No description
  • Go 99.1%
  • HTML 0.3%
  • CSS 0.3%
  • Shell 0.2%
Find a file
Repository files (latest commit first)
Filename Latest commit message Latest commit date
Djordje Lukic cecf9f876c
Merge pull request #3764 from rumpl/feat/mermaid-state-directions
feat: support Mermaid state diagram directions
2026-07-21 08:47:32 +02:00
.agents/skills docs(skills): address review feedback on triage-prs 2026-06-26 10:15:55 +02:00
.devcontainer devcontainer support 2025-09-05 22:31:52 +00:00
.github feat(docs): generate self-maintaining llms.txt from nav.yml 2026-07-17 09:35:20 +02:00
cmd Merge pull request #3702 from dwin-gharibi/feat/budget-limits 2026-07-20 09:34:04 +02:00
docs fix: address review feedback on agent-level compaction_model 2026-07-20 12:17:30 +02:00
e2e fix(tui): truncate resize-handle status suffix on narrow terminals 2026-07-17 19:33:49 +02:00
examples fix: address review feedback on agent-level compaction_model 2026-07-20 12:17:30 +02:00
lint lint: flag DNS resolution (net.Lookup* / Resolver.Lookup*) in constructors 2026-07-08 17:39:44 +02:00
pkg feat: support Mermaid state diagram directions 2026-07-20 23:20:50 +02:00
scripts feat(docs): generate self-maintaining llms.txt from nav.yml 2026-07-17 09:35:20 +02:00
.dockerignore feat(hooks): add safety_check event + safer_shell builtin 2026-06-29 13:15:37 +02:00
.env.test feat: add OpenRouter provider 2026-06-30 18:42:48 +02:00
.gitattributes Make sure to stop the whole process group 2025-10-23 16:51:28 +02:00
.gitignore fix: address all Sayt-0 review comments (blockers + minor) 2026-06-29 17:13:40 +02:00
.golangci.yml test: replace time.Sleep with deterministic synchronization 2026-07-02 00:48:45 +02:00
agent-schema.json freeze config v12 and start v13 as latest 2026-07-20 13:36:51 +02:00
AGENTS.md docs: push for shorter, more concise code comments in AGENTS.md 2026-07-01 16:13:35 +02:00
CHANGELOG.md docs: update CHANGELOG.md for v1.113.0 2026-07-20 16:15:51 +00:00
docker-compose.yaml Some basic opentelemetry 2025-08-21 09:53:50 +02:00
Dockerfile fix: replace unauthenticated GitHub API call in template stage with COPY --from 2026-07-19 10:15:05 +00:00
go.mod bump github.com/openai/openai-go/v3 from v3.43.0 to v3.44.0 2026-07-20 14:22:49 +02:00
go.sum bump github.com/openai/openai-go/v3 from v3.43.0 to v3.44.0 2026-07-20 14:22:49 +02:00
golang_developer.yaml feat: optimize GPT-5.6 defaults and reasoning 2026-07-10 11:38:14 +02:00
LICENSE Add License 2025-07-18 19:41:53 +02:00
main.go Remove package to github.com/docker/docker-agent 2026-03-09 12:04:59 +01:00
README.md docs(getting-started): add Set Up a Model tutorial for API key and local paths 2026-07-07 12:17:00 +02:00
SECURITY.md Update docs and samples to rename docker-agent, change usage samples to docker agent 2026-03-04 16:40:39 +01:00
Taskfile.yml docs: switch github.io site from Jekyll to Hugo 2026-07-03 23:57:00 +02:00

🤖 Docker Agent 🤖

Build, run, and share AI agents with a declarative YAML config, rich tool ecosystem, and multi-agent orchestration.

docker agent in action

What is Docker Agent?

docker-agent lets you create and run intelligent AI agents that collaborate to solve complex problems — no code required.

docker-agent is a docker CLI plugin and can be run with docker agent.

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:duckduckgo
docker agent run agent.yaml

Key Features

  • 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

Install

Docker Desktop (4.63+) — docker-agent CLI plugin is pre-installed. Just run docker agent.

Homebrewbrew install docker-agent. Run docker-agent directly or symlink the binary to ~/.docker/cli-plugins/docker-agent and run docker agent.

Binary releases — Download from GitHub Releases. Symlink the docker-agent binary to ~/.docker/cli-plugins/docker-agent to be able to use docker agent, or use docker-agent directly.

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.

See Set Up a Model for the full walkthrough of both paths (cloud API key or local model).

Quick Start

# Run the default agent
docker agent run

# Run from the agent catalog
docker agent run agentcatalog/pirate

# Generate a new agent interactively
docker agent new

# Run your own config
docker agent run agent.yaml

More examples in the examples/ directory.

Documentation

📖 Full documentation

Contributing

Read the Contributing guide to get started. We use docker-agent to build docker-agent:

docker agent run ./golang_developer.yaml

Telemetry

We collect anonymous usage data to improve the tool. See Telemetry.

Community

Docker Community Slack · #docker-agent channel