Hacktoberfest Hack Day Hampton x RevolutionVA

Build an original project that uses open-source or open-weight AI as an important part of how it works. Teams could create an agent skill, build with an open-weight large or small language model, or build or adapt an open-source model harness.

AI is changing security on both sides. It helps attackers write more convincing scams and gives them new systems to break, and it also gives defenders new tools. Build a project that uses AI to protect people or organizations, or that makes AI systems themselves harder to misuse.

You don’t need to be a security professional to compete. Some of the biggest risks are everyday ones that small businesses, nonprofits, and families deal with constantly:

• Phishing emails and texts that look like they came from a bank, vendor, or coworker
• Fake invoices and payment-change requests sent to whoever pays the bills
• Scam calls using cloned voices
• Outdated website plugins, weak passwords, and accounts nobody remembers creating
• Employees pasting customer data into public chatbots
• A small business adding an AI chatbot to its website without realizing customers can talk it into saying or doing things it shouldn’t

Projects can also go deeper: protecting an agent from prompt injection, probing a model for data leaks, or documenting what a model depends on.

Requirements:

• The project must address a specific, clearly stated security problem.
• Any offensive testing must target only systems you own or are explicitly authorized to test. Projects that attack third-party systems, or ship ready-to-use attack tooling without safeguards, are not eligible.
• Your demo must show the problem and how your project responds to it.

What a strong entry looks like:

• Clearly explains who is at risk, what could go wrong, and how the attack actually happens.
• Shows the problem happening, then shows the project catching, stopping, or explaining it.
• Is usable by the people who need it. A tool for a five-person office can’t assume an IT department.
• Is honest about its limits. Every defense has gaps, and a strong entry names its own.
• Avoids creating new problems, like a scam detector that sends private emails to a third party.

Prize: One winning team receives The AI Cybersecurity Handbook by Caroline Wong and Software Transparency by Chris Hughes and Tony Turner.

Build something that makes life better for a real community, or helps people take better care of the resources they share. Help a food pantry predict demand. Make public information easier to understand in plain language. Help neighbors track and report flooding. Cut the energy or cost of a task that people already depend on.

Requirements:

• The project must name a specific community or group of people it serves and the problem it addresses.
• The project must handle people’s data responsibly. Collect only what you need, and don’t use personal data without consent.
• Your demo must walk through a realistic scenario from the point of view of someone the project serves.

What a strong entry looks like:

• Shows an understanding of the problem. Why does it exist, what do people do about it today, and why does that fall short?
• Has a realistic path to use. How would someone find out about it, and why would they choose it over what they already do?
• Accounts for incentives. Who benefits, who would need to do extra work, and who would keep it running after the Fest?
• Fits the people it serves. It works on the devices, connections, and budgets they actually have, without training.
• Defines success. The team can say what would change if it worked and how they would measure that.
• Uses AI where it earns its place, and is efficient about cost and energy when people are depending on it.

Prize: One winning team receives Our Planet Powered by AI by Mark Minevich and The Equality Machine by Orly Lobel.

It’s time to see how much you can build with a lightweight, open model. Gemma 4 packs multimodal intelligence into an open-weights model that you can access through the Gemini API. So, what can Gemma 4 bring to your project?

• Multimodal Experience: Work with text and images to create an assistant that understands more of what users share.
• Focused AI Tools: Build a focused AI tool for learning, creativity, productivity, or your community.
• Rapid Prototyping: Experiment with an open model while using the Gemini API to move quickly from an idea to a working prototype.

Bring your idea to life… what will you build with Gemma 4 today?

Bring a sledgehammer to crack a nut. Take a problem that doesn’t need AI at all and solve it with far more AI engineering than anyone asked for. A multi-agent council that debates whether your toast is done. Retrieval over your houseplant’s feelings. A full eval suite for an AI that grades dad jokes. The more trivial the problem and the more rigorous the solution, the better.

Requirements:

• AI must do real work in the project. Hardcoded or faked responses are disqualified. The joke can be that a single if statement would have solved it, but your system can’t be an if statement in disguise.
• The project should be delightful.
• Your demo must show how the system works, not just the punchline.

What a strong entry looks like:

• Picks a problem so small that the effort spent on it is funny on its own.
• Uses real engineering techniques like agents, tool use, retrieval, evals, fine-tuning, or orchestration, and uses them well.
• Works live during the demo.
• Commits to the bit everywhere. The README, architecture diagram, benchmarks, and commit messages all treat the problem as though it were critically important.
• Makes the judges want to try it themselves.

What we mean by overengineered:
Overengineering is the gap between how much the problem matters and how much work went into solving it. Adding more parts isn’t enough on its own. A tangled pile of tools that barely runs is just a mess. A clean, well-built system that solves nothing important is the goal.

Prize: 1-month memberships to 757MakerSpace, awarded to each member of one winning team, maximum of three. Teams with more than three members decide among themselves who receives them.