Submission for the Hacktoberfest Open-Source AI Challenge — Week 2: Side Hustle.
Side Hustle is a project created for the Week 2 challenge: build something useful with open-source AI or open-weight models that could solve a real problem for someone.
The goal of this challenge is to move beyond an AI demo and think about practical value: who has the problem, how the project helps, and what would make the solution worth paying for.
Project status: This repository currently contains the project license only. A working application, its target users, features, and AI implementation are not yet documented in the repository. This README deliberately avoids claiming features or customer validation that cannot be verified.
As the project implementation is added, this section should explain the problem being solved, the intended users or customers, the core workflow, and the value the product provides.
A deployed application or video demonstration is not currently available.
Add a live demo URL or walkthrough video here when one is published.
Repository: RISHABH12005/Side-Hustle
The repository is public and licensed under the MIT License. The application source code and setup instructions can be added here as development progresses.
The Week 2 challenge focuses on building with open-source AI: open-weight models, local inference, agent frameworks, or other open-source tooling.
The specific model, framework, inference setup, and application architecture for this project have not yet been recorded in the repository. They will be documented here once the implementation is available.
A useful implementation write-up should cover:
- Model: The open-weight model used and why it was selected.
- Inference: Whether the model runs locally or through a hosted service.
- Application: The framework, backend, frontend, and data storage.
- AI workflow: What the model does, what inputs it receives, and how its output is used.
- Reliability: How outputs are validated and what limitations users should understand.
Open innovation makes it possible to experiment, learn, and build useful products without depending entirely on closed AI services.
Open-weight models and open-source tooling can provide greater flexibility over model selection, deployment, customization, and infrastructure. Depending on the model license and deployment setup, developers can evaluate local inference, adapt workflows, and choose infrastructure that fits their budget and privacy requirements.
For a side project intended to become a useful product, this flexibility matters. It can help keep experimentation accessible, make costs easier to evaluate, and give developers more control over how the AI component fits into the application.
Open innovation also makes collaboration possible: contributors can inspect the implementation, report issues, improve the workflow, and adapt the project for other use cases.
No public agent-session or DevRelay recording link is available yet.
Add a verified session link here if one is published.
No verified user testing, customer feedback, or paid usage has been documented yet.
The next step is to identify a target user, validate the problem through direct feedback, and test whether the project solves a problem valuable enough that someone would pay for it. Any feedback, usage figures, or revenue claims will be added only after they are verified.
Prize and partner categories will be selected only where the completed implementation meets the official challenge eligibility and integration requirements.
Built as part of the Hacktoberfest Open-Source AI Challenge. The aim is to turn open-source AI experimentation into something practical and useful.