microsoft / microsoft/agentsleague
Project: [Creative Apps] - RealTutorAI
Nobody has claimed this yet.
- Dominant language
- No language data
- Stars
- 286
- Forks
- 92
- Avg merge
- 12h 44m
- Merged PRs (30d)
- 1
Description
Track
Creative Apps (GitHub Copilot)
Project Name
RealTutorAI
GitHub Username
GaurRitika
Repository URL
https://github.com/GaurRitika/REALTUTOR-AI
Project Description
RealTutor AI is an intelligent coding assistant that provides real-time help and guidance as you code. Unlike static code assistants, RealTutor AI actively monitors your coding activity and provides contextual assistance when you need it most.
1.Live, Context-Aware AI Assistant: Watches your real-time coding activity and detects when you're stuck or paused
2.Human-Like Explanations: Uses advanced AI models to explain errors in simple, beginner-friendly language
3.Smart Triggering: Automatically responds when needed - on long pauses or error detection
4.Seamless Integration: Runs inside VS Code with a dedicated panel for AI responses
5.Full Stack Architecture: Real-time communication between extension and backend via HTTP API
6.Perfect for Learners: Ideal for students, self-taught developers, or coders working without a mentor
Demo Video or Screenshots
Demo Video : https://youtu.be/RyaeUic2mJU
ScreenShots :
Primary Programming Language
Python
Key Technologies Used
Backend
1.Flask: HTTP server for API endpoints
2.WebSockets: For real-time communication (optional)
3.Groq API: Powers the AI model responses
4.LangChain: Framework for working with language models
Extension
1.TypeScript: Main programming language for the extension
2.VS Code API: Integration with editor features
3.Webview API: For displaying the AI assistant panel
Submission Type
Individual
Team Members
No response
Submission Requirements
- My project meets the track-specific challenge requirements
- My repository includes a comprehensive README.md with setup instructions
- My code does not contain hardcoded API keys or secrets
- I have included demo materials (video or screenshots)
- My project is my own work with proper attribution for any third-party code
- I agree to the Code of Conduct
- I have read and agree to the Disclaimer
- My submission does NOT contain any confidential, proprietary, or sensitive information
- I confirm I have the rights to submit this content and grant the necessary licenses
Quick Setup Summary
1. Clone & setup backend
git clone https://github.com/GaurRitika/REALTUTOR-AI && cd realtutor-ai/backend/models
python -m venv venv && venv\Scripts\activate # Windows: venv\Scripts\activate | Mac/Linux: source venv/bin/activate
pip install -r ../requirements.txt
echo GROQ_API_KEY=your_api_key_here > .env
python model_api.py
2. Setup & run extension (in a new terminal)
cd realtutor-ai/extension && npm install && npm run compile
Then press F5 in VS Code to launch
Technical Highlights
1.Smart Triggering: onDidChangeTextDocument + setInterval detect 5s inactivity → sends selected code to backend
2.Error Detection: onDidChangeDiagnostics hooks VS Code's diagnostic engine → auto-explains compiler errors
3.Response Caching: SHA-256 hashed, 24hr TTL Map cache on the extension side to avoid duplicate API calls
4.Language Auto-Detection: Pattern-based fallback (file extension → code heuristics) for polyglot support
5.Retry Logic: 3 auto-retries with 30s timeout on HTTP calls to the backend
Challenges & Learnings
Main challenge was understanding of Docker , and to deploy the the extension in the marketplace of Microsoft . It was a different learning for me , i learnt a lot :)
Contact Information
Email: devritika.gaur@gmail.com , LinkedIn : https://www.linkedin.com/in/ritikagaur21/ , Twitter : https://x.com/Gaur2005Ritika
Country/Region
India
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Review the linked REALTUTOR-AI repository, starting with its README and the setup paths for backend/models/model_api.py and the extension. The submission describes an existing project but does not identify a specific change, test, or acceptance condition, so there is no defined implementation endpoint.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- docker, flask, python, typescript, vscode
- Domain
- ai, backend, devtools
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Quiet
- Clarity
- Needs clarification
- Newbie friendliness
- 15/100