Build Research and Rag agents with Granite on your laptop

Running LLMs against a sandbox airport to see if they can make the correct decisions in real time

Hash your files.

Experiments with LLMs in clouds (powered by SGLang)

Chat locally using leading open models built by the community, optimized and accelerated by NVIDIA's enterprise-ready inference runtime

An agentic pipeline implementing the Researcher-Critic pattern using IBM's Granite3-MoE:1B model

Run abstracts through a local LLM to give you some possible scores on what you are looking for.

Simple AI agent RAG chatbot based on Python, Ollama, Langchain, Gradio. Included tools: real time weather, calculate, local documents RAG, local SQL database .

Automated intelligent claims analysis for business process optimization

TalkToTech leverages IBM Granite models to build AI-powered automation solutions, streamlining business processes through intelligent generation and efficient workflows.

LeadGenAI is a Streamlit-based web application designed to help users generate LinkedIn leads and optimize business plans.

Succeed!!! ★ x 2 (Ollama - granite-code:20b)

This is the basic GenAI application involves Mistral, Granite, Llama

Human vs AI summarization game for Retail exhibition (Nov 24-25, 2025, Paris) - Bilingual interactive demo showcasing Adservio's sovereign AI

FIMpad is a FIM-focused local LLM interface in the form of a tabbed GUI text editor.