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.
Open-source neural speech synthesis for pre-training, SFT, and RLHF on SpeechLM and audio codecs across local and cloud GPUs.
AI-powered cyber fraud assistant with RAG, multi-agent orchestration & Google Calendar integration. Built with FastAPI + LangChain + ChromaDB + OpenAI.
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.
Add a description, image, and links to the llm-generative-ai topic page so that developers can more easily learn about it.
To associate your repository with the llm-generative-ai topic, visit your repo's landing page and select "manage topics."