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

# What is Averta

> Add runtime security checkpoints to OpenAI and Anthropic agent loops.

# What is Averta

Averta protects AI agent execution at the points where risk enters or leaves the model loop: user requests, exposed tools, model-requested tool calls, tool results, and final output.

Start with the provider your agent already uses. The wrappers preserve the native provider SDK shape and add [Averta decisions](/concepts/decisions) around supported calls.

<CardGroup cols={2}>
  <Card title="Installation" icon="download" href="/sdk/installation">
    Install the provider wrapper for your runtime.
  </Card>

  <Card title="Quickstart" icon="rocket" href="/quickstart">
    Wrap an OpenAI client and send one guarded request.
  </Card>

  <Card title="Choose an integration" icon="route" href="/choose-integration">
    Pick OpenAI, Anthropic, a custom adapter, or the raw API.
  </Card>

  <Card title="Policies" icon="sliders" href="/concepts/policies">
    Understand why API keys need attached policies.
  </Card>
</CardGroup>

## The Agent Loop

In a tool-using agent, Averta can make decisions before and after the provider call:

* **Request**: evaluate user and developer input before the provider sees it.
* **Tool exposure**: remove tools that should not be available for this request.
* **Tool call**: evaluate model-requested tool calls before your app executes them.
* **Tool result**: evaluate returned tool content before it goes back to the model.
* **Output**: evaluate final text and rewrite or block when [policy](/concepts/policies) requires it.

## Common Paths

<CardGroup cols={2}>
  <Card title="I use OpenAI" icon="code" href="/openai/quickstart">
    Install the OpenAI wrapper for JavaScript or Python and keep your existing OpenAI client.
  </Card>

  <Card title="I use Anthropic" icon="code" href="/anthropic/quickstart">
    Install `@averta-security/sdk-anthropic` and wrap your existing Anthropic client.
  </Card>

  <Card title="I manage policies" icon="sliders" href="/dashboard/policies">
    Create policies, attach them to API keys, and review runtime decisions.
  </Card>

  <Card title="I need a custom adapter" icon="puzzle-piece" href="/custom/overview">
    Use a core package or the raw API when provider wrappers are not enough.
  </Card>
</CardGroup>