diff --git a/content/manuals/ai/docker-agent/best-practices.md b/content/manuals/ai/docker-agent/best-practices.md index 550247864c..75a1f28a82 100644 --- a/content/manuals/ai/docker-agent/best-practices.md +++ b/content/manuals/ai/docker-agent/best-practices.md @@ -1,11 +1,11 @@ --- title: Best practices -description: Patterns and techniques for building effective Docker Agent agents +description: Patterns and techniques for building effective agents keywords: [docker agent, best practices, patterns, agent design, optimization] weight: 40 --- -Patterns you learn from building and running Docker Agent agents. These aren't +Patterns you learn from building and running agents with Docker Agent. These aren't features or configuration options - they're approaches that work well in practice. diff --git a/content/manuals/ai/docker-agent/integrations/_index.md b/content/manuals/ai/docker-agent/integrations/_index.md index a31c04ffd2..a9ab7235a5 100644 --- a/content/manuals/ai/docker-agent/integrations/_index.md +++ b/content/manuals/ai/docker-agent/integrations/_index.md @@ -1,6 +1,6 @@ --- title: Integrations -description: Connect Docker Agent agents to editors, MCP clients, and other agents +description: Connect agents to editors, MCP clients, and other agents keywords: [docker agent, integration, acp, mcp, a2a, editor, protocol] weight: 60 --- @@ -12,7 +12,7 @@ want to use them. Each integration type serves a specific purpose. ### ACP - Editor integration -Run Docker Agent agents directly in your editor (Neovim, Zed). The agent sees your +Run agents directly in your editor (Neovim, Zed). The agent sees your editor's file context and can read and modify files through the editor's interface. Use ACP when you want an AI coding assistant embedded in your editor. @@ -21,7 +21,7 @@ See [ACP integration](./acp.md) for setup instructions. ### MCP - Tool integration -Expose Docker Agent agents as tools in MCP clients like Claude Desktop or Claude +Expose agents as tools in MCP clients like Claude Desktop or Claude Code. Your agents appear in the client's tool list, and the client can call them when needed. Use MCP when you want Claude Desktop (or another MCP client) to have access to your specialized agents. @@ -30,7 +30,7 @@ See [MCP integration](./mcp.md) for setup instructions. ### A2A - Agent-to-agent communication -Run Docker Agent agents as HTTP servers that other agents or systems can call using +Run agents as HTTP servers that other agents or systems can call using the Agent-to-Agent protocol. Your agent becomes a service that other systems can discover and invoke over the network. Use A2A when you want to build multi-agent systems or expose your agent as an HTTP service. diff --git a/content/manuals/ai/docker-agent/integrations/a2a.md b/content/manuals/ai/docker-agent/integrations/a2a.md index e2952baa8e..afbe0d7a8d 100644 --- a/content/manuals/ai/docker-agent/integrations/a2a.md +++ b/content/manuals/ai/docker-agent/integrations/a2a.md @@ -1,12 +1,12 @@ --- title: A2A mode linkTitle: A2A -description: Expose Docker Agent agents via the Agent-to-Agent protocol +description: Expose agents via the Agent-to-Agent protocol keywords: [docker agent, a2a, agent-to-agent, multi-agent, protocol] weight: 40 --- -A2A mode runs your Docker Agent agent as an HTTP server that other systems can call +A2A mode runs your agent as an HTTP server that other systems can call using the Agent-to-Agent protocol. This lets you expose your agent as a service that other agents or applications can discover and invoke over the network. diff --git a/content/manuals/ai/docker-agent/integrations/acp.md b/content/manuals/ai/docker-agent/integrations/acp.md index 9a16306056..6caebfe128 100644 --- a/content/manuals/ai/docker-agent/integrations/acp.md +++ b/content/manuals/ai/docker-agent/integrations/acp.md @@ -1,12 +1,12 @@ --- linkTitle: ACP title: ACP integration -description: Configure your editor or IDE to use Docker Agent agents as coding assistants +description: Configure your editor or IDE to use agents as coding assistants keywords: [docker agent, acp, editor, ide, neovim, zed, integration] weight: 40 --- -Run Docker Agent agents directly in your editor using the Agent Client Protocol (ACP). +Run agents directly in your editor using the Agent Client Protocol (ACP). Your agent gets access to your editor's filesystem context and can read and modify files as you work. The editor handles file operations while cagent provides the AI capabilities. @@ -36,7 +36,7 @@ same files, same state. Before configuring your editor, you need: -- **cagent installed** - See the [installation guide](../_index.md#installation) +- **Docker Agent installed** - See the [installation guide](../_index.md#installation) - **Agent configuration** - A