Red Hat AI

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.

Learn how to fine-tune large language models in enterprise environments with Training Hub, an open source library for LLM post-training. Discover the benefits of LoRA and QLoRA using Unsloth, including reduced VRAM requirements and faster training times.

Explore the spending transaction monitor AI quickstart, demonstrating agentic AI for intelligent financial monitoring on enterprise-grade infrastructure. Lower the barrier to entry for AI experimentation and refine your AI strategy.

Explore the four pillars of AI coding: vibes, secs, skills, and agents, and learn how they can improve the coding quality and reduce the encoding/decoding gap. Discover the benefits of a spec-driven approach and the importance of modular specs and skills in achieving harmony.

Learn how to integrate Anthropic's Claude Code, an agentic coding tool, using Red Hat AI Inference Server on OpenShift. Keep the inference process private on your own infrastructure while retaining the full Claude Code workflow.

Follow this 4-step process using Training Hub and OpenShift AI to transition LLM fine-tuning from local experiments to repeatable, production-grade workflows.

Learn how to set up vLLM Semantic Router locally with two models: a quantized Qwen3-Coder-Next running on Apple Silicon, and Google's Gemini 2.5 Pro as the cloud fallback. This router can significantly reduce token costs by routing common requests to a less expensive model.

Learn how to set up and run a local AI audio transcription using an Red Hat open source model.

Learn how to deploy multiple large language models (LLMs) behind a single OpenAI-compatible endpoint on OpenShift using a Model-as-a-Service (MaaS) approach. This guide demonstrates how to build an intelligent routing infrastructure that dynamically inspects the request payload and directs traffic based on the specified model field, reducing GPU waste and simplifying application logic.