Build, run, and share AI agents with a declarative YAML config, rich tool ecosystem, and multi-agent orchestration.
Docker cagent lets you create and run intelligent AI agents that collaborate to solve complex problems — no code required. Define agents in YAML, give them tools, and let them work.
agents:
root:
model: openai/gpt-5-mini
description: A helpful AI assistant
instruction: |
You are a knowledgeable assistant that helps users with various tasks.
Be helpful, accurate, and concise in your responses.
toolsets:
- type: mcp
ref: docker:duckduckgocagent run agent.yaml- Multi-agent architecture — Create teams of specialized agents that delegate tasks automatically
- Rich tool ecosystem — Built-in tools + any MCP server (local, remote, or Docker-based)
- AI provider agnostic — OpenAI, Anthropic, Gemini, AWS Bedrock, Mistral, xAI, Docker Model Runner, and more
- YAML configuration — Declarative, versionable, shareable
- Advanced reasoning — Built-in think, todo, and memory tools
- RAG — Pluggable retrieval with BM25, embeddings, hybrid search, and reranking
- Package & share — Push agents to any OCI registry, pull and run them anywhere
Docker Desktop (4.49+) — cagent is pre-installed. Just run cagent.
Homebrew — brew install cagent
Binary releases — Download from GitHub Releases.
Set at least one API key (or use Docker Model Runner for local models):
export OPENAI_API_KEY=sk-... # or ANTHROPIC_API_KEY, GOOGLE_API_KEY, etc.# Run the default agent
cagent run
# Run from the agent catalog
cagent run agentcatalog/pirate
# Generate a new agent interactively
cagent new
# Run your own config
cagent run agent.yamlMore examples in the examples/ directory.
- Installation · Quick Start
- Agents · Models · Tools · Multi-Agent
- Configuration Reference
- TUI · CLI · MCP Mode · RAG
- Model Providers · Docker Model Runner
Read the Contributing guide to get started. We use cagent to build cagent:
cagent run ./golang_developer.yamlWe collect anonymous usage data to improve the tool. See Telemetry.