YAML file defining your agent. See the [tutorial](../tutorial.md) or [example configurations](https://github.com/docker/cagent/tree/main/examples) diff --git a/content/manuals/ai/docker-agent/integrations/mcp.md b/content/manuals/ai/docker-agent/integrations/mcp.md index 8b9cc1a1d9..7f5dfa7b9d 100644 --- a/content/manuals/ai/docker-agent/integrations/mcp.md +++ b/content/manuals/ai/docker-agent/integrations/mcp.md @@ -1,7 +1,7 @@ --- title: MCP mode linkTitle: MCP -description: Expose Docker Agent agents as tools to MCP clients like Claude Desktop and Claude Code +description: Expose agents as tools to MCP clients like Claude Desktop and Claude Code keywords: [ cagent, @@ -65,7 +65,7 @@ manage MCP servers interactively. Before configuring MCP integration, you need: -- **cagent installed** - See the [installation guide](../_index.md#installation) +- **Docker Agent installed** - See the [installation guide](../_index.md#installation) - **Agent configuration** - A YAML file defining your agent. See the [tutorial](../tutorial.md) or [example configurations](https://github.com/docker/cagent/tree/main/examples) @@ -93,7 +93,7 @@ Example configuration: { "mcpServers": { "myagent": { - "command": "/usr/local/bin/docker", + "command": "docker", "args": [ "agent", "serve", @@ -113,7 +113,7 @@ Example configuration: Configuration breakdown: -- `command`: Full path to your `docker` binary (use `which docker` to find it), or path to docker-agent if not using the docker CLI plugin +- `command`: Full path to your `docker` binary (use `which docker` to find it), or path to `docker-agent` if not using the Docker CLI plugin - `args`: MCP command arguments: - `mcp`: The subcommand to run cagent in MCP mode - `dockereng/myagent`: Your agent configuration (local file path or OCI @@ -181,7 +181,7 @@ Use the same syntax in MCP client configurations: { "mcpServers": { "myagent": { - "command": "/usr/local/bin/docker", + "command": "docker", "args": ["agent", "serve", "mcp", "agentcatalog/pirate"] } } diff --git a/content/manuals/ai/docker-agent/rag.md b/content/manuals/ai/docker-agent/rag.md index 3fbd7ec6f0..025535f52b 100644 --- a/content/manuals/ai/docker-agent/rag.md +++ b/content/manuals/ai/docker-agent/rag.md @@ -1,6 +1,6 @@ --- title: RAG -description: How RAG gives your Docker Agent agents access to codebases and documentation +description: How RAG gives your agents access to codebases and documentation keywords: [docker agent, rag, retrieval, embeddings, semantic search] weight: 70 --- diff --git a/content/manuals/ai/docker-agent/reference/config.md b/content/manuals/ai/docker-agent/reference/config.md index 2b49bb5e83..09be1981e6 100644 --- a/content/manuals/ai/docker-agent/reference/config.md +++ b/content/manuals/ai/docker-agent/reference/config.md @@ -6,7 +6,7 @@ keywords: [ai, agent, cagent, configuration, yaml] weight: 10 --- -This reference documents the YAML configuration file format for Docker Agent agents. +This reference documents the YAML configuration file format for agents suing Docker Agent. It covers file structure, agent parameters, model configuration, toolset setup, and RAG sources. diff --git a/content/manuals/ai/docker-agent/sharing-agents.md b/content/manuals/ai/docker-agent/sharing-agents.md index 77f0a883d8..44cadf21b8 100644 --- a/content/manuals/ai/docker-agent/sharing-agents.md +++ b/content/manuals/ai/docker-agent/sharing-agents.md @@ -82,7 +82,7 @@ Agents can be exposed as tools in MCP clients: { "mcpServers": { "myagent": { - "command": "/usr/local/bin/docker", + "command": "docker", "args": ["agent", "serve", "mcp", "agentcatalog/pirate"] } } diff --git a/content/manuals/ai/docker-agent/tutorial.md b/content/manuals/ai/docker-agent/tutorial.md index 360f1560c7..5d5e587829 100644 --- a/content/manuals/ai/docker-agent/tutorial.md +++ b/content/manuals/ai/docker-agent/tutorial.md @@ -25,7 +25,7 @@ A coding agent that can: ## What you'll learn -- How to configure Docker Agent agents in YAML +- How to configure agents in YAML with Docker Agents - How to give agents access to tools (filesystem, shell, etc.) - How to write effective agent instructions - How to compose multiple agents for specialized tasks @@ -43,7 +43,7 @@ Before starting, you need: ## Creating your first agent -A Docker Agent agent is defined in a YAML configuration file. The minimal agent needs +An agent is defined in a YAML configuration file. The minimal agent needs just a model and instructions that define its purpose. Create a file named `agents.yml`: @@ -288,4 +288,4 @@ You now know how to: different use cases - See the full [golang_developer.yaml](https://github.com/docker/cagent/blob/main/golang_developer.yaml) - that the Docker team uses to develop Docker Agent + that the Docker Team uses to develop Docker Agent