diff --git a/content/guides/agentic-ai.md b/content/guides/agentic-ai.md index 0ad9b8839007..9fb50bf5665e 100644 --- a/content/guides/agentic-ai.md +++ b/content/guides/agentic-ai.md @@ -12,8 +12,8 @@ params: > [!TIP] > > This guide uses the familiar Docker Compose workflow to orchestrate agentic AI -> applications. For a smoother development experience, check out [Docker -> Docker Agent](../manuals/ai/docker-agent/_index.md), a purpose-built agent runtime that +> applications. For a smoother development experience, check out +> [Docker Agent](../manuals/ai/docker-agent/_index.md), a purpose-built agent runtime that > simplifies running and managing AI agents. ## Introduction @@ -65,11 +65,11 @@ all works together. To follow this guide, you need to: - - [Install Docker Desktop 4.43 or later](../get-started/get-docker.md) - - [Enable Docker Model Runner](/manuals/ai/model-runner.md#enable-dmr-in-docker-desktop) - - At least the following hardware specifications: - - VRAM: 3.5 GB - - Storage: 2.31 GB +- [Install Docker Desktop 4.43 or later](../get-started/get-docker.md) +- [Enable Docker Model Runner](/manuals/ai/model-runner.md#enable-dmr-in-docker-desktop) +- At least the following hardware specifications: + - VRAM: 3.5 GB + - Storage: 2.31 GB ## Step 1: Clone the sample application @@ -90,8 +90,9 @@ run in the cloud. This particular example uses the [Gemma 3 4B model](https://hub.docker.com/r/ai/gemma3) with a context size of `10000`. Hardware requirements: - - VRAM: 3.5 GB - - Storage: 2.31 GB + +- VRAM: 3.5 GB +- Storage: 2.31 GB If your machine exceeds those requirements, consider running the application with a larger context size or a larger model to improve the agents performance. You can easily @@ -113,7 +114,7 @@ To run the application locally, follow these steps: incorrect fact in the prompt and hit enter. An agent searches DuckDuckGo to verify it and another agent revises the output. - ![Screenshot of the application](./images/agentic-ai-app.png) + ![Screenshot of the application](./images/agentic-ai-app.png) 3. Press ctrl-c in the terminal to stop the application when you're done. @@ -136,7 +137,7 @@ services: depends_on: - mcp-gateway models: - gemma3 : + gemma3: endpoint_var: MODEL_RUNNER_URL model_var: MODEL_RUNNER_MODEL @@ -160,16 +161,16 @@ models: The app consists of three main components: - - The `adk` service, which is the web application that runs the agentic AI - application. This service talks to the MCP gateway and model. - - The `mcp-gateway` service, which is the MCP gateway that connects the app - to external tools and services. - - The `models` block, which defines the model to use with the application. +- The `adk` service, which is the web application that runs the agentic AI + application. This service talks to the MCP gateway and model. +- The `mcp-gateway` service, which is the MCP gateway that connects the app + to external tools and services. +- The `models` block, which defines the model to use with the application. When you examine the `compose.yaml` file, you'll notice two notable elements for the model: - - A service‑level `models` block in the `adk` service - - A top-level `models` block +- A service‑level `models` block in the `adk` service +- A top-level `models` block These two blocks together let Docker Compose automatically start and connect your ADK web app to the specified LLM. @@ -189,7 +190,7 @@ example, it uses the [`duckduckgo` MCP server](https://hub.docker.com/mcp/server/duckduckgo/overview) to perform web searches. -> [!TIP] +> [!TIP] > > Looking for more MCP servers to use? Check out the [Docker MCP > Catalog](https://hub.docker.com/catalogs/mcp/). diff --git a/content/manuals/ai-overview.md b/content/manuals/ai-overview.md new file mode 100644 index 000000000000..81c6b1f38fc7 --- /dev/null +++ b/content/manuals/ai-overview.md @@ -0,0 +1,46 @@ +--- +title: Docker AI overview +linkTitle: Overview +description: Docker's AI tools help you build, run, and manage AI-powered applications and workflows. +weight: 1 +keywords: docker, ai, gordon, docker agent, sandboxes, model runner, mcp +params: + sidebar: + group: AI +--- + +Docker provides tools for working with AI across your development workflow. +Each tool serves a different purpose. + +## Which tool do I need? + +| I want to... | Use | CLI command | +| --------------------------------------------------------------- | -------------------------------------------------------- | ---------------- | +| Get