Installation
Install Docker Agent on your platform
Quickstart
Get your first agent running in minutes
Core Concepts
Understand agents, models, tools, and multi-agent orchestration
Configuration Reference
Complete reference for agent, model, and tool configuration
What is Docker Agent?
docker-agent lets you create and run intelligent AI agents that collaborate to solve complex problems — no code required.
It is a docker CLI plugin and can be run with docker agent. Define agents in YAML, give them tools, and let them work.
agent.yaml
Key features
Multi-agent architecture
Create teams of specialized agents that delegate tasks to each other automatically via a coordinator.
Rich tool ecosystem
Built-in tools for filesystem, shell, memory, and more. Extend with any MCP server — local, remote, or Docker-based.
AI provider agnostic
OpenAI, Anthropic, Gemini, AWS Bedrock, Docker Model Runner, and more. Switch providers without changing agent logic.
YAML configuration
Declarative, versionable, shareable agent configs. No framework code required.
Package and share
Push agents to any OCI-compatible registry. Pull and run them anywhere — just like container images.
Multiple interfaces
Beautiful TUI for interactive sessions, CLI for scripting, HTTP API for integrations, and MCP mode for interop.
Advanced reasoning
Built-in think, todo, and memory tools for complex multi-step reasoning and context retention.
RAG support
Pluggable retrieval with BM25, embeddings, hybrid search, and reranking for knowledge-grounded agents.
Quick example
Explore the docs
Agents
Learn about agent structure and configuration
Models
Configure AI models and providers
Tools
Give your agents capabilities with tools
Multi-Agent
Build teams of collaborating agents
TUI
Interactive terminal UI for agent sessions
MCP Mode
Expose agents as MCP tools