DEV Community: Arjun Sharma

PhantomCode 👻 – Building a Haunted AI Coding Assistant | Hacktoberfest 2026

Arjun Sharma — Sat, 31 Oct 2026 04:43:33 +0000

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 4: Ghost in the Machine
What if debugging your code felt a little less scary? 👻

As a first-year Computer Science student, I'm still learning programming and exploring how AI can make development easier. For the Hacktoberfest Week 4 challenge, I built PhantomCode – Haunted AI Lab.

What I Built

PhantomCode is a Python-based AI coding assistant designed to help developers understand code, identify common errors, and spot basic security risks.

✨ Features

AI Code Assistant: Helps explain and review Python code.

Error Analyzer: Helps understand common programming errors.

Security Scanner: Checks for potentially risky coding patterns.

AI Chat Assistant: Lets users ask programming-related questions.

Haunted Interface: A spooky-themed dashboard built with Streamlit.

Demo

codesnippet-lab / PhantomCode--Week4

AI-powered haunted coding assistant

👻 PhantomCode – Haunted AI Coding Lab

Your AI Coding Companion — Debugging Beyond the Grave.

PhantomCode is a colourful, Halloween-inspired AI coding assistant built with Python and Streamlit.

✨ Features

💻 Code Assistant – Understand Python code with AI explanations.
🔍 Error Analyzer – Investigate Python errors and get suggested fixes.
🛡️ Security Scanner – Detect common security risks in Python code.
💬 AI Chat – Ask programming questions using an open-weight AI model.

🛠️ Tech Stack

Python
Streamlit
Groq API
Open-weight GPT-OSS model

🚀 Run Locally

Clone this repository:

git clone YOUR_GITHUB_REPOSITORY_URL
Enter the project folder:

cd PhantomCode-Week4
Install dependencies:

pip install -r requirements.txt
Add your Groq API key using Streamlit secrets or the app's API key field.
Start the application:

streamlit run app.py

🔐 API Key Security

Never commit API keys or secrets to GitHub. For deployment, configure sensitive values using Streamlit Community Cloud secrets.

🎃 Hacktoberfest

…

View on GitHub

Code

Github repository : https://github.com/codesnippet-lab/PhantomCode--Week4

How I Built It

🛠️ Tech Stack

Python

Streamlit

Groq API

Open-weight GPT-OSS model

Why Does Open Innovation Matter?

used an open-weight AI model through Groq to power the AI features. Open-weight models give developers more flexibility to explore how AI works, experiment with different models, and build applications without being limited to one closed model ecosystem.

As a beginner, this project helped me understand how AI APIs can be integrated into a real application.

My Agent Session

The Spirit of It

Prize Categories

Built with curiosity, code, and a little bit of spooky energy. 👻

devchallenge #hf26challenge #Hacktoberfest2026 #Python #Streamlit #OpenSourceAI #BuildInPublic

Sorta — An AI Downloads Butler Built with Local Gemma

Arjun Sharma — Sat, 24 Oct 2026 04:55:50 +0000

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 3: Slow and Steady
My downloads folder can get messy pretty quickly, so for the Hacktoberfest Week 3 challenge, I decided to build something that could help me organize it.

I made Sorta, a small AI-powered app that suggests where a downloaded file could belong based on its filename.

What I Built

Sorta is built with Python, Streamlit, Ollama, and Gemma 3 1B.

I enter or select a filename, and Gemma suggests a folder category. I can review the suggestion in the app before deciding what to do with the file.

This is an early prototype: Sorta currently previews folder suggestions. It does not automatically move files, and its undo feature is not implemented yet.

Instead of having to think through a folder category for every download, Sorta gives me a quick suggestion to review. I haven’t measured a specific time saving yet, but I wanted to explore how AI could make this small, repetitive task easier.

Demo

codesnippet-lab / Sorta-AI

A local AI-powered downloads organizer that uses Gemma to suggest folders for your files—without sending filenames to a cloud AI.

Sorta — AI Downloads Butler 🪄

Sorta is a file-organization assistant that uses a locally running Gemma model to suggest folders for your files. You can review the suggestions before taking any action.

Features

Upload multiple files in a Streamlit interface
Use local Gemma AI through Ollama to suggest folders
Preview the proposed organization
Keep the user in control: this prototype does not move, rename, or delete files

Built with

Python
Streamlit
Ollama
Gemma 3 1B

Run locally

1. Install Ollama

Install Ollama for your operating system: https://ollama.com/download

2. Download Gemma

Open a terminal and run:

ollama pull gemma3:1b

Ensure Ollama is running.

3. Set up Sorta

From the project folder:

python3 -m venv .venv
source .venv/bin/activate
pip install -r requirements.txt

4. Launch the app

streamlit run app.py

Open the local URL printed in your terminal.

Privacy and safety

Sorta sends filenames to the locally running Gemma model to generate…

View on GitHub

Code

Github Repository:https://github.com/codesnippet-lab/Sorta-AI

How I Built It

I used Gemma 3 1B through Ollama, with the model running on my own computer. For this prototype, the filename is sent to the local model rather than a hosted AI API.

Using an open model gave me a chance to experiment with AI locally and connect it to an app I built myself.