AI help with Docker tasks (containers, images, Dockerfiles) | [Gordon](./ai/gordon/) | `docker ai` | +| Run AI models locally with an OpenAI-compatible API | [Model Runner](./ai/model-runner/) | `docker model` | +| Connect AI tools to external services via MCP | [MCP Catalog and Toolkit](./ai/mcp-catalog-and-toolkit/) | `docker mcp` | +| Build and orchestrate custom multi-agent teams | [Docker Agent](./ai/docker-agent/) | `docker agent` | +| Run coding agents in isolated environments | [Docker Sandboxes](./ai/sandboxes/) | `docker sandbox` | + +## How these tools relate + +**Gordon** is Docker's built-in AI assistant. It helps with Docker-specific +tasks like debugging containers, writing Dockerfiles, and managing images. You +interact with it through Docker Desktop or the `docker ai` command. + +**Docker Agent** is an open-source framework for defining teams of AI agents +in YAML. You configure agents with specific roles, models, and tools, then +run them from your terminal. Docker Agent is a general-purpose agent runtime, +not specific to Docker tasks. + +**Docker Sandboxes** provides isolated microVM environments for running coding +agents. It supports multiple agents including Claude Code, Codex, Copilot, +Gemini, and Docker Agent. Sandboxes is the isolation layer — the agents +themselves are separate tools. + +**Model Runner** lets you run LLMs locally. Other tools like Docker Agent can +use Model Runner as a model provider. + +**MCP Catalog and Toolkit** manages connections between AI tools and external +services using the Model Context Protocol. Gordon, Docker Agent, and +third-party tools can all use MCP servers configured through the Toolkit. diff --git a/content/manuals/ai/docker-agent/_index.md b/content/manuals/ai/docker-agent/_index.md index e950408d8125..a67133586645 100644 --- a/content/manuals/ai/docker-agent/_index.md +++ b/content/manuals/ai/docker-agent/_index.md @@ -16,10 +16,15 @@ keywords: [ai, agent, docker agent, cagent] {{< summary-bar feature_name="Docker Agent" >}} -[Docker Agent](https://github.com/docker/cagent) is an open source tool for building -teams of specialized AI agents. Instead of prompting one generalist model, you -define agents with specific roles and instructions that collaborate to solve -problems. Run these agent teams from your terminal using any LLM provider. +[Docker Agent](https://github.com/docker/cagent) is an open-source framework +for building teams of specialized AI agents. Instead of prompting one +generalist model, you define agents with specific roles and instructions that +collaborate to solve problems. Run these agent teams from your terminal using +any LLM provider. + +> [!NOTE] +> Docker Agent is a framework for building and running custom agent teams. +> For Docker's built-in AI assistant, see [Gordon](/ai/gordon/) (`docker ai`). ## Why agent teams diff --git a/content/manuals/ai/gordon/_index.md b/content/manuals/ai/gordon/_index.md index 386680ba74e0..b7bb0e7bda09 100644 --- a/content/manuals/ai/gordon/_index.md +++ b/content/manuals/ai/gordon/_index.md @@ -1,6 +1,7 @@ --- title: Gordon -description: AI agent for Docker workflows - execute tasks, debug issues, and +description: + AI assistant for Docker workflows - execute tasks, debug issues, and manage containers with intelligent assistance weight: 40 params: @@ -15,7 +16,7 @@ aliases: {{< summary-bar feature_name="Gordon" >}} -Gordon is an AI agent that takes action on your Docker workflows. It analyzes +Gordon is an AI-powered assistant that takes action on your Docker workflows. It analyzes your environment, proposes solutions, and executes commands with your permission. Available in Docker Desktop and via the `docker ai` CLI command. diff --git a/content/manuals/ai/gordon/concepts/capabilities.md b/content/manuals/ai/gordon/concepts/capabilities.md index c82fed9c13a5..ac0c190772e9 100644 --- a/content/manuals/ai/gordon/concepts/capabilities.md +++ b/content/manuals/ai/gordon/concepts/capabilities.md @@ -14,13 +14,13 @@ explains what Gordon can do and the tools it uses. Gordon uses five capabilities to take action on your behalf: -- Specialized agents for specific Docker tasks +- Specialized sub-agents for specific Docker tasks - Shell access to run commands - Filesystem access to read and write files - Knowledge base of Docker documentation and best practices - Web access to