HackStack

Project Info

Homer

Devpost

This project did not submit a demo video on Devpost.

Problem Statement For international students, studying abroad isn’t just an academic journey, it’s a cultural leap. Moving to a new country comes with excitement, but also a wave of uncertainty. The language barrier is often the first and biggest hurdle. It doesn’t just complicate classwork or paperwork, it affects everyday interactions, social life, and the ability to form real, lasting connections. Many students find themselves sticking to others from their own background, not by choice, but by necessity. This limits their exposure to the broader campus community and deepens feelings of isolation. The thought of starting fresh in a place where they might not be understood can feel intimidating, even paralyzing. Without support, this fear can start long before a student ever sets foot at UCSC. They don’t just need information, they need a bridge to people. A way to feel welcome, included, and connected before they arrive. Solution Statement Homer is a communication and community-building platform designed to make international students feel at home, no matter where they’re from or what language they speak. At its core is powerful real-time translation technology that lets users communicate fluidly in their native language while still being fully understood by others. Whether it's English, Korean, Portuguese, or any other language, Homer makes multilingual conversations feel natural, seamless, and even a little magical. Picture this: three students, each speaking a different language, having a conversation where everyone understands each other perfectly. That’s what Homer enables, removing language as a barrier and turning it into a shared experience. But Homer goes beyond messaging. It pairs incoming international students with experienced UCSC mentors, helping them build meaningful connections before they even arrive. This early engagement creates a foundation of trust, friendship, and support. The platform also acts as an information hub, delivering campus updates, survival tips, and culturally relevant guidance, curated with the international student in mind. Homer isn’t just a tool, it’s a welcome mat, a translator, and a community builder all in one.

What we learned

We would all say that we learned quite a bit during this hackathon. The two biggest lessons we could say we learned was 1) Setting up customized versions of large production ready projects are not as easy as we thought. We should have committed more time to setting up these projects instead of trying to think through the implementation details of the AI Translation Features. 2) Whiteboards are awesome! Surprisingly out of everything we tried to keep organized a simple short list of tasks on a whiteboard that we could check off was the most effective. It kept us feeling motivated and helped us deal with the overwhelming scale of the project in order to avoid feeling overwhelmed. Building and the Challenges we faced So after coming up with the idea of an communication app that could translate from any language to any language we had set the bar pretty high for what we wanted to accomplish. One challenge that we ran into was lack of clarity on what we exactly wanted to do but once we got the problem and solution statement we were off to the races. Then the biggest challenge was learning how to setup these large production ready projects with gcp and being able to customize and build from source. But through sheer perseverance and luck we were able to accomplish the text translation and hopefully set a good base for the future of this product.

Analysis

Compare with all teams

View

Metric

Figures cover GitHub contributors during the hackathon window. A co-authored commit counts in full for each author, so per-member totals add up to more than the whole-team figures.

Technology

Found in codeClaimed only
  • CSSIn code
  • ExpressIn code
  • HTMLIn code
  • JavaScriptIn code
  • MongoDBIn code
  • PHPIn code
  • ReactIn code
  • TypeScriptIn code
  • Node.jsClaimed

8 of 9 appear in the indexed code. 1 claimed on Devpost could not be matched to code, which may simply mean the tool leaves no trace in the repository.

AI coding agents

No AI coding agent signals were found in this repository.

Detected from committed agent config files and commit authorship. Absence of a signal is not proof an agent was unused.

Codebase size

Source size

25 MB

Source files

8,409

Counts recognized source files only; vendored directories, binaries and lockfiles are excluded, so this is smaller than the repository on disk.

0 stars