Project Info
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.
This is a Next.js project bootstrapped with create-next-app.
Getting Started
First, run the development server:
npm run dev
# or
yarn dev
# or
pnpm dev
# or
bun dev
Open http://localhost:3000 with your browser to see the result.
You can start editing the page by modifying app/page.tsx. The page auto-updates as you edit the file.
This project uses next/font to automatically optimize and load Geist, a new font family for Vercel.
Learn More
To learn more about Next.js, take a look at the following resources:
- Next.js Documentation - learn about Next.js features and API.
- Learn Next.js - an interactive Next.js tutorial.
You can check out the Next.js GitHub repository - your feedback and contributions are welcome!
Deploy on Vercel
The easiest way to deploy your Next.js app is to use the Vercel Platform from the creators of Next.js.
Check out our Next.js deployment documentation for more details.
Analysis
View
Metric
- 51
- 42
- 36
- 16
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
- 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.
Repository
franciscoerramuspe/brain-pods
83 files · 1.2 MB · @ af94fcb
Structure
Interface
45 files · 54%Screens, components and styles rendered to the user.
API & routing
3 files · 4%Request entry points: routes, handlers and controllers.
Application logic
8 files · 10%Domain rules, services and shared utilities.
Data & schema
1 file · 1%Schema definitions, migrations and data access.
Supporting
Layers are inferred from where files sit in the tree, not from reading the code. A project that names its directories unconventionally will read oddly here — open the file browser to check anything the diagram implies.
Languages
- TypeScript98%
- CSS1%
- Markdown1%
- JavaScript0%
Share of indexed source by file size. Binary and vendored files are excluded.
Dependencies
package.json
npm · 37- @google/generative-ai
- @heroicons/react
- @radix-ui/react-dialog
- @radix-ui/react-dropdown-menu
- @radix-ui/react-popover
- @radix-ui/react-separator
- @radix-ui/react-slot
- @radix-ui/react-toast
- @supabase/auth-helpers-nextjs
- @supabase/supabase-js
- agora-rtc-react
- agora-rtc-sdk-ng
- class-variance-authority
- clsx
- cmdk
- dotenv
- framer-motion
- groq-sdk
- +19 more
Declared in the repository’s manifests at the indexed commit. A declared package is not proof it is used, and runtime dependencies are listed first.
This project’s features have not been analysed yet.
Export this project's context (description, README, evidence, key source files) to chat with an AI agent elsewhere.