{"slug": "docker-agent", "title": "Docker Agent", "summary": "Docker released docker-agent, a docker CLI plugin that lets developers build, run, and share AI agents through declarative YAML configuration with no code required. The tool supports multi-agent orchestration, any MCP server as a tool source, provider-agnostic models including OpenAI, Anthropic, Gemini, AWS Bedrock, Mistral, xAI, and Docker Model Runner, plus RAG with BM25, embeddings, hybrid search, and reranking, and agents can be pushed to any OCI registry. Docker Desktop 4.63+ ships the plugin pre-installed, and it is also available via Homebrew and GitHub binary releases.", "body_md": "Build, run, and share AI agents with a declarative YAML config, rich tool ecosystem, and multi-agent orchestration.\n\n`docker-agent` lets you create and run intelligent AI agents that collaborate to solve complex problems — no code required.\n\n`docker-agent` is a `docker` CLI plugin and can be run with `docker agent`.\n\nDefine agents in YAML, give them tools, and let them work.\n\n```\nagents:\n  root:\n    model: openai/gpt-5-mini\n    description: A helpful AI assistant\n    instruction: |\n      You are a knowledgeable assistant that helps users with various tasks.\n      Be helpful, accurate, and concise in your responses.\n    toolsets:\n      - type: mcp\n        ref: docker:duckduckgo\ndocker agent run agent.yaml\n```\n\n- **Multi-agent architecture** — Create teams of specialized agents that delegate tasks automatically\n- **Rich tool ecosystem** — Built-in tools + any[MCP](https://modelcontextprotocol.io/) server (local, remote, or Docker-based)\n- **AI provider agnostic** — OpenAI, Anthropic, Gemini, AWS Bedrock, Mistral, xAI,[Docker Model Runner](https://docs.docker.com/ai/model-runner/) , and more\n- **YAML configuration** — Declarative, versionable, shareable\n- **Advanced reasoning** — Built-in think, todo, and memory tools\n- **RAG** — Pluggable retrieval with BM25, embeddings, hybrid search, and reranking\n- **Package & share** — Push agents to any OCI registry, pull and run them anywhere\n\n**Docker Desktop** (4.63+) — docker-agent CLI plugin is pre-installed. Just run `docker agent`.\n\n**Homebrew** — `brew install docker-agent`. Run `docker-agent` directly or symlink the binary to `~/.docker/cli-plugins/docker-agent` and run `docker agent`.\n\n**Binary releases** — Download from [GitHub Releases](https://github.com/docker/docker-agent/releases). Symlink the `docker-agent` binary to `~/.docker/cli-plugins/docker-agent` to be able to use `docker agent`, or use `docker-agent` directly.\n\nSet at least one API key (or use [Docker Model Runner](https://docs.docker.com/ai/model-runner/) for local models):\n\n```\nexport OPENAI_API_KEY=sk-...        # or ANTHROPIC_API_KEY, GOOGLE_API_KEY, etc.\n```\n\nSee [Set Up a Model](https://docker.github.io/docker-agent/getting-started/set-up-a-model) for the full walkthrough of both paths (cloud API key or local model).\n\n```\n# Run the default agent\ndocker agent run\n\n# Run from an OCI registry\ndocker agent run myorg/agent:tag\n\n# Generate a new agent interactively\ndocker agent new\n\n# Run your own config\ndocker agent run agent.yaml\n```\n\nMore examples in the [`examples/`](https://github.com/docker/docker-agent/blob/main/examples/README.md) directory.\n\n- [Installation](https://docker.github.io/docker-agent/getting-started/installation) ·[Set Up a Model](https://docker.github.io/docker-agent/getting-started/set-up-a-model) ·[Quick Start](https://docker.github.io/docker-agent/getting-started/quickstart)\n- [Agents](https://docker.github.io/docker-agent/concepts/agents) ·[Models](https://docker.github.io/docker-agent/concepts/models) ·[Tools](https://docker.github.io/docker-agent/concepts/tools) ·[Multi-Agent](https://docker.github.io/docker-agent/concepts/multi-agent)\n- [Configuration Reference](https://docker.github.io/docker-agent/configuration/overview)\n- [TUI](https://docker.github.io/docker-agent/features/tui) ·[CLI](https://docker.github.io/docker-agent/features/cli) ·[MCP Mode](https://docker.github.io/docker-agent/features/mcp-mode) ·[RAG](https://docker.github.io/docker-agent/tools/rag)\n- [Model Providers](https://docker.github.io/docker-agent/providers/overview) ·[Docker Model Runner](https://docker.github.io/docker-agent/providers/dmr)\n\nRead the [Contributing guide](https://docker.github.io/docker-agent/community/contributing) to get started. We use `docker-agent` to build `docker-agent`:\n\n```\ndocker agent run ./golang_developer.yaml\n```\n\nWe collect anonymous usage data to improve the tool. See [Telemetry](https://docker.github.io/docker-agent/community/telemetry).", "url": "https://wpnews.pro/news/docker-agent", "canonical_source": "https://github.com/docker/docker-agent", "published_at": "2026-10-07 17:48:38+00:00", "updated_at": "2026-10-07 18:49:12.225362+00:00", "lang": "en", "topics": ["ai-agents", "ai-tools", "agent-protocols", "developer-tools", "ai-products"], "entities": ["Docker", "docker-agent", "Docker Desktop", "Docker Model Runner", "OpenAI", "Anthropic", "Gemini", "Model Context Protocol"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/docker-agent", "markdown": "https://wpnews.pro/news/docker-agent.md", "text": "https://wpnews.pro/news/docker-agent.txt", "jsonld": "https://wpnews.pro/news/docker-agent.jsonld"}}