Implementation:CrewAIInc CrewAI Browserbase Load Tool

Knowledge Sources	CrewAI
Domains	Tools, Web_Scraping, Browser_Automation
Last Updated	2026-02-11 00:00 GMT

Overview

Concrete tool for loading webpages in a headless browser using Browserbase's serverless infrastructure provided by CrewAI.

Description

The BrowserbaseLoadTool class extends BaseTool to wrap Browserbase's Python SDK for reliable content extraction from complex web applications. During initialization, it validates the BROWSERBASE_API_KEY environment variable and includes interactive package installation prompting via the click library if the browserbase package is missing (with automatic installation via uv add browserbase). The _run method delegates to the Browserbase client's load_url method, passing configuration for text-only content extraction (text_content), session reuse (session_id), and proxy settings (proxy). The tool optionally uses BROWSERBASE_PROJECT_ID for project-scoped operations.

Usage

Use this tool when CrewAI agents need to reliably load and extract content from JavaScript-heavy websites and single-page applications that cannot be scraped with simple HTTP requests.

Code Reference

Source Location

• Repository: CrewAI
• File: lib/crewai-tools/src/crewai_tools/tools/browserbase_load_tool/browserbase_load_tool.py
• Lines: 1-77

Signature

class BrowserbaseLoadTool(BaseTool):
    name: str = "Browserbase web load tool"
    description: str = "Load webpages url in a headless browser using Browserbase..."
    args_schema: type[BaseModel] = BrowserbaseLoadToolSchema
    api_key: str | None = os.getenv("BROWSERBASE_API_KEY")
    project_id: str | None = os.getenv("BROWSERBASE_PROJECT_ID")
    text_content: bool | None = False
    session_id: str | None = None
    proxy: bool | None = None

    def __init__(self, api_key=None, project_id=None, text_content=False, ...): ...
    def _run(self, url: str): ...

Import

from crewai_tools import BrowserbaseLoadTool

I/O Contract

Inputs

Name	Type	Required	Description
url	str	Yes	Website URL to load in the headless browser
api_key	str or None	No	Browserbase API key (constructor; falls back to BROWSERBASE_API_KEY env var)
project_id	str or None	No	Browserbase project ID (constructor; falls back to BROWSERBASE_PROJECT_ID env var)
text_content	bool or None	No	Extract text-only content (constructor, default False)
session_id	str or None	No	Reuse an existing browser session (constructor)
proxy	bool or None	No	Enable proxy routing (constructor)

Outputs

Name	Type	Description
_run() returns	str	Loaded webpage contents from the headless browser

Usage Examples

Basic Usage

from crewai_tools import BrowserbaseLoadTool

tool = BrowserbaseLoadTool(text_content=True)
content = tool.run(url="https://example.com")

Related Pages

• Principle:CrewAIInc_CrewAI_Built_In_Tool_Selection