RAW HTTP — NO HEADLESS BROWSER OVERHEADMARKDOWN · JSON · HTML · LLM-READY FORMATSMCP SERVER FOR AI AGENTSTLS FINGERPRINT IMPERSONATIONEXTRACT · SUMMARIZE · DIFF · BRANDSITEMAP DISCOVERY & DEEP CRAWLINGSELF-HOST OR USE OUR CLOUD APIBUILT IN RUST — FAST BY DEFAULTDEEP RESEARCH — AI SYNTHESIZES REPORTS FROM 50+ SOURCESWEB SEARCH — QUERY AND SCRAPE SEARCH RESULTS IN ONE CALLAGENT SCRAPE — GIVE A GOAL, AI EXTRACTS WHAT YOU NEEDURL MONITORING — WATCH PAGES FOR CHANGES WITH WEBHOOKSBONUS CREDITS — EARN FREE CREDITS BY STARRING AND REFERRINGRAW HTTP — NO HEADLESS BROWSER OVERHEADMARKDOWN · JSON · HTML · LLM-READY FORMATSMCP SERVER FOR AI AGENTSTLS FINGERPRINT IMPERSONATIONEXTRACT · SUMMARIZE · DIFF · BRANDSITEMAP DISCOVERY & DEEP CRAWLINGSELF-HOST OR USE OUR CLOUD APIBUILT IN RUST — FAST BY DEFAULTDEEP RESEARCH — AI SYNTHESIZES REPORTS FROM 50+ SOURCESWEB SEARCH — QUERY AND SCRAPE SEARCH RESULTS IN ONE CALLAGENT SCRAPE — GIVE A GOAL, AI EXTRACTS WHAT YOU NEEDURL MONITORING — WATCH PAGES FOR CHANGES WITH WEBHOOKSBONUS CREDITS — EARN FREE CREDITS BY STARRING AND REFERRING

SDK INTEGRATION

Web scraping for CrewAI agents

Give your CrewAI agents real-time web access as a tool.

CrewAI is a Python framework for building multi-agent systems where specialized agents collaborate on tasks. webclaw plugs in as a crew tool that any agent can call, providing scrape, search, crawl, and extract capabilities with automatic bot bypass.

Setup

CrewAI Python — custom tool

from crewai import Agent, Task, Crew
from crewai.tools import tool
from webclaw import Webclaw

wc = Webclaw(api_key="wc_...")

@tool("Web Scraper")
def scrape_url(url: str) -> str:
    """Scrape any URL and return clean markdown."""
    result = wc.scrape(url=url, formats=["markdown"])
    return result.markdown

researcher = Agent(
    role="Research Analyst",
    goal="Find and summarize information from the web",
    tools=[scrape_url],
)

task = Task(
    description="Research the latest Rust async runtime benchmarks",
    agent=researcher,
)

crew = Crew(agents=[researcher], tasks=[task])
crew.kickoff()

Why webclaw for CrewAI

  • Drop-in @tool wrapping of webclaw SDK
  • Bot bypass lets agents access any public site
  • Structured output agents can reason over
  • Fast enough for interactive crew execution

Common use cases

  • Multi-agent research crews
  • Sales intelligence agents
  • Content aggregation and summarization
  • Automated competitive analysis

Frequently asked questions

How do I add webclaw as a tool in a CrewAI crew?

Wrap the webclaw SDK call in a @tool-decorated function and pass it to your agent's tools list. The agent can then call scrape, crawl, or extract as needed during task execution.

Can multiple agents share the same webclaw tool?

Yes. Define the tool once and include it in each agent's tools list. All agents will share the same API key and rate limit pool.

Get started

500 pages/month free. No credit card. Open source.

Stay in the loop

Get notified when the webclaw API launches. Early subscribers get extended free tier access.

No spam. Unsubscribe anytime.