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

# CrewAI

> Auto-instrument CrewAI crews. Tasks, agent conversations, and tool calls captured via OpenTelemetry.

The CrewAI integration uses OpenTelemetry under the hood, so it works with any CrewAI version that emits OTel spans (most current versions do).

## Install

```bash theme={null}
pip install decimalai
```

CrewAI itself is not bundled — install it separately if you don't already have it.

## Use

```python theme={null}
import decimalai
decimalai.init(api_key="dai_sk_...", crewai=True)

# Crew tasks and agent interactions are traced
crew.kickoff()
```

## What gets captured

* Each task in the crew as a span
* Agent-to-agent conversations
* Tool calls with inputs and outputs
* LLM generations underneath each agent's reasoning step

## Caveats

* Manifest detection captures tool **names** only — schemas aren't always exposed through CrewAI's API. Use [`register_manifest()`](/sdk/python/manifests) for schema-aware tracking.
* Multi-crew setups: each crew is its own DecimalAI "agent" by default. Pass `agent_name=` to `init()` if you want them unified.

## What's next

<CardGroup cols={2}>
  <Card title="Multi-agent guide" icon="users" href="/guides/multi-agent">
    Modeling crew-of-crews patterns.
  </Card>

  <Card title="Manifests" icon="layer-group" href="/sdk/python/manifests">
    Register a manifest explicitly to capture tool schemas.
  </Card>
</CardGroup>