A community-driven registry for Claude, Cursor, Windsurf, Cline & more. Not affiliated with Anthropic.
Are you the author? Sign in to claim
let LLMs control your desktop for tasks
raya is an AI agent for raya that harnesses the power of code and AI to control your PC with ease. It enables you to automate any task by interacting with applications, clicking buttons, typing, running commands, and capturing the UI state.
https://github.com/user-attachments/assets/82ab57fe-8e4d-4f37-9516-0001e7e08845
Unlike traditional computer vision models, raya works directly at the raya GUI layer, providing advanced automation capabilities without relying on image recognition techniques.
Requirements:
To install with uv:
uv pip install raya
Or with pip:
pip install raya
To use raya in your own script:
from langchain_google_genai import ChatGoogleGenerativeAI
from raya.agent import Agent
from dotenv import load_dotenv
load_dotenv()
llm = ChatGoogleGenerativeAI(model='gemini-2.0-flash')
agent = Agent(llm=llm, browser='chrome', use_vision=True)
query = input("Enter your query: ")
result = agent.invoke(query=query)
print(result.content)
To run the agent from the command line:
python main.py
See the demos for screenshots and more examples.
raya interacts directly with your windows OS at the GUI layer to perform actions. While designed to be intelligent and safe, it can make mistakes that might cause unintended changes. Use with care.
This project is licensed under the MIT License - see the LICENSE file for details.
Thank you for your interest in contributing to raya!
raya requires:
git clone https://github.com/YOUR_USERNAME/raya.git
cd raya
pip install -e ".[dev,search]"
pip install pre-commit
pre-commit install
main branch contains the latest stable codemain named according to the feature you're implementing: feature/your-feature-namefix/bug-descriptionruff.toml)..pre-commit-config.yaml.Run the test suite with pytest:
pytest
To run specific test categories:
pytest tests/
tests/unit/@pytest.mark.slow or @pytest.mark.integrationdef function_name(param1: type, param2: type) -> return_type:
"""Short description.
Longer description if needed.
Args:
param1: Description of param1
param2: Description of param2
Returns:
Description of return value
Raises:
ExceptionType: When and why this exception is raised
"""
@software{
author = {Rayamah, Ibrahim},
title = {raya: Enable AI to control your PC},
year = {2025},
publisher = {GitHub},
url={https://github.com/iBz-04/raya}
}
npx CLI installing 100+ agents, commands, hooks, and integrations in one command
干净、强大、属于你的 AI Agent 平台 --AI agents, without the clutter.
Native macOS app to monitor Claude AI usage limits and watch your coding sessions live
Pocket Flow: Codebase to Tutorial