Skip to content
← All projects

EdTech

Green & Gold Guru

Best AI HackTeam of 3

Multimodal AI tutor that teaches step-by-step using voice, visuals, and a live whiteboard — without ever giving away the answer.

GitHub ↗Devpost ↗

3

input modalities

01 — Problem

It's late at night, you're stuck on a complex problem, and office hours are over. Existing chatbots just give you the answer. Students need a tool that teaches through guided problem-solving across voice, text, and visual input.

02 — Approach

  1. 01

    Streamlit-based multimodal interface with a live canvas whiteboard, voice input via speech recognition, and PDF analysis via pyPDF2.

  2. 02

    OpenRouter routes to Gemini for step-by-step tutoring that guides without revealing the answer, adapting to whiteboard drawings and spoken questions.

  3. 03

    Edge TTS provides natural voice responses; NumPy processes whiteboard images for real-time visual analysis.

03 — Results

3

modalities (voice, whiteboard, PDF)

Step-by-step

guided tutoring without giving answers

Stack

StreamlitOpenRouterGeminiEdge TTSSpeech RecognitionpyPDF2NumPy

Next

Bowser→

Autonomous pediatric physical therapy robot that coaches exercises in real time using computer vision.