MinionWorks β Modular browser agents that work for bananas π
minionworks
README
<!-- Light/Dark Mode Banner Hack --> <p align="center"> <img src="static/minion-works-cover-light.png#gh-light-mode-only" alt="Minion Works" width="100%" /> <img src="static/minion-works-cover-dark.png#gh-dark-mode-only" alt="Minion Works" width="100%" /> </p>
<h1 align="center"> MinionWorks β Modular browser agents that work for bananas π</h1>
<p align="center"> <em>Modular. Extensible. AI-native browser agents for modern web automation.</em> </p>
π Overview
Minion Works is a modular AI agent framework that connects to your browser and executes complex tasks autonomously. Built for developers, researchers, and curious builders.
β¨ Features
- π Perform Google searches and scrape content
- π€ Use LLMs (like GPT-4) to plan actions
- π Modular architecture for plug-and-play use cases
- π DOM interaction & content extraction
- π Run workflows via Python or UI
π οΈ Installation
-
Install the package
pip install minion-agent
-
Set up environment variables
cp .env.example .env # Edit your .env file with OpenAI or other API keys
π§ͺ Quick Start
Hereβs a complete example using MinionAgent
with langchain-openai
:
from langchain_openai import ChatOpenAI
from minion_agent.browser import MinionAgent
import asyncio
from dotenv import load_dotenv
# Load environment variables from .env file
load_dotenv()
async def main():
# Example 1: Using environment variables for OpenAI configuration
agent1 = MinionAgent(
task="Compare the price of GPT-4 and DeepSeek-V3",
llm=ChatOpenAI(model="gpt-4o"),
headless=True
)
result1 = await agent1.run()
print("Result 1:", result1)
# Example 2: Providing custom LLM and configuration
agent2 = MinionAgent(
task="Search for the latest news about AI",
llm=ChatOpenAI(model="gpt-4o"),
headless=False # Show browser window
)
result2 = await agent2.run()
print("Result 2:", result2)
if __name__ == "__main__":
asyncio.run(main())
π§ Example Use Case
agent = MinionAgent(
task="Find the top 3 ML conferences in 2025 and summarize each.",
llm=ChatOpenAI(model="gpt-4")
)
await agent.run()
π§ͺ Testing
pytest --maxfail=1 --disable-warnings -q
Ensure youβre in the root folder where tests/
lives.
π€ Contributing
We welcome PRs, feedback, and creative ideas!
- Fork β Branch β Commit
- Add tests
- Submit a Pull Request
- Tell your friends π
π Citation
@software{minion_works2025,
author = {Sairaam, Aman, Cheena},
title = {Minion Works: Let AI take the helm of your browser.},
year = {2025},
publisher = {GitHub},
url = {https://github.com/minionworks/minions}
}
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Playwright MCP Server
Provides a server utilizing Model Context Protocol to enable human-like browser automation with Playwright, allowing control over browser actions such as navigation, element interaction, and scrolling.
@kazuph/mcp-fetch
Model Context Protocol server for fetching web content and processing images. This allows Claude Desktop (or any MCP client) to fetch web content and handle images appropriately.
DuckDuckGo MCP Server
A Model Context Protocol (MCP) server that provides web search capabilities through DuckDuckGo, with additional features for content fetching and parsing.
YouTube Transcript MCP Server
This server retrieves transcripts for given YouTube video URLs, enabling integration with Goose CLI or Goose Desktop for transcript extraction and processing.
serper-search-scrape-mcp-server
This Serper MCP Server supports search and webpage scraping, and all the most recent parameters introduced by the Serper API, like location.
The Verge News MCP Server
Provides tools to fetch and search news from The Verge's RSS feed, allowing users to get today's news, retrieve random articles from the past week, and search for specific keywords in recent Verge content.
Tavily MCP Server
Provides AI-powered web search capabilities using Tavily's search API, enabling LLMs to perform sophisticated web searches, get direct answers to questions, and search recent news articles.
mcp-pinterest
A Pinterest Model Context Protocol (MCP) server for image search and information retrieval

Crawlab MCP Server