Uploaded September 2025 | Updated September 2026, 1 week ago
In this AI Guide to the Galaxy episode, Oleg sits down with Principal Software Engineer Djordje Lukic to demo cagent — Docker’s open-source, declarative agent builder and runtime. See how to define agents in YAML, run them with Docker Model Runner (DMR) or external providers (OpenAI/Gemini/etc.), plug into Model Context Protocol (MCP) servers via the Docker MCP Toolkit, compose multi-agent systems with sub-agents, and share agents as OCI artifacts on Docker Hub.
What you’ll learn
-- Why cagent focuses on declarative YAML for agents (instructions, model, tools, chat loop)
-- Running agents locally with DMR, or swapping to cloud LLMs
-- Using MCP servers (e.g., Context-aware docs lookup) and built-in toolsets (shell, filesystem, to-do, “thinking”)
-- Creating multi-agent setups where sub-agents are invoked as tool calls
-- Pushing/pulling agents as OCI artifacts to Docker Hub for easy sharing
-- Bootstrapping: an agent that creates agents from a CLI prompt
-- Where to get binaries (GitHub Releases for Linux, Windows, macOS)
🔥 Want More Docker Content?
If you found this demo exciting, hit that like button and subscribe for more! We’ve got even more Docker demos coming your way in this ongoing series showcasing new tools, integrations, and powerful workflows to level up your projects. Stay tuned!
Where to find Docker:
Docker: docker.com
LinkedIn: linkedin.com/company/docker
Bluesky: https://bsky.app/profile/docker.com
X: @docker
Instagram: @dockerinc
#Docker #AIGuidetotheGalaxy #CAgent #AIAgents #MCP #Golang #YAML #DevTools #DockerModelRunner #OCI #OpenSource
In this AI Guide to the Galaxy episode, Oleg sits down with Principal Software Engineer Djordje Lukic to demo cagent — Docker’s open-source, declarative agent builder and runtime. See how to define agents in YAML, run them with Docker Model Runner (DMR) or external providers (OpenAI/Gemini/etc.), plug into Model Context Protocol (MCP) servers via the Docker MCP Toolkit, compose multi-agent systems with sub-agents, and share agents as OCI artifacts on Docker Hub.
What you’ll learn
-- Why cagent focuses on declarative YAML for agents (instructions, model, tools, chat loop)
-- Running agents locally with DMR, or swapping to cloud LLMs
-- Using MCP servers (e.g., Context-aware docs lookup) and built-in toolsets (shell, filesystem, to-do, “thinking”)
-- Creating multi-agent setups where sub-agents are invoked as tool calls
-- Pushing/pulling agents as OCI artifacts to Docker Hub for easy sharing
-- Bootstrapping: an agent that creates agents from a CLI prompt
-- Where to get binaries (GitHub Releases for Linux, Windows, macOS)
🔥 Want More Docker Content?
If you found this demo exciting, hit that like button and subscribe for more! We’ve got even more Docker demos coming your way in this ongoing series showcasing new tools, integrations, and powerful workflows to level up your projects. Stay tuned!
Where to find Docker:
Docker: docker.com
LinkedIn: linkedin.com/company/docker
Bluesky: https://bsky.app/profile/docker.com
X: @docker
Instagram: @dockerinc
#Docker #AIGuidetotheGalaxy #CAgent #AIAgents #MCP #Golang #YAML #DevTools #DockerModelRunner #OCI #OpenSource
