Add web browsing capabilities to Agno - Browserbase Documentation

Get up and running with data extraction in under 5 minutes.

Setup

Install packages:

pip install browserbase playwright agno

Set environment variables:

export BROWSERBASE_API_KEY=your_api_key_here

To get env variables, go over the Dashboard’s Settings tab:

Then copy your API Key directly from the input and set the BROWSERBASE_API_KEY environment variable.

Basic example

Python

from agno.agent import Agent
from agno.tools.browserbase import BrowserbaseTools

# Create extraction agent
agent = Agent(
    name="Data Extractor",
    tools=[
        BrowserbaseTools(),
    ],
    instructions=[
        "Extract content clearly and format nicely",
        "Always close sessions when done",
    ],
    markdown=True,
)

# Extract quotes
response = agent.run("""
    Go to https://quotes.toscrape.com and:
    1. Get the first 3 quotes with authors
    2. Navigate to page 2  
    3. Get 2 more quotes from page 2
""")

print(response.content)

Essential functions

Function	Purpose	Usage
`navigate_to`	Go to URL	”Navigate to https://example.com”
`get_page_content`	Extract HTML	”Get the page content”
`screenshot`	Take screenshot	”Take screenshot, save as ‘page.png‘“
`close_session`	End session	”Close the current session”

Expected output

The agent response should contain five quotes with their authors: three from the first page and two from the second. The wording and formatting depend on the model response.

Cleanup

Ask the agent to close the current session using close_session, then confirm it ended in the Sessions dashboard. If the agent fails to close it, release the session using Manage browser sessions.

Python SDK

Use the Browserbase SDK from Python.

Browser contexts

Reuse cookies and browser state across sessions.

⌘I

​Setup

​Basic example

​Essential functions

​Expected output

​Cleanup

​Related guides