Integrations
AutoGen
Give Microsoft AutoGen agents a Thunderbit-powered web reader
AutoGen agents accept Python functions as tools. Wrap /distill and any AssistantAgent (or member of a GroupChat) can fetch live web content.
Install
pip install pyautogen httpxFunction tool
import httpx
API = "https://openapi.thunderbit.com/openapi/v1"
H = {"Authorization": "Bearer YOUR_API_KEY"}
def read_url(url: str) -> str:
"""Fetch a URL and return clean Markdown.
Use for any web research task: docs, articles, search results, product pages.
"""
resp = httpx.post(f"{API}/distill",
headers=H,
json={"url": url, "renderMode": "basic"},
timeout=60.0)
resp.raise_for_status()
return resp.json()["data"]["markdown"]Register with an Agent
from autogen import AssistantAgent, UserProxyAgent
llm_config = {"model": "gpt-4o", "api_key": "YOUR_OPENAI_KEY"}
researcher = AssistantAgent(name="researcher", llm_config=llm_config)
proxy = UserProxyAgent(name="proxy", code_execution_config=False)
researcher.register_for_llm(name="read_url", description="Fetch URL as Markdown")(read_url)
proxy.register_for_execution(name="read_url")(read_url)
proxy.initiate_chat(researcher, message="Summarize https://arxiv.org/abs/2501.00001")GroupChat
For multi-agent crews (researcher + writer + critic), register read_url only on the researcher's register_for_llm so other agents can't trigger it. Execution still goes through the shared UserProxyAgent.
Related
- CrewAI — similar multi-agent pattern
- Agent Read-URL Tool