Yash-Kavaiya /
GenAI-Projects
This is a collection of various Generative AI projects and AI Agents exploring the realms of Images, code, text, and more
69/100 healthLoading repository data…
masfaatanveer / repository
This is a fully autonomous, self-operating computer automation system designed to automate tasks on Windows without any user interaction. It runs scheduled or trigger-based workflows using Python, system tools, and smart agents — ideal for repetitive tasks, bots, or self-executing pipelines.
A transparent discovery signal based on current public GitHub metadata.
This score does not audit code, security, maintainers, documentation quality, or suitability. Verify the repository and its current documentation before adoption.
This project turns your computer into a self-operating intelligent agent that can:
👇 Terminal-based usage of the
operatecommand with AI automation:
GPT‑4o, Claude 3, Gemini Pro Vision, LLaVa--voice flag)pip install self-operating-computer-automation
operate
You’ll be prompted to enter an OpenAI, Claude, or Gemini key
→ Get OpenAI Key
This app needs screen recording and accessibility control on Windows/Mac.
| Mode Flag | Description |
|---|---|
| (default) | -m gpt-4-with-ocr for best click accuracy |
Selected from shared topics, language and repository description—not editorial ratings.
Yash-Kavaiya /
This is a collection of various Generative AI projects and AI Agents exploring the realms of Images, code, text, and more
69/100 healthmamgad /
This course uses a deliberately vulnerable banking application to demonstrate common security vulnerabilities, their impact, and how to fix them. The application is built with Flask (backend) and React (frontend).
68/100 healthjenasuraj /
-m gemini-pro-vision | Use Gemini Pro Vision |
-m claude-3 | Use Claude 3 |
-m llava | Use local model via Ollama |
--voice | Voice input support for hands-free operation |
# Step 1: Install Ollama (https://ollama.ai/download)
# Step 2: Pull model
ollama pull llava
# Step 3: Start Ollama
ollama serve
# Step 4: Run your agent
operate -m llava
# Clone the repo and install audio dependencies
git clone https://github.com/masfaatanveer/_Self-Operating-Computer-Automation_.git
cd self-operating-computer-automation
pip install -r requirements-audio.txt
# Install system audio libs
# Mac:
brew install portaudio
# Linux:
sudo apt install portaudio19-dev python3-pyaudio
# Run with voice
operate --voice
git clone https://github.com/masfaatanveer/_Self-Operating-Computer-Automation_.git
cd _Self-Operating-Computer-Automation_
pip install -r requirements.txt
Run the dev build:
operate
📁 self-operating-computer-automation/
├── operate # CLI entry
├── core/ # Main agent logic
├── vision/ # Screenshot and OCR tools
├── plugins/ # Custom skill scripts
├── models/ # API model wrappers
├── requirements.txt
├── requirements-audio.txt
└── README.md
automation
self-operating
windows-automation
multimodal-ai
gpt-4o
gemini-pro-vision
claude-3
ollama
agentic-ai
ai-agent
python
autopilot
MIT License — free for personal and commercial use. Attribution appreciated!
This is a repository of collection of many agents build on top of Langchain , Langgraph, MCP and so many amazing tools
Demolinator /
this is a repo for students to use and start learning Agentic Ai. All the best!
60/100 health24-mohamedyehia /
This is a smart procurement agents that can help you to find the best product for your company. and generate a report for you.
68/100 healthabdulwasea89 /
This is the repo where you learn ai agents and ai llm application
62/100 health