# docker/docker-agent

AI Agent Builder and Runtime by Docker Engineering

Repository: https://github.com/docker/docker-agent
Canonical: https://ross.abutalabs.com/products/docker-agent
Homepage: https://docker.github.io/docker-agent/
Language: Go
License: Apache-2.0
License Family: permissive
Topics: agents, ai
Last push: 2026-08-26T20:43:00+00:00

## Health v2 (maintenance only)
Score: 80/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 99, release rhythm 86, longevity 26
- inputs: {"age_days": 366, "days_push": 7, "days_rel": 12, "gap_med": 0, "n_releases_24m": 240}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3289, forks 443 (observed 2026-08-28T04:07:53.856942+00:00)

## What it is
Docker Agent is an open-source CLI (and Docker CLI plugin) that lets developers build, run, and share AI agents defined declaratively in YAML or HCL, with multi-agent orchestration, MCP tool integration, and RAG support. Agents are packaged and distributed via OCI registries, mirroring the container workflow of build, run, and push.

## Use cases
- run ai agents from a yaml file
- build multi-agent teams without writing code
- give an llm agent tools like filesystem and shell access
- share ai agents through an oci registry
- connect agents to mcp servers
- add rag retrieval to an ai agent
- run a local coding assistant agent in the terminal

## When to choose
- you want declarative, config-driven agents instead of writing orchestration glue code
- you already use Docker and want agents in the same workflow
- you need multi-agent delegation with MCP tool support
- you want to distribute agents as OCI artifacts

## When to avoid
- you need a code-first agent framework with fine-grained programmatic control
- you want a hosted SaaS agent platform with a web UI
- you need to train or fine-tune models rather than run agents

## Facets
- artifact type: cli-tool
- maturity: active
- function: agent-framework, cli, rag, mcp, llm-inference, chatbot
- domain: large-language-models, developer-tools
- platform: cli, cross-platform, windows, go
- tags: docker-cli-plugin, yaml-configuration, multi-agent-orchestration, oci-registry, declarative-agents, tool-use, ai-agents, command-line, retrieval-augmented-generation, docker, macos, linux

## Member repositories
- docker/docker-agent (main) score 80

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:53.856942+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T07:22:50.370030+00:00, confidence not recorded.
  - readme: https://github.com/docker/docker-agent (fetched 2026-08-28T04:07:53.856942+00:00, sha 3444e7a11670)
  - homepage: https://docker.github.io/docker-agent/ (fetched 2026-08-29T09:35:45.668042+00:00, sha b59f8cba2d91)
- Data as of 2026-08-30T08:39:29.467469+00:00.