This is a submission for the Hacktoberfest Open-Source AI Challenge Week 4: Ghost in the Machine
What I Built
I built GhostShell AI, an offline AI-powered assistant with a mysterious, dark-themed web interface.
It can:
- Answer user questions.
- Explain Git commands.
- Provide basic coding assistance.
It uses a locally running AI model through Ollama.
Demo
GhostShell AI runs locally on my computer.
To launch the application:
- Start Ollama.
- Run
python web_app.py. - Open
http://127.0.0.1:5000in your browser.
The application can work offline after the required dependencies and AI model have been downloaded.
Code
GitHub Repository:
https://github.com/abubakkarsithikm06/Advance-GhostShell-AI
How I Built It
Technologies Used:
- Python
- Flask
- HTML
- CSS
- JavaScript
- Ollama
- Gemma 3 (1B)
I used Ollama for local AI inference with Gemma 3 (1B). This allows GhostShell AI to generate responses locally without depending on cloud AI APIs.
Why Does Open Innovation Matter?
Open-source AI makes technology accessible to everyone. It helped me build and experiment with AI locally without depending on paid cloud APIs.
It also gave me an opportunity to learn how local AI models can be integrated into a real application.
The Spirit of It
What if a ghost lived inside a machine?
That idea inspired me to build GhostShell AI — a digital assistant with intelligence, mystery, and an offline mind.
Built with Python, open-source AI, and a little mystery. 👻💚
Prize Categories
- Best Use of Gemma – Using Gemma 3 (1B) with Ollama for local AI inference.
#Hacktoberfest #OpenSourceAI #Gemma #Ollama #Python #LocalAI
Top comments (0)