TubeMind AI is a Chrome extension that uses Retrieval-Augmented Generation, FAISS, and Groq LLMs to let users chat with YouTube videos, generate summaries, study notes, and key takeaways with timestamp citations.
8
No data
0
0
No data
2026-07-28
It combines semantic search, FAISS vector search, and Groq's Llama 3.3 70B model in a practical Chrome extension to make video learning interactive and efficient.
🧠 TubeMind AI AI-Powered YouTube Learning Assistant
Retrieval-Augmented Generation • Semantic Search • FAISS • Groq • Chrome Extension
TubeMind AI is an AI-powered Chrome Extension that transforms YouTube videos into an interactive learning experience.
Using Retrieval-Augmented Generation (RAG), semantic search, FAISS vector search, and Groq LLMs, TubeMind AI enables users to:
Add your screenshots to the
assets/folder.
| Chat | Summary |
|---|---|
| Study Notes | Takeaways |
|---|---|
flowchart TD
A[YouTube Video] --> B[Transcript Retrieval]
B --> C[Semantic Chunking]
C --> D[Sentence Transformers]
D --> E[Embeddings]
E --> F[FAISS Index]
F --> G[Semantic Search]
G --> H[Prompt Builder]
H --> I[Groq LLM]
I --> J[Streaming Response]
J --> K[Chrome Extension]
TubeMind-AI
│
├── assets
│ ├── banner.png
│ ├── demo.gif
│ ├── chat.png
│ ├── summary.png
│ ├── notes.png
│ └── takeaways.png
│
├── backend
├── extension
├── README.md
└── .gitignore
git clone https://github.com/Omkar-narsale/TubeMind-AI.git
cd TubeMind-AI
cd backend
pip install -r requirements.txt
Create a .env
GROQ_API_KEY=YOUR_API_KEY
GROQ_MODEL=llama-3.3-70b-versatile
Run
uvicorn app.main:app --reload
cd extension
npm install
npm run build
Load the generated extension/dist folder from `chrome://
Similar projects matched by category, topics, and programming language.
Harness Engineering is a methodology for improving coding agent outputs by carefully crafting the environment around them—providing curated context, tools, and executable constraints that encode an organization’s nonfunctional requirements and cumulative lessons.
A 28.9 million parameter language model runs on an $8 ESP32-S3 microcontroller entirely on-device, generating simple stories at about 9.5 tokens per second.
mimic captures traffic from any iOS or web app and automatically generates a Python client library that lets you call the app's API like a regular library.