Discover the toolingbehind modern intelligence
The operating system for AI infrastructure discovery. Search a live map of MCP servers, AI agents, LLM tools, automation systems, and developer infrastructure.
docker-agent
AI Agent Builder and Runtime by Docker Engineering
3kstars
369forks
Go
agentsai
Quality signals
StaleNo testsNo CIThin docsNo licensePopular
AI summary
Auto-generated overview of what this skill does and when to reach for it.
A toolkit to build and run AI agents that automate tasks inside Docker containers.
Use this when
- You need an AI agent to manage Docker containers
- You want to automate repetitive tasks inside containers
- You're prototyping AI-driven DevOps workflows
- You need a sandboxed environment for agent execution
- You're testing AI agent behavior in isolated containers
Don't use when
- You need a GUI for agent management
- You want a no-code automation platform
- Your agents must run outside Docker containers
Capabilities
- Build AI agents that interact with Docker containers
- Run agents in isolated, ephemeral containers
- Define agent behavior via YAML or code
- Integrate with Docker APIs for container control
- Support for multi-agent workflows
- Extensible with custom agent logic
InstallSKILLInstall as a Claude Code skill
Universal installANY TOOL
$ npx skillcity@latest docker/docker-agentAuto-detects the skill or MCP server in this repo and installs it for Claude Code, Codex, Cursor, Cline, OpenCode, Gemini CLI, Anti-Gravity, OpenClaw and Hermes.
Requires Node.js 18+ (ships with npx).
Or install manually
# Install into ~/.claude/skills/ mkdir -p ~/.claude/skills/docker-agent curl -fsSL https://raw.githubusercontent.com/docker/docker-agent/main/SKILL.md -o ~/.claude/skills/docker-agent/SKILL.md
Loading README…
Ask a simulated agent to run this skill. It loads the real SKILL.md and reasons over your task with NVIDIA.
docker-agent — sandboxAI sandbox
Pick a quick prompt below or type your own — watch the agent execute this skill step by step.
guest@skillcity:~$Try a prompt