fetch external resources -## Agent architecture +## Internal architecture Gordon uses a primary agent that handles most tasks, with a specialized sub-agent for specific workflows: diff --git a/content/manuals/ai/sandboxes/_index.md b/content/manuals/ai/sandboxes/_index.md index 3678b5fa6145..c15005fe41df 100644 --- a/content/manuals/ai/sandboxes/_index.md +++ b/content/manuals/ai/sandboxes/_index.md @@ -1,6 +1,6 @@ --- title: Docker Sandboxes -description: Run AI agents in isolated environments +description: Run AI coding agents in isolated environments weight: 20 params: sidebar: @@ -91,7 +91,7 @@ Docker Sandboxes works with multiple AI coding agents: - **Copilot** - GitHub Copilot agent (in development) - **Gemini** - Google's Gemini agent (in development) - **OpenCode** - Multi-provider agent with TUI interface (in development) -- **Docker Agent** - Docker's multi-provider coding agent (in development) +- **[Docker Agent](/ai/docker-agent/)** - Docker's multi-provider coding agent (in development) - **Kiro** - Interactive agent with device flow auth (in development) - **Shell** - Minimal sandbox for manual agent installation diff --git a/content/manuals/ai/sandboxes/agents/_index.md b/content/manuals/ai/sandboxes/agents/_index.md index 53f57d6b9d44..575da97124e1 100644 --- a/content/manuals/ai/sandboxes/agents/_index.md +++ b/content/manuals/ai/sandboxes/agents/_index.md @@ -12,16 +12,16 @@ inside microVMs with private Docker daemons. ## Supported agents -| Agent | Command | Status | Notes | -| ----------- | ---------- | ------------ | ----------------------------------------- | -| Claude Code | `claude` | Experimental | Most tested implementation | -| Codex | `codex` | Experimental | In development | -| Copilot | `copilot` | Experimental | In development | -| Gemini | `gemini` | Experimental | In development | -| Docker Agent | `cagent` | Experimental | In development | -| Kiro | `kiro` | Experimental | In development | -| OpenCode | `opencode` | Experimental | In development | -| Custom shell | `shell` | Experimental | Minimal environment for manual setup | +| Agent | Command | Status | Notes | +| --------------------------------- | ---------- | ------------ | ------------------------------------ | +| Claude Code | `claude` | Experimental | Most tested implementation | +| Codex | `codex` | Experimental | In development | +| Copilot | `copilot` | Experimental | In development | +| Gemini | `gemini` | Experimental | In development | +| [Docker Agent](/ai/docker-agent/) | `cagent` | Experimental | Also available as a standalone tool | +| Kiro | `kiro` | Experimental | In development | +| OpenCode | `opencode` | Experimental | In development | +| Custom shell | `shell` | Experimental | Minimal environment for manual setup | ## Experimental status @@ -67,7 +67,7 @@ agent (no fallback authentication methods are used). See the agent-specific documentation: - [Claude Code](./claude-code.md) -- [cagent](./cagent.md) +- [Docker Agent](./docker-agent.md) - [Codex](./codex.md) - [Copilot](./copilot.md) - [Gemini](./gemini.md) diff --git a/content/manuals/ai/sandboxes/agents/cagent.md b/content/manuals/ai/sandboxes/agents/docker-agent.md similarity index 86% rename from content/manuals/ai/sandboxes/agents/cagent.md rename to content/manuals/ai/sandboxes/agents/docker-agent.md index 0f248718db86..10e5fb4f849b 100644 --- a/content/manuals/ai/sandboxes/agents/cagent.md +++ b/content/manuals/ai/sandboxes/agents/docker-agent.md @@ -3,15 +3,19 @@ title: Docker Agent sandbox description: | Use Docker Agent in Docker Sandboxes with multi-provider authentication supporting OpenAI, Anthropic, and more. -keywords: docker, sandboxes, docker agent, ai agent, multi-provider, authentication +keywords: docker, sandboxes, docker agent, multi-provider, authentication +aliases: + - /ai/sandboxes/agents/cagent/ + - /manuals/ai/sandboxes/agents/cagent/ weight: 60 --- {{< summary-bar feature_name="Docker Sandboxes" >}} -This guide covers authentication, configuration, and usage of Docker Agent in -a sandboxed environment. [Docker Agent](/ai/docker-agent/) is Docker's open source coding -agent that supports multiple providers. +This page covers running [Docker Agent](/ai/docker-agent/) inside Docker +Sandboxes. Docker Agent is also available as a standalone CLI tool. See the +full documentation for standalone usage, configuration reference, and building +agent teams. ## Quick start