llm-generative-ai

Multi-agent AI simulation platform for modeling team behavior, crisis response, and collaborative decision-making.

A high-performance, multi-modal AI workspace powered by the Google Gemini ecosystem. Featuring real-time low-latency voice interaction, search-grounded reasoning, cinematic video generation via Veo, and professional-grade image synthesis. Built for the next generation of AI-native workflows.

NEXUS RAG is a production-grade Retrieval-Augmented Generation (RAG) platform engineered for secure enterprise knowledge management. Unlike standard RAG demos, NEXUS is built for multi-tenancy and strict data isolation, enabling organizations to ingest vast datasets and query them using state-of-the-art LLMs (Qwen 2.5) with confidence.

AI-powered cyber fraud assistant with RAG, multi-agent orchestration & Google Calendar integration. Built with FastAPI + LangChain + ChromaDB + OpenAI.

Open-source neural speech synthesis for pre-training, SFT, and RLHF on SpeechLM and audio codecs across local and cloud GPUs.

Disclosure Pilot AI is a full-stack desktop application that demonstrates using Large Language Models to automate the drafting, compilation, and iXBRL compliance tagging of SEC quarterly Form 10-Q and yearly Form 10-K financial reports.

Automated Alteryx-to-Databricks migration framework that converts .yxmd workflows into optimized PySpark SDP code and Databricks Asset Bundles (DAB), with CI/CD deployment to Databricks using GitHub Actions and token-efficient XML parsing for reduced LLM costs.