google-adk-quercle

Quercle web search, fetch, and extraction tools for Google Agent Development Kit (ADK).

Installation

uv add google-adk-quercle
# or
pip install google-adk-quercle

Setup

Set your API key as an environment variable:

export QUERCLE_API_KEY=qk_...

Get your API key at quercle.dev.

Quick Start

from google.adk.agents import Agent
from google_adk_quercle import get_async_quercle_tools

agent = Agent(
    model="gemini-2.0-flash",
    name="research_agent",
    instruction="You are a helpful research assistant. Use the search and fetch "
    "tools to find accurate, up-to-date information.",
    tools=get_async_quercle_tools(),
)

Tools

Direct Tool Usage

Sync

from google_adk_quercle import (
    quercle_search,
    quercle_fetch,
    quercle_raw_search,
    quercle_raw_fetch,
    quercle_extract,
)

# AI-synthesized search
result = quercle_search(query="best practices for building AI agents")
print(result)

# Search with domain filtering
result = quercle_search(
    query="Python documentation",
    allowed_domains=["docs.python.org"],
)
print(result)

# Fetch and analyze a page with AI
result = quercle_fetch(
    url="https://en.wikipedia.org/wiki/Python_(programming_language)",
    prompt="Summarize the key features of Python",
)
print(result)

# Raw search results (no AI synthesis)
result = quercle_raw_search(query="Python web frameworks", format="markdown")
print(result)

# Raw page content
result = quercle_raw_fetch(url="https://example.com", format="markdown")
print(result)

# Extract relevant content from a page
result = quercle_extract(
    url="https://en.wikipedia.org/wiki/Python_(programming_language)",
    query="What are Python's main features?",
    format="markdown",
)
print(result)

Async

import asyncio
from google_adk_quercle import (
    async_quercle_search,
    async_quercle_fetch,
    async_quercle_raw_search,
    async_quercle_raw_fetch,
    async_quercle_extract,
)

async def main():
    result = await async_quercle_search(query="latest AI agent frameworks")
    print(result)

    result = await async_quercle_fetch(
        url="https://en.wikipedia.org/wiki/TypeScript",
        prompt="What is TypeScript?",
    )
    print(result)

    result = await async_quercle_raw_search(query="Python web frameworks")
    print(result)

    result = await async_quercle_raw_fetch(url="https://example.com")
    print(result)

    result = await async_quercle_extract(
        url="https://en.wikipedia.org/wiki/TypeScript",
        query="TypeScript type system",
    )
    print(result)

asyncio.run(main())

Custom API Key

from google_adk_quercle import (
    create_quercle_search,
    create_quercle_fetch,
    create_quercle_raw_search,
    create_quercle_raw_fetch,
    create_quercle_extract,
)

search = create_quercle_search(api_key="qk_...")
fetch = create_quercle_fetch(api_key="qk_...")
raw_search = create_quercle_raw_search(api_key="qk_...")
raw_fetch = create_quercle_raw_fetch(api_key="qk_...")
extract = create_quercle_extract(api_key="qk_...")

Agentic Usage

With Google ADK Agent

from google.adk.agents import Agent
from google.adk.runners import Runner
from google.adk.sessions import InMemorySessionService
from google.genai import types
from google_adk_quercle import get_async_quercle_tools

agent = Agent(
    model="gemini-2.0-flash",
    name="research_agent",
    instruction="You are a research assistant. Search the web to find "
    "accurate, up-to-date information and analyze relevant pages.",
    tools=get_async_quercle_tools(),
)

session_service = InMemorySessionService()
runner = Runner(agent=agent, app_name="research_app", session_service=session_service)

session = await session_service.create_session(app_name="research_app", user_id="user1")

response = await runner.run_async(
    session_id=session.id,
    user_id="user1",
    new_message=types.Content(
        role="user",
        parts=[types.Part(text="Research the latest developments in WebAssembly")],
    ),
)

for event in response:
    if event.content and event.content.parts:
        print(event.content.parts[0].text)

Sync Agent (with sync tools)

from google_adk_quercle import get_quercle_tools

agent = Agent(
    model="gemini-2.0-flash",
    name="sync_agent",
    instruction="You are a helpful assistant.",
    tools=get_quercle_tools(),
)

Configuration

API Reference

Module-Level Tools (use QUERCLE_API_KEY env var)

Factory Functions (custom API key / timeout)

License

MIT