OwnAgent

AI-based Task Automation System

Overview

OwnAgent is an advanced AI-based task automation system designed to learn from user interactions. It leverages Large Language Models (LLMs) and AI agents to meticulously record and replicate keyboard and mouse activities, distinguishing dynamic elements and storing these interactions in a JSON format. When prompted, the system utilizes AI to dynamically adapt and replicate the recorded actions based on new instructions.

OS Supported

Windows and Linux

User Interface

Prototype UI: Developed using Python Eel, HTML, CSS, and JavaScript.

Workflow

Show a demo of a task to the system.
Identify the dynamic content.
Save your demo with a proper description.
Command the system to perform a task based on prompt.
The system analyzes the prompt and decides what task to perform.
It generates the dynamic content and performs the tasks utilizing AI-Agents(using crewAI framework)

Demo - 1: Writing a linkedin post based on a prompt

Demo1.mp4

Demo - 2: Writing on Google doc based on a prompt

Demo2.mp4

License

This project is licensed under the MIT License - see the LICENSE file for details.

Acknowledgements

Thanks to the contributors of the Python Eel library and the crewAI framework.

##Contact If you have any questions or suggestions, feel free to open an issue or contact me directly at ahmedanwar.aa872@gmail.com.