watsonx

This is an autogen>=0.4 extension for watsonx client integration.

Model Context Protocol (MCP) server for IBM watsonx.data - enables AI assistants to query and explore lakehouse data Resources

Hands-on lab material for Agentic AI bootcamp.

VRSecretary is a production-ready reference implementation for building AI-powered assistants in virtual reality. It combines Unreal Engine 5 (VR), a FastAPI backend, local/cloud LLM backends (Ollama, IBM watsonx.ai), and Chatterbox TTS to drive an interactive VR secretary avatar. The project includes an Unreal plugin, a sample VR demo level

Simple implementation of RAG using watsonx.ai, capturing the chat history to keep track of the conversation context and answer follow up questions.

This project contains a simple example implementation for a simple question-answering pipeline using inside-search (IBM Cloud Watson Discovery) and prompt (IBM watsonx with prompt-lab).

LLM application for complaint analysis and process improvement recommendations.

Working example of a custom Python tool for IBM watsonx Orchestrate that allows to query Calendar Events from Microsoft 365 using a member connection implementing an OAuth Authorization Code flow.

Real-time, screen-reader-native, IFAB-grounded AI explainer of VAR and offside decisions for blind fans. IBM SkillsBuild June 2026.

A collection of small projects and coding experiments that showcase various skills, technologies, and problem-solving approaches. It serves as a portfolio to demonstrate software development, traditional ai and generative ai expertise.

LLM data-structuring pipeline with Pydantic validation and JSON auto-repair, plus a complete Model Context Protocol (MCP) stack — FastMCP server, protocol-level client with roots/sampling, and a Gradio ReAct agent host on IBM watsonx.ai Granite. Unit-tested, credentials via env vars.

Bob The Judge-Migration Cutover Decision Advisor powered by IBM Bob — IBM Bob Hackathon 2026 CyberFalcon team

BioTactix AI: A zero-latency edge architecture using IBM Granite to synchronize player biometric fatigue with tactical spacing, predicting injuries and triggering real-time substitution alerts

Create your own Retrieval-Augmented Generation (RAG) chatbot for PDFs. This project uses LangChain, Flask, and an LLM (IBM WatsonX/Hugging Face) to build a conversational AI that understands your documents.

BioTactix AI: A zero-latency edge architecture using IBM Granite to synchronize player biometric fatigue with tactical spacing, predicting injuries and triggering g real-time substitution alerts.BioTactix-AI transforms live soccer telemetry into Explainable AI (XAI) using IBM watsonx.ai and an O(1) edge VFS.

Seven agentic AI projects — LangChain SQL agent, LangGraph routing, CrewAI & AG2 multi-agent apps, the full BeeAI progression, and Model Context Protocol client/server + security stack — each with verified tests (73 total), incl. real end-to-end MCP protocol integration tests.

A local-first compatibility and intelligence platform for Python package stacks. Detects runtime mismatches, validates hardware compatibility, and recommends stable dependency stacks.

Automated PyTest generation and static security vulnerability scanning powered by multi-agent AI.

Military-first Space Domain Awareness (SDA) AI Copilot: orbital noise analysis & micro-anomaly detection powered by IBM Granite & watsonx.

This is an example using the langchain_ibm implementation for function calling a LLM model running in watsonx.