---
site: steel.dev
collection: docs
canonical_url: https://steel.dev/docs/integrations/crewai
markdown_url: https://steel.dev/docs/integrations/crewai.md
content_signal: ai-input=yes, ai-train=yes, search=yes
title: Build a CrewAI crew on Steel
description: Give a CrewAI agent a tool that reads web pages through a Steel browser, and let a crew of agents research and write from them.
summary: Give a CrewAI agent a tool that reads web pages through a Steel browser, and let a crew of agents research and write from them.
type: integration-guide
reviewed: 2026-11-13
prerequisites: []
related:
  - https://steel.dev/docs/integrations/ai-sdk.md
  - https://steel.dev/docs/integrations/openai-agents-sdk.md
  - https://steel.dev/docs/integrations/claude-agent-sdk.md
  - https://steel.dev/docs/integrations/langgraph.md
  - https://steel.dev/docs/integrations/pydantic-ai.md
agent_setup: https://setup.steel.dev/install.md
docs_index: https://steel.dev/docs/sitemap.md
---

# Build a CrewAI crew on Steel

CrewAI runs a crew of agents. Each agent has a role and works on a task, and a sequential crew passes each task's result to the next task. To give an agent the web, you write a CrewAI tool that calls [Scrape](https://steel.dev/docs/control/scrape). Scrape loads the page in a Steel browser, runs its JavaScript, and returns the page as Markdown. There is no session to create or release. CrewAI is a Python framework.

## Before you begin

- Python 3.10 to 3.13. CrewAI does not support Python 3.14 yet.
- A Steel API key in the `STEEL_API_KEY` environment variable. See [API keys](https://steel.dev/docs/account/api-keys).
- An OpenAI API key in the `OPENAI_API_KEY` environment variable. CrewAI reads it from there.

Install CrewAI and the Steel SDK.

```sh
python3 -m venv .venv
source .venv/bin/activate
pip install crewai steel-sdk
```

## Set up the integration

### Build the crew

This program defines a `scrape` tool with CrewAI's `@tool` decorator. The model reads the tool's docstring to decide when to call it. A researcher agent uses the tool to read a list of stories on a [practice page](https://steel.dev/practice/news), and a writer agent then summarizes what the researcher found.

```python file=crew.py
from crewai import LLM, Agent, Crew, Process, Task
from crewai.tools import tool
from steel import Steel

steel = Steel()


@tool("Scrape a web page")
def scrape(url: str) -> str:
    """Load a web page in a Steel browser and return its content as Markdown."""
    result = steel.scrape(url=url, format=["markdown"])
    return result.content.markdown or ""


llm = LLM(model="gpt-6-luna", api="responses")

researcher = Agent(
    role="Web researcher",
    goal="Find facts on the web pages that a task names, and keep the link of each.",
    backstory="You read pages with the scrape tool and never invent facts.",
    tools=[scrape],
    llm=llm,
)

writer = Agent(
    role="Writer",
    goal="Turn research notes into a short, accurate summary.",
    backstory="You write plain summaries and keep every link from the notes.",
    llm=llm,
)

research = Task(
    description="Scrape https://steel.dev/practice/news and list the top 3 stories.",
    expected_output="The top 3 stories, each with its title, link and points.",
    agent=researcher,
)

summary = Task(
    description="Summarize the stories from the research in one sentence each.",
    expected_output="Three bullet points, one for each story, with its link.",
    agent=writer,
)

crew = Crew(
    agents=[researcher, writer],
    tasks=[research, summary],
    process=Process.sequential,
)
result = crew.kickoff()
print(result.raw)
```

Only the researcher has the tool. The writer works from the researcher's result, which the crew passes to the second task.

### Run the program

```sh
python crew.py
```

The program prints the writer's summary. Its wording changes from run to run.

```text nocopy
- [Steel Speaks Rust and Go](https://steel.dev/blog/rust-go-sdks) — Steel announces SDKs for Rust and Go.
- [Why Browser Agents Fail in Production](https://steel.dev/blog/why-browser-agents-fail-in-production) — The post explains why browser agents fail in production.
- [Steel Browser: the open-source browser API](https://github.com/steel-dev/steel-browser) — Steel Browser is an open-source browser API.
```

To see each agent's steps and tool calls, pass `verbose=True` to `Crew`.

### Add Steel features and a session

- To load a page through a [Steel proxy](https://steel.dev/docs/stealth/proxies), or to wait for a page that shows its content late, pass `use_proxy=True` or `delay` to `steel.scrape()`. See [Control how the page loads](https://steel.dev/docs/control/scrape#control-how-the-page-loads).
- Scrape returns one page for each call. When an agent must sign in, click, or keep cookies from page to page, give it tools that drive a [session](https://steel.dev/docs/sessions) instead. [Connect Playwright to Steel](https://steel.dev/docs/integrations/playwright) shows how a program connects to a session.

## Next steps

- [CrewAI documentation](https://docs.crewai.com)
- [Cookbook starter](https://github.com/steel-dev/steel-cookbook/tree/main/examples/crewai): a researcher and a reporting analyst that work on a task that you set in `TASK`.
