Red Hat AI

Battle-test your AI agents before production. Discover how MiDojo's open source framework red-teams tool calls for real-world security and utility.

Explore Kubernetes resources for Red Hat AI Inference on Amazon EKS, enabling intelligent routing for your model serving.

Stop guessing RAG settings. Discover how AutoRAG uses fast evaluation sweeps to optimize chunking and retrieval precision for small LLMs on your data.

Improve model reliability at inference time with its_hub: Learn how to select accurate outputs without retraining.

Learn behavioral testing for agents, catching non-deterministic failures with golden queries and YAML files.

Consider a scenario where a zero-day vulnerability in a supply chain component allows an attacker to execute code inside one of your pods. Even if your network policies successfully block them from pivoting to other namespaces or exfiltrating data, they are still inside the pod, where attempts to run reconnaissance scripts, inject payloads, or execute shell commands, can take place.

The moment the attacker tries to execute a dangerous command or exhibit suspicious behavior, ACS detects the anomaly. Because these policies are set to termination mode within the ZTVP, ACS doesn't just send an alert, it immediately kills the rogue pod.
This is the ultimate synergy of defense in depth: Network policies block the attacker's escape routes, and active runtime monitoring eliminates the threat entirely. Even if a configuration was missed, the risk of a successful, prolonged attack drops effectively to zero.

Boost AI coding agent performance with AGENTS.md and Agent Skills. Learn how to standardize project context, structure tasks, and share skills across teams.

Learn how PyTorch's Inductor compiler and vertical fusion optimize GPU code for faster neural network layers

Headed to JavaZone 2026? Visit the Red Hat Developer booth on-site to speak to our expert technologists.

Learn how to parse SEC filings into JSON objects matching a given schema with agentic-graphrag-finance.

Agentic AI is cool, but how can we make it actually do things for us? Welcome to the world of Computer Use, where your model can take action for you on your desktop, and perform actions like typing, clicking, and more.

In this demo, we run an open source, natively multimodal model (Qwen3.6, 35B sparse MoE) locally on Mac using MLX, then connect it to Hermes, an AI agent with built-in guardrails for computer use. Watch it move a chess piece, apply a Photo Booth filter, and read a graph straight out of a research paper, all by seeing the screen and clicking, typing, and navigating like a human would. Everything runs on your own hardware through an OpenAI-compatible endpoint, so nothing you see or do ever leaves your machine.

#ComputerUse #AIAgents #RedHatAI #LocalLLM #PrivateAI #OpenSourceAI

Learn how to build an open cloud native architecture for AI agents. This blueprint explains how to improve workload isolation and implement inference routing.

Learn how to set up local agentic AI computer use. Run quantized models like Qwen 3.6 with Hermes to automate desktop tasks on your own terms today.

Upgrade your PyTorch training and inference with TorchComms, the new back-end layer for modern large-scale ML systems.

Learn how OpenShift and OpenShell combine for dual protection of AI coding agents, reducing attack surface and securing your infrastructure.

Deploy a self-hosted AI coding assistant with vLLM and Red Hat OpenShift AI for privacy and operational independence.

Discover how to configure EvalHub evaluation collections on Red Hat AI. Run Lighteval, Garak, and GuideLLM in parallel for a unified LLM pass/fail verdict.

Learn how smarter data generation strategies can reduce the cost and time needed to train high-quality speculator models for speculative decoding. This post shares findings on cross-distillation, training efficiency, and production inference gains that deliver faster LLM serving with no loss in output quality.

Learn how to isolate AI agents using the supervisor pattern and OpenShell sandboxes. Protect credentials and limit blast radius during incident response.

Explore a demo of serving a multimodal model (Qwen3-Omni) with vLLM-Omni on a single hardware accelerator.

Learn how to optimize deployment of vLLM for various traffic shapes, including high-concurrency chat, long-context RAG, high-throughput batch, and distributed AI-grid.

Learn about the three optimization levers for distributed AI inference: prefill/decode disaggregation, KV cache strategy, and speculative decoding.

Learn how Red Hat's SastAI initiative, in collaboration with NVIDIA, automates false positive identification in static application security testing (SAST) using generative AI. By employing an agentic, multi-stage research workflow, SastAI reduces noise and improves triage efficiency. Discover the pattern harvesting methodology that greatly enhances the SastAI solution, now offering a tighter solution with better knowledge and reasoning.

Learn how to connect the EvalHub runtime to internal or external model servers using service account tokens, API keys, or custom certificates.

Learn about the five-dimensional design space in modern LLM serving, including tensor, pipeline, expert, data, and context parallelism.