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

# Anthale Quickstart for Your First Guarded Integration

> Create an API key, create a first policy, and connect Anthale through an OpenAI, LangChain, or direct SDK path in Python or TypeScript.

This quickstart gets one Anthale path working end to end. For most teams, the fastest path is an existing integration. Use the direct SDK path when you need framework-independent control or when Anthale does not already wrap the client you use.

## Before you start

* Access to the Anthale dashboard for the Organization you want to use.
* A Python or Node.js environment, depending on the path you choose.
* One workflow you can test, such as a customer support assistant, a retrieval flow, or an internal copilot.

## Recommended integration paths

<Columns cols={2}>
  <Card title="OpenAI Integration for Python" icon="sparkles" href="/docs/quickstart/python/openai">
    Wrap the OpenAI Python client with Anthale when your application already uses the OpenAI SDK.
  </Card>

  <Card title="OpenAI Integration for TypeScript" icon="sparkles" href="/docs/quickstart/typescript/openai">
    Wrap the OpenAI Node client with Anthale when your application already uses the OpenAI SDK.
  </Card>

  <Card title="LangChain Agent Integration" icon="bot" href="/docs/quickstart/python/langchain-agent-middleware">
    Add Anthale middleware to a Python LangChain agent workflow with tools and agent execution.
  </Card>

  <Card title="LangChain Chat Integration" icon="messages-square" href="/docs/quickstart/python/langchain-chat-model">
    Guard a standalone LangChain chat model in Python when you do not need full agent middleware.
  </Card>
</Columns>

## Direct SDK paths

Use the direct SDK path when you want explicit control over `allow`, `detect`, `redact`, and `block`, or when you are building a custom integration Anthale does not already wrap.

<Columns cols={2}>
  <Card title="Python Direct SDK Path" icon="code" href="/docs/quickstart/python">
    Send Anthale enforcement requests directly from Python and handle the runtime action in your own application code.
  </Card>

  <Card title="TypeScript Direct SDK Path" icon="code" href="/docs/quickstart/typescript">
    Send Anthale enforcement requests directly from TypeScript and handle the runtime action in your own application
    code.
  </Card>
</Columns>

## Recommended order

1. Create an [API key](/docs/learn/api-keys/create-an-api-key) for the service that will call Anthale.
2. Create a [first policy](/docs/quickstart/first-policy) for one trust boundary.
3. Start with the integration guide that matches the client or framework already in your application.
4. Use the [Python Direct SDK Path](/docs/quickstart/python) or [TypeScript Direct SDK Path](/docs/quickstart/typescript) only when you need lower-level control.

## Result

After you finish one quickstart path, you will have an Anthale API key stored server-side, a policy you can test, and an application path that can enforce Anthale decisions before risky content continues.