fidzu : Docker

Building and Running Custom Models Is Still Hard Running AI models locally is still hard. Even as open-source LLMs grow more capable, actually getting them to run on your machine, with the right dependencies, remains slow, fragile, and inconsistent. There's two sides to this challenge: Model creation and optimization: making fine-tuning and quantization efficient. Model...

18 Nov 2025 5:57pm GMT

Running a Chat UI Agent doesn't have to involve a complicated setup. By combining Docker with the Vercel AI SDK, it's possible to build and launch a conversational interface in a clean, reproducible way. Docker ensures that the environment is consistent across machines, while the Vercel AI SDK provides the tools for handling streaming responses...

18 Nov 2025 2:00pm GMT

First steps: Run your first secure, production-ready image Container base images form the foundation of your application security. When those foundations contain vulnerabilities, every service built on top inherits the same risk. Docker Hardened Images addresses this at the source. These are continuously-maintained, minimal base images designed for security: stripped of unnecessary packages, patched proactively,...

14 Nov 2025 5:04pm GMT

AI-powered developer tools claim to boost your productivity, doing everything from intelligent auto-complete to (https://openai.com/index/introducing-codex/). But the productivity gains users report have been something of a mixed bag. Some groups claim to get 3-5x (or more), productivity boosts, while other devs claim to get no benefit at all-or even losses of up to 19%. I...

14 Nov 2025 2:00pm GMT

Docker Desktop now includes cagent bundled out of the box. This means developers can start building AI agents without a separate installation step. For those unfamiliar with cagent: it's Docker's open-source tool that lets you build AI agents using YAML configuration files instead of writing code. You define the agent's behavior and tools, and cagent...

13 Nov 2025 3:00pm GMT

This is Part 5 of our MCP Horror Stories series, where we examine real-world security incidents that highlight the critical vulnerabilities threatening AI infrastructure and demonstrate how Docker's comprehensive AI security platform provides protection against these threats. Model Context Protocol (MCP) promises seamless integration between AI agents and communication platforms like WhatsApp, enabling automated message...

13 Nov 2025 2:00pm GMT

Docker Desktop 4.50 represents a major leap forward in how development teams build, secure, and ship software. Across the last several releases, we've delivered meaningful improvements that directly address the challenges you face every day: faster debugging workflows, enterprise-grade security controls that don't get in your way, and seamless AI integration that makes modern development...

12 Nov 2025 2:00pm GMT

This post is for Linux users running Docker Engine (Community Edition) directly on their hosts. Docker Desktop users don't need to take any action - Engine updates are included automatically in future Desktop releases. Docker Engine v29 is a foundational release that sets the stage for the future of the Docker platform. While it may...

11 Nov 2025 3:16pm GMT

In just a year, the Model Context Protocol (MCP) has become the standard for connecting AI agents to tools and external systems. The Docker MCP Catalog now hosts hundreds of containerized local MCP servers, enabling developers to quickly experiment and prototype locally. We have now added support for remote MCP servers to the Docker MCP...

11 Nov 2025 1:53pm GMT

Welcome to the fourth annual Docker State of Application Development survey! Please help us better understand and serve the application development community with just 20 minutes of your time. We want to know where you're focused, what you're working on, and what is most important to you. Your thoughts and feedback will help us build...

10 Nov 2025 2:00pm GMT