https://github.com/mrigank005/neotutor
NeoTutor is an interactive Agentic AI tutor system powered by LLaMA 3 and LangGraph. It dynamically generates questions, provides structured feedback, and offers personalized practice—all within a single notebook. Ideal for students and educators looking to explore adaptive learning using large language models.
https://github.com/mrigank005/neotutor
adapters adaptive-learning ai-tutor edutech langgraph llama-3 text-generation
Last synced: 8 months ago
JSON representation
NeoTutor is an interactive Agentic AI tutor system powered by LLaMA 3 and LangGraph. It dynamically generates questions, provides structured feedback, and offers personalized practice—all within a single notebook. Ideal for students and educators looking to explore adaptive learning using large language models.
- Host: GitHub
- URL: https://github.com/mrigank005/neotutor
- Owner: Mrigank005
- License: mit
- Created: 2025-07-11T13:14:24.000Z (11 months ago)
- Default Branch: main
- Last Pushed: 2025-07-11T13:33:08.000Z (11 months ago)
- Last Synced: 2025-09-04T06:49:19.978Z (9 months ago)
- Topics: adapters, adaptive-learning, ai-tutor, edutech, langgraph, llama-3, text-generation
- Language: Jupyter Notebook
- Homepage: https://colab.research.google.com/drive/1X4QwSB48fddXATlJBYtab16l7TM72KZk?usp=sharing
- Size: 30.3 KB
- Stars: 2
- Watchers: 0
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# 🤖 Enhanced AI Tutor System using LLaMA-3 and LangGraph
[](LICENSE)
[](https://python.langgraph.dev/)
[](https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct)
An **adaptive, feedback-based AI tutor system** built using:
- 🧠 Meta's [LLaMA-3.2-3B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct)
- 🔄 [LangGraph](https://github.com/langchain-ai/langgraph) for multi-agent workflow
- ⚡ Hugging Face Transformers (4-bit quantization for efficiency)
- ✅ PyTorch, BitsandBytes, Accelerate for seamless GPU usage
---
## 🎓 What It Does
This notebook walks you through a **complete interactive tutor session** that:
1. 📚 Asks a question from a topic you choose
2. 📝 Evaluates your answer and gives structured feedback
3. 🧪 Generates a new practice question
4. 📈 Tracks your progress and adapts difficulty
It's like having your own AI teacher, personalized to your learning!
---
## 📄 View Notebook in Colab
[](https://colab.research.google.com/drive/1X4QwSB48fddXATlJBYtab16l7TM72KZk?usp=sharing)
You can explore the full .ipynb notebook on Google Colab using the button above.
---
## 📁 Project Structure
```
├── EnhancedTutorSystem.ipynb
├── README.md
├── requirements.txt
```
---
## 🧠 Model Info
This project uses (but does not rehost) Meta's official instruction-tuned model:
[](https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct)
The model is loaded via transformers using 4-bit quantization (BitsAndBytes)
**Note:** You must agree to Meta's license to access the model.
---
## 🎯 Features
- ✍️ Adaptive questions across difficulty levels
- 📊 Real-time performance tracking
- 🤓 Intelligent feedback on every answer
- 💡 LangGraph-powered multi-agent workflow
- 🧵 Fully reproducible session history
---
## 🔜 Coming Soon
- 🌐 A Hugging Face Space with a user-friendly UI
- 📝 Student progress export to PDF
- 🎯 Topic-based quiz sessions
- 🧪 Integration with LangChain for evaluation metrics
---
## 📄 License
This project is released under the MIT License.
---
## 🙌 Acknowledgments
- 🧠 Meta AI for LLaMA-3
- 🔄 LangGraph by LangChain
- 🤗 Hugging Face for open infrastructure
---
## 📬 Contact / Feedback
[](https://github.com/Mrigank005)
[](https://www.linkedin.com/in/mrigank005)
Feel free to raise issues or suggestions on GitHub
Or connect via Hugging Face community tab!
**Happy learning!** 💡
---