One Year of Model Context Protocol: From Experiment to Industry Standard
How a November 2024 Launch Became the "USB-C for AI" in Just 12 Months
Why Developers Are Moving to Docker Hardened Images (DHI)?
What if securing your containers was as simple as changing one line in your Dockerfile? Docker Hardened Images—now free for everyone—delivers zero-CVE base images and 95% smaller (distroless approach) while maintaining full compatibility with your existing workflows.
Docker Sandboxes Tutorial and Cheatsheet
Docker Sandboxes lets AI coding agents like Claude Code run safely in isolated containers. Get full autonomy without compromising your localhost security. Docker Desktop 4.50+
Understanding Claude's Conversation Compacting: A Deep Dive into Context Management
Ever seen "Compacting our conversation so we can keep chatting..." in Claude? It's not a bug—it's a feature that lets you have 100k+ token conversations without losing context. Here's how to leverage it for complex Docker and AI projects. 🧵
Kubernetes and GPU: The Complete Guide to Running AI/ML Workloads at Scale
A comprehensive deep dive into GPU orchestration in Kubernetes — from device plugins and the GPU Operator to advanced sharing strategies like MIG, MPS, and time-slicing. Learn how to schedule, monitor, and optimize GPU workloads for AI/ML at scale.
Complete Step-by-Step Tutorial: GPU-Accelerated Dental AI Training on NVIDIA Jetson AGX Thor
Robotics is at an inflection point. We're witnessing a fundamental shift from single-purpose, fixed-function robots to generalist machines that can adapt, reason, and perform diverse tasks across unpredictable environments. This transformation demands something unprecedented: the ability to run massive generative AI models—large language models (LLMs), vision language
Introducing the Penpot Docker Extension: One-Click Deployment for Self-Hosted Design
I am thrilled to share the release of the Penpot Docker Extension, a tool designed to streamline the deployment and management of a complete self-hosted Penpot instance directly within Docker Desktop.
Understanding Quantization in AI
Quantization = compressing a model by lowering the precision of numbers, making it smaller, faster, and cheaper to run, often with only a small drop in accuracy.
LLM Chat UIs That Support MCP: Your Complete Guide to Building Smarter AI Workflow
From Claude Desktop to Cursor: A complete breakdown of which AI chat interfaces support MCP—and which ones are worth your time. Because in 2025, your AI assistant should do more than just talk.
Connecting to Your NVIDIA Jetson AGX Thor via Type C cable on macOS
No monitor? No problem. Learn how a simple USB Type-C charging cable and serial console access saved a student demo at our Docker meetup.
Dynamic MCP: Teaching AI Agents to Configure Themselves
What if your AI chatbot could configure itself based on what customers ask, without developers editing config files? That's Dynamic MCP.
Running Vision Models Locally with Docker Model Runner: A Complete Tutorial
Want to add vision capabilities to your applications without sending data to external APIs? Docker Model Runner makes it straightforward to run multimodal AI models locally, giving you complete control over your data while using the familiar OpenAI-compatible API format.