Build resilient guardrails for OpenClaw AI agents on Kubernetes
Learn how to secure AI agents like OpenClaw using containers for isolation, RBAC for access control, secrets management, and full observability on Kubernetes.
Writing on software development, containers & Kubernetes, and AI.
Here's all of my longer content from around the web, collected in chronological order.
Building effective AI agents with Model Context Protocol (MCP)
Learn how Model Context Protocol (MCP) standardizes how AI models discover and call tools, enabling the shift from simple chatbots to reliable agentic AI applications.
The state of open source AI models in 2025
A look at the open source AI model landscape in 2025, from DeepSeek and Qwen to gpt-oss and small language models, and how to run them on your own hardware.
Run containerized AI models locally with RamaLama
Learn how to run AI models locally with RamaLama, an open source project that simplifies running AI models in containers for local inference, serving, and RAG.
3 MCP servers you should be using (safely)
Explore the three most useful Model Context Protocol (MCP) servers for developers, including Kubernetes, Context7, and GitHub, along with essential safety guardrails.
How to run OpenAI's gpt-oss models locally with RamaLama
Learn how to run OpenAI gpt-oss open-weight models locally and securely using RamaLama, a CLI tool that leverages OCI containers and automatic GPU detection.
What is llm-d and why do we need it?
Discover llm-d, an open source Kubernetes-native framework for distributed AI inference that improves performance and reduces costs through disaggregation and intelligent scheduling.
LLM compression and optimization: Cheaper inference with fewer hardware resources
Learn how model compression techniques like quantization and sparsity can significantly accelerate inference, reduce costs, and enable efficient AI deployment.
Can you vibe code without knowing how to code?
Explore how AI-powered tools like Cursor are changing software development through vibe coding, and what you need to know before diving in.
Alignment tuning and RAG: What you should know
Explore how alignment tuning and retrieval-augmented generation (RAG) are two strategies for customizing large language models for enterprise use cases.
Get started with bootable containers and image mode for RHEL
Learn how to create and manage bootable containers using Podman Desktop and the bootc extension to build workloads deployable from bare metal to cloud environments.
How to make generative AI more consumable
Learn about the three stages of AI adoption—utilization, adoption, and customization—and how open frameworks make generative AI accessible for enterprises.
IBM’s Granite foundation model: A detailed look at its training data
Explore IBM’s Granite family of models, with a transparent look into its training data, datasets, and enhancements made to Granite 13b models.
Enhance LLMs and streamline MLOps using InstructLab and KitOps
Add knowledge to large language models with InstructLab and streamline MLOps using KitOps for efficient model improvement and deployment.
How InstructLab’s Synthetic Data Generation Enhances LLMs
InstructLab is a community-driven project designed to simplify the process of contributing to and enhancing large language models (LLMs) through synthetic data generation.
Supercharge Your Development with Open Source AI Code Assistants
Learn how to integrate powerful AI code assistants into your IDE using open source tools like Continue, Ollama, and the Granite family of code models.
Experiment and test AI models with Podman AI Lab
Discover how Podman AI Lab's Playground feature accelerates your AI application development workflow
Getting started with InstructLab for generative AI model tuning
Learn how to get started with InstructLab, an open source project that enables community-driven alignment of large language models on consumer hardware.
Getting started with Podman Desktop on Windows
Learn how to install, setup, and use Podman Desktop on Windows, allowing you to manage and run containers on your Windows machine.
Deploy and test Kubernetes containers using Podman Desktop
Deploy and test a containerized application from your desktop to the no-cost Developer Sandbox for Red Hat OpenShift using Podman Desktop's Developer Sandbox extension.
Intro to Podman
Podman is an alternative to the Docker command-line interface that lets you run standalone, daemonless containers. See examples of how easy it is to use Podman.
Getting started with Buildah
Use Buildah to create a working Open Container Initiative container image from scratch, or from a pre-existing Dockerfile, before running it with Podman.
How to create cloud-native CI/CD Pipelines with Tekton
Let's get started with Tekton, an open-source cloud native CI/CD solution, by creating a real-world CI/CD pipeline.
Containers without Docker (podman, buildah, and skopeo)
Are there alternatives to Docker? Yes, and let's take a look at how we can get started with Podman, Buildah, and Skopeo.