Why Does Open Innovation Matter?

As a first-year Computer Science student who’s still learning development, this project helped me practice connecting a local AI model to a Python interface and handling the model’s response.

My next steps are to add safe, user-approved file organization and implement a real undo feature.

Thanks for checking out my project! I’d appreciate feedback and ideas for improving Sorta.

devchallenge #hf26challenge #Hacktoberfest #OpenSource #Python #Gemma #Ollama

My Agent Session

The Lazy Payoff

Prize Categories

devchallenge #hf26challenge

Sorta-AI : An AI Downloads Butler

Arjun Sharma — Fri, 23 Oct 2026 20:30:01 +0000

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 3: Slow and Steady
My Downloads folder can get messy pretty quickly, so for Hactoberfest Week 3 challenge,I decided to build something that could help me organise it.

I made Sorta ,a small AI-powered app that suggests where a downloaded file could belong based on its filename.

What I Built

Sorta is built with Python, Streamlit, Ollama, and Gemma 3 1B.

I enter or select a filename, and Gemma suggests a folder category. I can review the suggestion in the app before deciding what to do with the file.

This is an early prototype: Sorta currently previews folder suggestions. It does not automatically move files, and its undo feature is not implemented yet.

Github Repository:https://github.com/codesnippet-lab/Sorta-AI

Code

codesnippet-lab / Sorta-AI

A local AI-powered downloads organizer that uses Gemma to suggest folders for your files—without sending filenames to a cloud AI.

Sorta — AI Downloads Butler 🪄

Sorta is a file-organization assistant that uses a locally running Gemma model to suggest folders for your files. You can review the suggestions before taking any action.

Features

Upload multiple files in a Streamlit interface
Use local Gemma AI through Ollama to suggest folders
Preview the proposed organization
Keep the user in control: this prototype does not move, rename, or delete files

Built with

Python
Streamlit
Ollama
Gemma 3 1B

Run locally

1. Install Ollama

Install Ollama for your operating system: https://ollama.com/download

2. Download Gemma

Open a terminal and run:

ollama pull gemma3:1b

Ensure Ollama is running.

3. Set up Sorta

From the project folder:

python3 -m venv .venv
source .venv/bin/activate
pip install -r requirements.txt

4. Launch the app

streamlit run app.py

Open the local URL printed in your terminal.

Privacy and safety

Sorta sends filenames to the locally running Gemma model to generate…

View on GitHub

How I Built It

I used Gemma 3 1B through Ollama, with the model running on my own computer. For this prototype, the filename is sent to the local model rather than a hosted AI API.

Using an open model gave me a chance to experiment with AI locally and connect it to an app I built myself.

Why Does Open Innovation Matter?

I used Gemma 3 1B through Ollama, with the model running on my own computer. For this prototype, the filename is sent to the local model rather than a hosted AI API.

Using an open model gave me a chance to experiment with AI locally and connect it to an app I built myself.

I used Gemma 3 1B through Ollama, with the model running on my own computer. For this prototype, the filename is sent to the local model rather than a hosted AI API.

Using an open model gave me a chance to experiment with AI locally and connect it to an app I built myself.

My Agent Session

The Lazy Payoff

Prize Categories

devchallenge #hf26challenge

InvoicePilot AI : Making Invoice Processing Smarter with AI

Arjun Sharma — Fri, 16 Oct 2026 10:57:00 +0000

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 2: Side Hustle

What I Built

InvoicePilot AI is a project I am building to make invoice processing easier and more efficient.

The goal is to reduce manual work and help users organize invoice information through a simple application.

I built this project to improve my Python development skills and explore how AI can be applied to real-world problems.

Demo

Try InvoicePilot AI using the live demo link :
https://invoice-pilot-ai-b2iqponirobba7zwczpkud.streamlit.app

Code

Github Repository:
https://github.com/codesnippet-lab/invoice-pilot-ai

How I Built It

I built InvoicePilot AI using Python and Streamlit.

I used VS Code for development and GitHub to manage and share my source code.

I worked on organizing the project files, installing dependencies, and running the application locally before deploying it.

This project helped me improve my Python programming skills and understand how to turn an idea into a working application.

Why Does Open Innovation Matter?

Open innovation matters because it allows people from different backgrounds to share ideas, learn from one another, and build better solutions together.

As a first-year Computer Science student, I believe open-source projects give beginners like me an opportunity to learn from real-world code, improve our skills, and contribute to the developer community.

By sharing projects openly, we can help others learn, receive feedback, and make technology more accessible to everyone.

My Agent Session

My First User

I am looking forward to getting feedback from my first users.

Prize Categories

devchallenge

hf26challenge

My Java Learning Journey

Arjun Sharma — Fri, 09 Oct 2026 11:29:47 +0000

Hi everyone!
I'm a first-year Computer Science student at Bosscoder School of Technology , and I'm starting my journey in programming.
Currently, I'm learning Java, practicing coding problems, and improving my problem-solving skills.
My goal is to become a better programmer and contribute to open-source projects.
I'll share my learning progress , challenges ,and achievements here.
I'm excited to learn and grow this community.

#Java #Programming #Beginners