It seems that CrewAI is more suited to passive browser automations (no Puppeeter tool etc.). But I would like to create an active browsing agent that performs interactive tasks such as form-filling, shopping cart actions, or ticket booking, instead of just passive research tasks.
Is if possible with CrewAI? How? Some uses cases you could share?
If no possible with CrewAI, could you recommend the best framework (and setup of tools).
Thanks
PS: I’m a fresh rookie developer
@ardavan16 CrewAI allows you to implement any SDK out there as a custom tool.
I see Puppeteer doesn’t provide a Python SDK, but you can use the Playwright Python SDK as an alternative.
So, use the Playwright Python SDK and adjust the code below:
from typing import Type
from crewai.tools import BaseTool
from pydantic import BaseModel, Field
class MyToolInput(BaseModel):
"""Input schema for MyCustomTool."""
argument: str = Field(..., description="Description of the argument.")
class MyCustomTool(BaseTool):
name: str = "Name of my tool"
description: str = "What this tool does. It's vital for effective utilization."
args_schema: Type[BaseModel] = MyToolInput
def _run(self, argument: str) -> str:
# Your tool's logic here
return "Tool's result"
Great, thank you Robenko. By any chance do you know of an active browser Crew use-case that is public so that I can see as an example?