A curated hub of interactive Streamlit applications showcasing practical AI and data science. Each app is designed for clarity, fast iteration, and hands-on exploration.

• 📊 Stock Screener: AI-assisted equity research with indicators, charts, and reports
• 🗺️ Airbnb Tour Agent (MCP + Weather): Trip plans from Airbnb listings + weather via MCP
• 📖 HarryAgent: LLM multi-agent research and writing with retrieval + critique loop
• 🎯 Logo Detection: YOLO-based logo recognition
• 📈 Clustering: Interactive clustering demos (KMeans/DBSCAN)
• 🧠 Image Classifier: Multi-backbone image classification

Streamlit-AI-Portfolio/
├── StockScreener/        # Stock market analysis tools
├── HarryAgent/           # Harry Potter X Mythology
├── LogoYolo/            # Logo detection system
├── Clustering/          # Clustering algorithms
├── HPVdb/              # Harry Potter Books
├── app.py              # Main Streamlit application
└── requirements.txt    # Project dependencies

# Clone the repository
git clone https://github.com/ambideXtrous9/Streamlit-App.git

cd Streamlit-App

# Install dependencies
pip install -r requirements.txt

# Run the application
streamlit run app.py

• Launch: streamlit run app.py → open http://localhost:8501
• Navigate via the sidebar between applications
• Open a specific page directly:

streamlit run app.py -- "?page=stockscreener"
# pages: home | stockscreener | newsqa | tourAgent | yolologo | image_classifer | clusterplay | login

• Real-time price data via yfinance
• Fundamentals/shareholding scraped from screener.in
• News context via GNews
• Technical indicators: EMA, SMA, RSI, MACD; breakout heuristics
• Interactive tables and charts (mlpchart)
• AI stock research report powered by ChatGroq

• LangGraph composition: parallel weather agent + Airbnb MCP agent → tour synthesis
• MCP stdio to @openbnb/mcp-server-airbnb via npx
• Weather tool formats a concise forecast report
• Streams tour synthesis updates to the UI
• Uses system Node 20 or bundled nodev20/ for reliable MCP execution

• Thematic blend: Harry Potter × Indian Mythology
• LangGraph workflow: classify → researcher → mythologist → writer → critic (with loop)
• Retrieval via FAISS index in HPVdb/ with CrossEncoder reranking
• Checkpointing in SQLite; observability via Langfuse

• Multiple backbones: Xception, InceptionV3, MobileNetV2, EfficientNet
• Loads checkpoints (*.ckpt) and runs per-model inference
• Displays per-model metrics for comparison

• Ultralyics YOLO-based logo recognition with bundled weights (LogoYolobest.pt)
• Integrated into the app via shared utilities
• Real-time inference on uploaded images

• KMeans and DBSCAN demos with synthetic data
• Interactive visualizations with seaborn/matplotlib
• K-distance graph to explore cluster structure

Contributions are welcome! Please feel free to submit a Pull Request or open an Issue for any improvements or bug fixes.

This project is licensed under the MIT License - see the LICENSE file for details.

• Streamlit - For the amazing framework
• Python - The language that makes it all possible
• Machine Learning Community - For continuous learning and inspiration

For any questions or collaborations, feel free to reach out!

🌟 Star this repository if you find it useful!