decides" icon="server">
    The AI proposes actions; the server checks and runs them. Policy is never left
    to the AI.
  </Card>
</CardGroup>

## Your credentials stay with the server

When you connect a tool, the credential is held by the server, encrypted, and
never handed to the AI or included in what is sent to the model. When Token uses
a tool, the server attaches the credential at the last moment, on the way out.
The AI only ever sees that a tool succeeded or failed, not the secret behind it.

## What is stored

To give Token history and memory, your messages and any attachments are stored on
your own instance, in its database and per-chat folders. You stay in control:
admins can review activity with [`/token-audit`](/slash-commands) and manage what
Token is allowed to do.

## The AI model

Token uses Anthropic's Claude models through their commercial API to generate
replies, so your messages are sent to Anthropic to produce a response.

<Note>
  Anthropic does not use data submitted through its commercial API to train its
  models. See [Anthropic's commercial terms](https://www.anthropic.com/legal/commercial-terms)
  for the authoritative details.
</Note>