Skip to main content
We are excited to unveil DeepResearchTool, a powerful autonomous research capability within our AG2 framework. Inspired by OpenAI’s Deep Research, our tool is designed to tackle complex, multi-step research tasks efficiently, synthesizing insights from diverse online sources.

Installation

DeepResearchTool is built on top of Browser Use, which requires Python 3.11 or higher.
To get started with the DeepResearchTool, follow these steps:
  1. Install AG2 with the browser-use extra:
    If you have been using autogen or ag2, all you need to do is upgrade it using:
    or
    as autogen and ag2 are aliases for the same PyPI package.
  2. Set up Playwright:
  3. For running the code in Jupyter, use nest_asyncio to allow nested event loops.
You’re all set! Now you can start using browsing features in AG2.

Imports

Agent Configuration

Configure the agents for the interaction.
  • config_list defines the LLM configurations, including the model and API key.
  • UserProxyAgent simulates user inputs without requiring actual human interaction (set to NEVER).
  • AssistantAgent represents the AI agent, configured with the LLM settings.

DeepResearchTool Configuration

Once the DeepResearchTool is created, it needs to be registered to the agents.

Initiate Chat