Red Hat AI

Learn how to prevent GPU waste and financial loss by implementing just-in-time (JIT) checkpointing with Kubeflow Training SDK on OpenShift AI.

Learn about the five primary structural challenges in enterprise AI evaluation and how EvalHub addresses them with a unified foundation for AI evaluation.

Learn how our team implemented CI/CD pipelines for the it-self-service-agent AI quickstart and the benefits of using CI/CD for agentic systems.

Learn how Red Hat AI can help address the security challenges of AI agents in production, from semantic malware to container escapes.

Scale agentic AI with Red Hat’s trusted software factory. Use Policy as Code and SBOMs to strengthen your development pipeline and manage software provenance.

Learn how Red Hat AI 3.4 uses EvalHub to orchestrate AI evaluations on Kubernetes. Scale frameworks like Garak and LightEval with built-in MLflow tracking.

Learn how Kagenti ADK, an open source toolkit, handles the complexities of managing production AI agents. It aligns with the Linux Foundation's Agent2Agent (A2A) protocol and provides a set of runtime services for easier deployment and operation.

Learn about our team's experience implementing a defense-in-depth safety architecture for AI agents using Llama Stack shields.

This article discusses the benefits of diffusion LLMs, a revolutionary approach to language models that offers a dynamic tradeoff between accuracy and performance. The article covers the architecture, evolution, and real-world statistics of this technology, including examples of open source models like LLaDA 2.X and Mercury 2.

Learn how to use OpenViking context database instead of traditional flat vector storage to provide AI agents with persistent, structured memory.

This article describes how to onboard a project and the results using two tools, CodeCov and CodeRabbit.

Learn how to combine KServe and llm-d to optimize generative AI inference, improve performance, and reduce infrastructure costs. This article demonstrates the integration architecture and provides practical guidance for AI platform teams.

Learn about critical lessons from building an MCP-powered AI agent for ServiceNow, including how to structure testing environments, best practices for implementing safeguards, and a phased approach to deploying enterprise AI integrations.

Users can deploy vLLM on a variety of hardware with a simple command. But a lot of work goes on below the surface to make the magic happen.

Discover how Red Hat optimized for human maintainability and significantly increased AI-assisted productivity by formalizing architectural constraints into machine-readable rules, custom lint rules, and deep documentation. Learn about the three layers they built and the impact on development.

Explore how Red Hat AI simplifies agent deployment with OpenClaw, showcasing model inference, safety guardrails, agent identity, and persistent state. Learn about vLLM, Llama Stack, and Models-as-a-Service (MaaS) options, and discover the benefits of agent identity and zero trust with Kagenti and AuthBridge.

Learn how Fromager, an open source project, helps protect Python dependencies by rebuilding entire dependency trees from source, providing network-isolated builds, and managing dependencies as a verifiable map. Discover how Fromager ensures supply chain verifiability, ABI compatibility, and customization.

Learn how to use Claude AI as a pattern matcher to refactor legacy test suites and save time. Discover how to install and set up Claude for large-scale refactoring, and follow a step-by-step guide to remove hard-coded paths and add FMF metadata.

Learn how to run OpenClaw on Red Hat OpenShift with production-grade security and observability. We cover default-deny network policies for blast radius containment, container-level sandboxing with OpenShift, Kubernetes Secrets for credential management, and end-to-end OpenTelemetry tracing with MLflow, so every decision your AI agent makes is isolated, auditable, and safe by default. Whether you're a developer exploring AI agents for the first time or a platform engineer thinking about running agentic workloads at scale, this is the infrastructure story that makes it production-ready.

Learn how to build security hygiene into OpenClaw by using containers for isolation, role-based access control (RBAC) for user access permissions, and secrets for sensitive information. This article explores how to use infrastructure powered by open source technology to help protect these workflows.

Learn how to use Lola, a unified package manager for AI context. Treat your AI context as versioned, auditable code with Lola modules and marketplaces. Improve your AI assistant workflow with this open source tool.

Learn how to build AI-assisted development workflows using harness engineering, a practice that emphasizes structured context over free-form tickets. Discover the two techniques that led to more consistent and predictable results.

Explore how Red Hat OpenShift AI was used to run an unsupervised AI agent for 24 hours, improving validation loss by 2.3% without human intervention. Learn about the container build, Kubernetes deployment, and key findings.

Learn how to set up distributed tracing for an agentic workflow based on lessons learned while developing the it-self-service-agent AI quickstart. This post covers configuring OpenTelemetry to track requests end-to-end across application workloads, MCP servers, and Llama Stack.

Learn how to deploy and experiment with Gemma 4, the latest open model family from Google DeepMind. This guide covers text, image, and video input, Mixture-of-Experts architecture, and more. Get started with Red Hat AI Inference Server today.