Guides

National Research Platform (NRP)

Free open-weight LLM endpoints plus free Kubernetes GPU compute for InCommon-affiliated researchers. Reference + Python code-along for hitting the NRP-hosted LLM API.

Claude Code Best Practices

AI coding agents — tools that can autonomously write, edit, run, and test code on your behalf — are rapidly changing how software gets built. The space is crowded and…

UW-Madison Cloud Services (AWS, GCP, Azure)

UW-Madison offers enterprise cloud computing through contracts with Amazon Web Services (AWS), Google Cloud Platform (GCP), and Microsoft Azure. These services are managed…

OpenScholar: Scientific Literature Synthesis with Retrieval-Augmented LMs

Foundation models

OpenScholar is an open-source, retrieval-augmented language model (LM) designed to help researchers navigate and synthesize scientific literature. Developed by the Allen…

Claude Code Cloud Setup Guide (Vertex AI & Bedrock)

This guide walks UW-Madison researchers and staff through setting up Claude Code with a cloud provider — either Google Vertex AI or Amazon Bedrock. It covers Windows and…

Google Colab

Google Colab is a cloud-based Jupyter notebook environment that runs entirely in the browser. It allows you to write and execute Python code without installing anything…

BadgerCompute

BadgerCompute is UW–Madison’s browser-based interactive computing service built on JupyterHub. It provides on-demand access to CPUs, memory, and GPUs without requiring any…

MLflow 101: Local Experiment Tracking for Beginners

Reproducibility

This is a beginner-friendly overview of local experiment tracking with MLflow. If you’ve ever lost a “good” result because you forgot which settings you used, MLflow solves…

UW Generative AI Services & Policies

Microsoft Copilot

Foundation models

The University of Wisconsin–‍Madison is committed to responsibly harnessing the power of generative artificial intelligence to enhance teaching, learning, research and…

NotebookLM: A GenAI Summarization Tool

Foundation models

NotebookLM is a generative AI tool designed to assist with understanding dense, complex texts, including research papers in machine learning and AI. Developed by Google Labs…

Version Control with GitHub Desktop

Reproducibility

Navigating the world of version control systems like Git can initially feel daunting, especially for those new to programming or collaborative software development projects.…

How to Contribute?

Nexus is built by people sharing what they’ve learned with each other. This guide covers what we’re looking for, what makes a good contribution, and how to submit one.

Center for High Throughput Computing (CHTC)

Established in 2006, the Center for High Throughput Computing (CHTC) is UW-Madison’s core computational service provider for large-scale computing. CHTC offers two main…