AI-driven analysis of company news with sentiment, topics, and trend visualizations delivering actionable insights for decision-makers.

Demonstrates sentiment analysis with a multi-tool agent using langgraph, featuring fast protocol communication and diverse transport options.

Different use cases of the Model Context Protocol (MCP)

A Copilot integration that delivers context-aware, project-specific code suggestions through a modular prompt system and lightweight adapter.

A scalable integration of the Model Context Protocol enabling efficient propagation of rich context across distributed learning tasks.

AI-driven vulnerability data collection and patch generation with end-to-end automation and deployment focus.

Exercise: Integrate Model Context Protocol with GitHub Copilot

Open protocol adds ontology-based semantics to service interactions, enabling capability-driven discovery, data grounding, and cross-domain tool integration for smarter LLM agents.

Integrates Copilot with a modular context protocol to enrich AI-assisted coding.

Lightweight Python MCP server enabling A2A model context exchanges with extensible plugins.

Agentic RAG Chatbot orchestrates specialized agents for ingestion, retrieval, and Gemini-powered responses via a Streamlit UI, backed by FAISS vector store.

Streamlit-based grounded multi-format document QA leveraging MCP and Gemini for precise, cited results.

Modular MCP-driven RAG chatbot orchestrates dedicated agents to ingest, index, and answer from multi-format documents.

Local, private document QA with agentic ingestion-retrieval flow, FAISS indexing, and Ollama-backed on-device LLMs for multi-format PDFs, docs, and slides.

A decoupled, enterprise-grade RAG chatbot that orchestrates ingestion, retrieval, and LLM response via REST endpoints. It uses FAISS for fast initial search, cross-encoder re-ranking for result quality, and precise source citations to ensure verifiable answers across PDFs, Word, and slides. Frontend in React; backend in FastAPI with modular agents.

Modular, agent-based retrieval-augmented chatbot for multi-format documents using Model Context Protocol with local LLMs.

Lightweight toolkit to explore and prototype Model Context Protocol exchanges, validate messages, and observe context flows.

Modular agent-based RAG chatbot for multi-format documents with traceable, explainable messaging and efficient retrieval.

End-to-end demonstration of JSON-driven agent creation with memory, sequential thinking, and multi-server orchestration.

A unified protocol toolkit for coordinating context-aware models with extensible schemas, enabling scalable, reproducible experiments.

Modular multi-agent RAG platform leveraging structured inter-agent messaging for contextual retrieval and a Streamlit chat UI.

Streamlit-based RAG chatbot orchestrating LLM tool calls for document QA with FAISS indexing.

Modular, multi-language AI framework enabling dynamic tool discovery and context-sharing across Java Spring Boot and Python services.

Demonstrates math tooling, multi-tool orchestration, Groq/LangGraph agents, and interactive chat with external tool integrations.