DEV Community: Dhanush K urs

GhostScript AI: A Haunted Terminal Powered by Local AI 👻

Dhanush K urs — Tue, 27 Oct 2026 17:54:52 +0000

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 4: Ghost in the Machine.

What I Built 👻

I built GhostScript AI, a spooky but helpful coding companion powered by local AI.

Users can ask questions about terminal commands and coding concepts. The ghost responds with spooky commentary, a beginner-friendly explanation, and a useful example.

I chose the haunted-machine theme to make learning programming more fun and less intimidating for beginners.

Code

GitHub repository: https://github.com/DhanushRajUrs/ghostscript-ai

How I Built It

My technology stack:

Python
Streamlit
Ollama
Gemma 3:1B

The user enters a question, chooses a spooky personality, and clicks Summon the Ghost. The application sends the prompt to Gemma through Ollama, which runs locally on my machine.

The model generates a playful response alongside a practical explanation.

Why Does Open Innovation Matter?

Using an open-weight model with local inference gives developers more control over their applications and the prompts they process.

Once the software and model are installed, GhostScript AI can generate responses without depending on a hosted AI API. This reduces reliance on external services and allows developers to experiment with local models.

The project also demonstrates how open AI tools can be used to build creative, interactive applications with a small technology stack.

The Spirit of It 👻

I wanted to combine the fun of a haunted computer with the practical goal of helping beginners learn programming.

Instead of making terminal commands feel intimidating, GhostScript AI turns coding questions into a playful conversation with a digital ghost.

This is an early prototype, and future improvements could include a terminal-style interface, more ghost personalities, and interactive coding lessons.

Building this project helped me practise Python, Streamlit, GitHub, and local AI integration.

Happy Hacktoberfest! 🎃

LazyList AI: Let Local AI Organize Your Day 🦥

Dhanush K urs — Wed, 21 Oct 2026 17:38:13 +0000

LazyList AI: Let Local AI Organize Your Day 🦥

This is my submission for the Hacktoberfest Open-Source AI Challenge Week 3: Slow and Steady.

What I Built

I built LazyList AI, a simple AI productivity assistant that transforms a messy to-do list into a prioritized, low-stress action plan.

Users enter their tasks, choose their energy level, and receive suggestions for what to focus on first. The goal is to spend less time organizing tasks and more time completing them.

Demo

I tested the application locally and captured a screenshot of LazyList AI generating an action plan.

Demo screenshot: Attached to this post.

This is an early prototype that currently runs on my machine.

Code

GitHub repository: https://github.com/DhanushRajUrs/lazylist-ai

How I Built It

Python for the application logic
Streamlit for the user interface
Ollama to run the model locally
Gemma 3:1B as the open-weight language model

The application sends the user's task list and selected energy level to Gemma running locally through Ollama. The model generates a prioritized plan with explanations and manageable first steps.

Why Does Open Innovation Matter?

Running an open-weight model locally gives users more control over their data and lets developers experiment without relying on a paid hosted AI API.

After the software and model have been installed, inference can run without an internet connection. Developers can also explore compatible models and adapt their applications to different needs.

The Lazy Payoff 🦥

LazyList AI helps reduce the mental effort of deciding where to start when a person has many tasks. It is an early prototype, and future improvements could include task tracking, deadlines, and saving plans.

Building it helped me practise Python, Streamlit, Git, GitHub, and local AI integration while exploring how open AI tools can make everyday work easier.

Thanks for checking out my project!

LocalBiz AI 🛍️ LocalBiz AI is a small AI-powered prototype that helps small businesses generate product descriptions.

Dhanush K urs — Sun, 18 Oct 2026 07:28:48 +0000

LocalBiz AI: A Local AI Assistant for Small Businesses 🛍️

Small businesses often need attractive product descriptions to promote their products online, but writing them manually takes time. I built LocalBiz AI, a simple AI-powered prototype that helps small business owners generate product descriptions from a few details.

This is my project for the Hacktoberfest 2026 Week 2 — Side Hustle Challenge.

💡 What I built

LocalBiz AI takes three inputs:

Product name
Product features
Target customers

It uses an open-weight AI model to generate a concise, engaging product description.

🛠️ Tech stack

Python — application logic
Streamlit — user interface
Ollama — local model execution
Gemma 3:1B — open-weight language model

🎯 Who would use it?

My target customers are small business owners, handmade-product sellers, local retailers, and online sellers who want to create product descriptions without spending too much time or money.

A future business model could offer a free basic version and a paid version with batch generation, multiple languages, and platform-specific descriptions.

🤖 Why open innovation matters

Using an open-weight model through Ollama allows LocalBiz AI to run inference locally instead of sending product details to a hosted AI API. This can help reduce API costs and give users greater control over their data.

It also gives developers the freedom to experiment with different models and improve the application without depending on a single AI provider.

🎬 Demo

I tested the application locally using a handmade cotton bag as an example. The app generated product-description text from its features and target audience.

Demo video or screenshot: [Add your demo video or screenshot here before publishing.]

🔗 Source code

GitHub repository: https://github.com/DhanushRajUrs/localbiz-ai

The repository includes the Python application and setup instructions so others can run it locally.

🚀 What's next?

I would like to add multiple description styles, multilingual generation, copy-to-clipboard functionality, and a way to generate descriptions for multiple products at once.

This is an early prototype, but building it helped me practise Python, Streamlit, Git, GitHub, and local AI integration.

I'm excited to keep improving it and learn from the developer community!

devchallenge #hf26challenge #gemma

hi

Dhanush K urs — Sun, 18 Oct 2026 06:05:34 +0000

Starting My Software Development Journey: Learning, Building, and Contributing 🚀

Dhanush K urs — Sun, 18 Oct 2026 05:54:53 +0000

Hello, DEV Community! 👋 My Developer Journey Begins 🚀

Hey everyone! 👋

I'm Dhanush, an engineering student who's passionate about technology, software development, and exploring the world of AI/ML.

I'm starting my journey on DEV Community to learn from other developers, share what I build, document my mistakes, and grow alongside the developer community.

💻 What I'm Learning

Currently, I'm focusing on:

Software Development: Learning to build practical applications and write better code.
AI/ML: Exploring how artificial intelligence can solve real-world problems.
Web Development: Working with technologies like React, Python, and FastAPI.
Open Source: Learning how to collaborate, contribute to projects, and become part of the developer ecosystem.

🛠️ What I'm Building

One of my projects is PocketNature AI, where I'm exploring how technology and AI can encourage people to connect with nature.

Working on projects is teaching me that development isn't just about writing code. It's also about solving problems, debugging errors, experimenting, and learning something new every day.

🎯 My Goal

My goal is to become a better software developer, build projects that make a difference, and contribute to open source.

I'm still learning, and I know there's a long way to go. Instead of waiting until I become an expert, I've decided to start sharing my journey now.

I believe that every expert was once a beginner who kept going.

🤝 Let's Connect!

If you're a developer, student, open-source contributor, or someone exploring AI, I'd love to connect and learn from you.

What advice would you give someone starting their developer journey today? I'd love to hear your thoughts in the comments!

Here's to learning, building, breaking things, fixing them, and growing together. 🚀

DEVCommunity #100DaysOfCode #WebDev #AI #OpenSource