Project Info

Brain Pods

Devpost

Inspiration

The inspiration for Brain Pods came as an idea after a long path of bad teachers and the spontaneous boredom that study brings to people. We wanted to create a simple and fun tool for all students all over the world using the power of AI.

What it does

Brain Pods allows students to quickly create or join live video calls where an AI, using context from study guides the owner of the pod uploaded, can ask game-like questions in real time and give custom feedback to the students.

How we built it

We built our platform on top of the technology that Agora offers with their real-time video SDK. Using this, we leveraged frameworks like Supabase and NextJS to quickly iterate over the ideas we had. For AI, we leveraged the technology of Groq for small tasks such as recommendations, while using Google's Gemini for bigger context windows in live pods.

Challenges we ran into

Working with a completely new tool such as Agora Figuring out what was the best architecture for the real-time events Managing the different contexts for the different AI sessions

Accomplishments we're proud of

Being able to create multiple pods without them interacting with each other. Deploying our product in a production environment where others can use it.

What we learned

No one in our team had ever worked with real-time communication to the extent this project required us to. We learned about the importance of having fallbacks and robust systems that will assure the system does not fail in case of an error, something that happens very often in real-time events.

What's next

We believe Brain Pods has a lot of space to grow, during our process, we thought about many things that would make this THE go-to tool for studying. The first next step for Brain Pods would be to integrate several things to allow students to share other types of information, such as whiteboards, sharing screens, coding pads, etc.. We also believe that voice is an important feature for both accessibility and easiness, which is why implementing a live voice agent that could interact with the students is the big next step.

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
  • Google GeminiIn code
  • JavaScriptIn code
  • Next.jsIn code
  • ReactIn code
  • SupabaseIn code
  • Tailwind CSSIn code
  • TypeScriptIn code
  • ExpressClaimed
  • VercelClaimed

8 of 10 appear in the indexed code. 2 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

170 KB

Source files

59

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

0 stars