Products
-
Docker Hardened Images: crafted by humans, protected by AI
At Docker, we are building our hardened images to exacting standards. That means carefully crafting by hand, because humans are still the best security architects. That said, we understand the value of AI and deploy it as an extra set of eyes at critical junctures in our Docker Hardened Image (DHI) build process. With this…
Read now
-
How to add MCP Servers to Gemini CLI with Docker MCP Toolkit
Learn how to connect Gemini CLI to MCP servers with Docker MCP Toolkit in this step-by-step example using the GitHub MCP server.
Read now
-
Build a Multi-Agent System in 5 Minutes with cagent
Learn what a multi-agent system is and how to build one in minutes using Docker cagent.
Read now
-
Join Us in Rebooting the Docker Model Runner Community!
Docker Model Runner is GA, now in all Docker versions with Vulkan support for nearly any GPU. Star, fork, and contribute in our unified repo.
Read now
-
Docker Model Runner on the new NVIDIA DGX Spark: a new paradigm for developing AI locally
We’re thrilled to bring NVIDIA DGX™ Spark support to Docker Model Runner. The new NVIDIA DGX Spark delivers incredible performance, and Docker Model Runner makes it accessible. With Model Runner, you can easily run and iterate on larger models right on your local machine, using the same intuitive Docker experience you already trust. In this…
Read now
-
100% Transparency and Five Pillars
How to Do Hardened Images (and Container Security) Right Container security is understandably a hot topic these days, with more and more workloads running atop this mainstay of the cloud native landscape. While I might be biased because I work at Docker, it is safe to say that containers are the dominant form factor for…
Read now
-
How to Add MCP Servers to Claude Code with Docker MCP Toolkit
Learn how to add and configure MCP servers for Claude Code using Docker MCP Toolkit.
Read now
-
LoRA Explained: Faster, More Efficient Fine-Tuning with Docker
LoRA is a method that freezes a base model and adds trainable adapters to teach pre-trained models new behaviors, without overwriting their existing knowledge.
Read now