Integrations

Use anybrowse as LangChain tools — drop them into any agent, chain, or RAG pipeline. Handles JS-heavy pages, paywalls, and anti-bot measures automatically.

pip install anybrowse[langchain]

from anybrowse.langchain import get_tools
from langchain.agents import initialize_agent, AgentType
from langchain.chat_models import ChatOpenAI

llm = ChatOpenAI(model="gpt-4")
tools = get_tools()  # free tier — or get_tools(api_key="your-key")

agent = initialize_agent(tools, llm, agent=AgentType.OPENAI_FUNCTIONS)
result = agent.run("Research the latest AI agent frameworks and summarize the top 3")

from anybrowse.langchain import AnybrowseLoader

# Use as a document loader
loader = AnybrowseLoader("https://techcrunch.com")
docs = loader.load()
print(docs[0].page_content[:500])

Available tools: anybrowse_scrape, anybrowse_search

Load any URL as a LlamaIndex Document — ready for indexing, querying, and RAG workflows.

pip install anybrowse[llamaindex]

from anybrowse.llamaindex import AnybrowseReader

reader = AnybrowseReader()  # or AnybrowseReader(api_key="your-key")
docs = reader.load_data(["https://techcrunch.com"])

from llama_index.core import VectorStoreIndex
index = VectorStoreIndex.from_documents(docs)
query_engine = index.as_query_engine()

response = query_engine.query("What are the key announcements this week?")
print(response)

Use anybrowse as a CrewAI tool for web-enabled agents.

pip install anybrowse crewai crewai-tools

from crewai_tools import tool
from anybrowse import AnybrowseClient

client = AnybrowseClient()  # or AnybrowseClient(api_key="your-key")

@tool("Web Scraper")
def scrape_url(url: str) -> str:
    """Scrape any URL and return clean Markdown content for analysis."""
    return client.scrape(url).markdown

@tool("Web Search")
def search_web(query: str) -> str:
    """Search the web and return structured Markdown results."""
    results = client.search(query)
    return "\n\n".join([f"## {r.title}\n{r.url}" for r in results])

# Use in a crew
from crewai import Agent, Task, Crew

researcher = Agent(
    role="Research Analyst",
    goal="Find and synthesize information from the web",
    backstory="Expert at web research and competitive intelligence",
    tools=[scrape_url, search_web]
)

Add anybrowse as a function tool for AutoGen agents.

pip install anybrowse pyautogen

from anybrowse import AnybrowseClient
import autogen

client = AnybrowseClient()

def scrape_url(url: str) -> str:
    """Scrape any URL and return Markdown."""
    return client.scrape(url).markdown

def search_web(query: str) -> str:
    """Search the web. Returns Markdown with results."""
    results = client.search(query)
    return "\n\n".join([f"{r.title}: {r.url}" for r in results])

# Configure and use in an agent
config = autogen.config_list_from_json("OAI_CONFIG_LIST")
assistant = autogen.AssistantAgent("assistant", llm_config={"config_list": config})
user = autogen.UserProxyAgent(
    "user",
    human_input_mode="NEVER",
    function_map={"scrape_url": scrape_url, "search_web": search_web}
)

Use the HTTP Request node to call anybrowse from any n8n workflow.

1. Add an HTTP Request node to your workflow
2. Set Method to POST and URL to https://anybrowse.dev/scrape
3. Set Body Type to JSON
4. Set the request body:
   

   { "url": "{{ $json.url }}" }

5. Use {{ $json.markdown }} from the response in your next node

With API key: add header Authorization: Bearer your-api-key

Use Webhooks by Zapier to call anybrowse from any Zap.

1. Add a Webhooks by Zapier → POST action
2. URL: https://anybrowse.dev/scrape
3. Payload Type: JSON
4. Data: url → map from your trigger
5. Map the markdown field from the response to your next action (Google Docs, Notion, Slack, etc.)

Use the HTTP → Make a request module to call anybrowse in any scenario.

1. Add an HTTP → Make a request module
2. URL: https://anybrowse.dev/scrape
3. Method: POST
4. Body type: Raw · Content type: application/json
5. Request content:
   

   { "url": "{{url}}" }

6. Parse the response and use markdown downstream

No SDK needed. Works from any language or tool that can make HTTP requests.

# Scrape a URL
curl -X POST https://anybrowse.dev/scrape \
  -H "Content-Type: application/json" \
  -d '{"url": "https://techcrunch.com"}'

# Web search
curl -X POST https://anybrowse.dev/serp/search \
  -H "Content-Type: application/json" \
  -d '{"q": "web scraping API 2025", "count": 5}'

# With API key (Pro)
curl -X POST https://anybrowse.dev/scrape \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer your-api-key" \
  -d '{"url": "https://techcrunch.com"}'