#kaggle

Permission-aware, evidence-grounded performance-review agent (ADK 2.0 + Gemini + Next.js) - Kaggle AI Agents Intensive capstone

A RAG pipeline that reads PDFs and answers questions using LangChain and ChromaDB. The Streamlit app uses Qwen/Qwen2.5-7B-Instruct while a quantized Zephyr-7B LLM is used in the notebook.

Deep learning-based PM2.5 air quality forecasting using LSTM, GRU, and ARIMA to predict 24-hour ahead PM2.5 concentrations in Dhaka.

Documentation and project work from the 5-Day AI Agents Intensive Course with Google. Exploring agentic engineering, vibe coding, AI-assisted development, prompt engineering, cloud deployment, and modern AI workflows through hands-on labs using Google AI Studio, Antigravity, and Cloud Run.

📚 Personal study notes from Google's 5-Day AI Agents course — covering Antigravity, ADK 2.0, MCP, secure agent dev, and Agent Runtime deployment.

Run open LLMs on free Colab/Kaggle GPUs and call them from your machine over an OpenAI-compatible endpoint

🍿 A premium AI-powered movie discovery platform. Features Content-Based Filtering using TF-IDF, a high-performance FastAPI backend, and a modern Streamlit "Netflix-style" frontend. Integrated with the TMDB API for live trending data and metadata. 🎬✨

A trustworthy multi-agent AI emergency response companion powered by Planner → Worker → Evaluator architecture with memory, MCP tools, explainable AI, and verified resources.

AI-Powered B2B Lead Qualifier and Personalized Outreach Agent using Gemini API

AI Concierge Agent for Indian Grocery Planning - Kaggle Capstone 2026

AI Agent Security: Multi-Step Tool Attacks — Kaggle (OpenAI) attack.py + working note