Project Info

Study Buddy

This project did not submit a demo video on Devpost.

Inspiration

We wanted to create a study bot that felt less invasive into our studying environments. Do you ever just wish your friend would just sit there and respond occasionally to your monologue? We wanted to create an idea off of that.

What it does

Using 3 personas that we have built, we can tailor our study environments and vibes to match what we are feeling. Simply just use the voice controls and talk to our Study Buddy AI. It can understand how you feel through your tone and offer feedback specifically to your perceived emotions.

How we built it

with love. (and hume.ai+gemini+love)

Challenges we ran into

We had the most trouble with merge conflicts. Some of us occasionally thought about pivoting majors.

Accomplishments we're proud of

We got one of our buttons to be the most beautiful color.

What we learned

Perseverance.

What's next

More tailored study models.

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

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

8 of 8 appear in the indexed code.

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

48 KB

Source files

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

Feature verification

4 Verified3 Code-supported1 Claimed only1 Blocked

Gemini-powered AI chat/response generationVerified
with hume.ai+gemini+love
Claimed on Devposthigh confidence
- app/components/Model.tsx:14 — GoogleGenerativeAI client instantiated and gemini-1.5-flash model called with conversation history to generate responses
Next.js application built with React, MUI, TailwindVerified
next.js, react.js, materialui, tailwindcss
Claimed on Devposthigh confidence
- package.json:16 — next, react, @mui/material, tailwindcss all listed as dependencies and used throughout app/ components
- tailwind.config.ts:1 — Tailwind config present and referenced by globals.css
Real-time transcript/conversation displayVerified
implied by voice conversation UX in description
Claimed on readmemedium confidence
- app/components2/Messages.tsx:12 — useVoice().messages consumed and pushed into conversation history, rendered via Assistant/User components
Voice conversation via Hume AI (voice controls to talk to Study Buddy)Verified
Simply just use the voice controls and talk to our Study Buddy AI
Claimed on Devposthigh confidence
- app/page1/VoicePage.tsx:6 — fetchAccessToken from hume package retrieves a Hume access token on mount
- app/components/Controls.tsx:11 — useVoice() hook drives mute/unmute/disconnect controls for the live voice call
Axios usage (web scraping utility)Code-supported
axios listed in Built With
Claimed on Devpostmedium confidence
- app/page3/webscraper.ts:2 — Axios imported for what appears to be a webscraper utility, but page3 is not linked from the main navigation flow observed
Emotional intelligence / real-time tone-based feedbackCode-supported
It can understand how you feel through your tone and offer feedback specifically to your perceived emotions
Claimed on Devpostmedium confidence
- app/components2/Sentiment.tsx:6 — Component sorts and takes the top 3 entries of a values object (matches shape of Hume prosody expression scores)
- utils/expressionLabels.ts:1 — Map of Hume expression keys to human-readable labels, scaffolding for displaying detected emotions
- utils/expressionColors.ts:1 — Map of Hume expression keys to colors, scaffolding for displaying detected emotions
- app/components2/Assistant.tsx:2 — Imports Sentiment but never renders it in JSX, so prosody scores are not actually surfaced to the user
- app/components2/User.tsx:2 — Imports Sentiment but never renders it in JSX, so prosody scores are not actually surfaced to the user
Three selectable personas tailoring the study environmentCode-supported
Using 3 personas that we have built, we can tailor our study environments and vibes to match what we are feeling
Claimed on Devpostmedium confidence
- app/page2/otherPage/Selection.jsx:81 — UI renders 3 selectable persona cards (Tutor, BuddyBuddy, Your Therapist) with a 'Start!' button that navigates to /page5
- app/data.js:1 — tutorList defines 3 persona description strings (lebron, turtle, pikachu), but selectedCharacter state in Selection.jsx is never passed into the session or used to select a prompt/persona downstream
More tailored study models (future work)Claimed only
What's next for Study Buddy: More tailored study models
Claimed on Devposthigh confidence
GitHub-based collaborationBlocked
github listed in Built With
Claimed on Devpostlow confidence

An AI agent derived these features from the project’s Devpost page and readme, then searched the code for each one. Verified features are backed by cited code; claimed-only features had no supporting code, which is not by itself proof a feature is missing.