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

# Auto-Instrumentation [BETA]

> Portkey's auto-instrumentation allows you to instrument tracing and logging for multiple LLM/Agent frameworks and view the logs, traces, and metrics in a single place.

<Warning>
  This feature is currently in beta. We're rolling out support for more frameworks and will also be exposing the otel collector endpoint to view the traces and logs.
</Warning>

## Overview

There's two main components to auto-instrumentation:

1. The Portkey SDK, which can be used for tracing along with being used as a unified API gateway.
2. The Portkey dashboard, which can be used to view the logs, traces, and metrics.

## Portkey SDK

Using portkey for auto-instrumentation is fairly straightforward. A one line addition at the top of your code execution will start sending traces and logs to Portkey.

```python theme={"system"}
from portkey import Portkey

Portkey(api_key="{{PORTKEY_API_KEY}}", instrumentation=True)
```

## Portkey Dashboard

The Portkey dashboard can be used to view the logs, traces, and metrics.

<img src="https://mintcdn.com/portkey-docs/Buc1Vm2P31GSPm3S/images/product/opentelemetry.png?fit=max&auto=format&n=Buc1Vm2P31GSPm3S&q=85&s=bc982b581d5ce60764d207b004b4677f" alt="Portkey dashboard auto-instrumentation image" width="2860" height="2087" data-path="images/product/opentelemetry.png" />

## Supported Frameworks

We currently support auto-instrumentation for the following frameworks:

* [CrewAI](/integrations/agents/crewai#auto-instrumentation)
* [LangGraph](/integrations/agents/langgraph#auto-instrumentation)

<Note>
  To request support for another framework, please reach out to us on [Discord here](https://portkey.ai/community).
</Note>