This is a submission for the Hacktoberfest Open-Source AI Challenge Week 2: Side Hustle
What I Built
SellSmart AI is an AI-powered product listing generator built for small online sellers, student entrepreneurs, and small businesses.
Users enter a product name, category, price, target audience, key features, and writing style. The application uses the Gemma gemma4:e2b model through Ollama to generate an attractive product title, description, four key benefits, and relevant hashtags.
The problem: Writing product listings takes time, especially for sellers managing many products.
The solution: SellSmart AI provides a useful first draft in seconds, with a Copy Listing button to make the content easy to reuse.
Who could pay for it? Small shop owners, resellers, and freelancers who create product listings for clients could benefit from this tool. I haven't validated willingness to pay yet, but this is a potential commercial use case.
Demo
GitHub repository: https://github.com/Manish010325/sellsmart-ai
Demo screenshot: https://github.com/Manish010325/sellsmart-ai/blob/main/sellsmart-ai-demo.png
Code
The project is open source and available on GitHub.
Repository: https://github.com/Manish010325/sellsmart-ai
The repository contains the frontend, Express backend, setup instructions, demo screenshot, and MIT License.
To run it locally, you need Node.js, npm, and Ollama with the gemma4:e2b model installed.
How I Built It
I built SellSmart AI using HTML, CSS, and JavaScript for the frontend and Node.js with Express for the backend.
The backend sends the product details to Ollama's local API, which runs the Gemma gemma4:e2b model and returns the generated listing.
I also added input validation, error handling, health-check endpoints, and a copy-to-clipboard feature.
One of my main goals was to keep the AI inference local rather than depend on a hosted inference API. This makes the project useful for experimenting with AI while learning full-stack development.
Building this project helped me understand how to connect an open-weight language model to a practical web application.
Why Does Open Innovation Matter?
SellSmart AI demonstrates how open innovation can help developers turn open-weight AI models and open-source tools into practical applications.
I built this project using Gemma through Ollama, along with Node.js, Express, HTML, CSS, and JavaScript. These tools allowed me to experiment with AI-powered product listing generation without depending on a hosted inference API.
Open innovation also makes it easier for other developers to learn from the project, suggest improvements, adapt the code, and contribute new features. Small businesses and student entrepreneurs can explore how AI might simplify everyday tasks.
The project is still evolving, and community feedback can help make it more useful, accessible, and reliable.
Why Open-Source AI?
Open-weight models such as Gemma give developers an opportunity to build AI-powered applications without relying entirely on hosted inference APIs.
With SellSmart AI, users can run the gemma4:e2b model locally through Ollama after downloading it. This allows product details to be processed on the local machine in the current setup and avoids per-request charges from a hosted inference API.
Open-source tools also make experimentation and learning more accessible. Developers can inspect their application code, adapt the workflow, and explore other compatible models.
Local inference still requires suitable hardware, storage, and setup. The project is a learning prototype, and further testing with real sellers is needed.
Top comments (0)