diff --git a/content/manuals/ai/docker-agent/integrations/_index.md b/content/manuals/ai/docker-agent/integrations/_index.md index a9ab7235a5..ff22ba28da 100644 --- a/content/manuals/ai/docker-agent/integrations/_index.md +++ b/content/manuals/ai/docker-agent/integrations/_index.md @@ -5,7 +5,7 @@ keywords: [docker agent, integration, acp, mcp, a2a, editor, protocol] weight: 60 --- -cagent agents can integrate with different environments depending on how you +Agents created with Docker Agent can integrate with different environments depending on how you want to use them. Each integration type serves a specific purpose. ## Integration types diff --git a/content/manuals/ai/docker-agent/integrations/a2a.md b/content/manuals/ai/docker-agent/integrations/a2a.md index afbe0d7a8d..ca58923130 100644 --- a/content/manuals/ai/docker-agent/integrations/a2a.md +++ b/content/manuals/ai/docker-agent/integrations/a2a.md @@ -18,7 +18,7 @@ tools in MCP clients, see [MCP integration](./mcp.md). Before starting an A2A server, 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) - API keys configured - If using cloud model providers (see [Model @@ -74,7 +74,7 @@ $ curl http://localhost:8080/.well-known/agent-card "id": "agent_root", "name": "root", "description": "A helpful coding assistant", - "tags": ["llm", "cagent"] + "tags": ["llm", "dockeragent"] } ], "preferredTransport": "jsonrpc", @@ -165,7 +165,7 @@ specialist has access to the codebase tools it needs. ## Calling other A2A agents -Your cagent agents can call remote A2A agents as tools. Configure the A2A +Your agents can call remote A2A agents as tools. Configure the A2A toolset with the remote agent's URL: ```yaml diff --git a/content/manuals/ai/docker-agent/integrations/acp.md b/content/manuals/ai/docker-agent/integrations/acp.md index 6caebfe128..7029a72211 100644 --- a/content/manuals/ai/docker-agent/integrations/acp.md +++ b/content/manuals/ai/docker-agent/integrations/acp.md @@ -8,16 +8,16 @@ weight: 40 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 +modify files as you work. The editor handles file operations while Docker Agent provides the AI capabilities. -This guide shows you how to configure Neovim, or Zed to run cagent agents. If -you're looking to expose cagent agents as tools to MCP clients like Claude +This guide shows you how to configure Neovim, or Zed to run agents with Docker Agent. If +you're looking to expose agents as tools to MCP clients like Claude Desktop or Claude Code, see [MCP integration](./mcp.md) instead. ## How it works -When you run cagent with ACP, it becomes part of your editor's environment. You +When you run Docker Agent with ACP, it becomes part of your editor's environment. You select code, highlight a function, or reference a file - the agent sees what you see. No copying file paths or switching to a terminal. @@ -52,21 +52,21 @@ launching your editor. Zed has built-in ACP support. -1. Add cagent to your agent servers in `settings.json`: +1. Add `docker agent` to your agent servers in `settings.json`: ```json { "agent_servers": { - "my-cagent-team": { - "command": "cagent", - "args": ["acp", "agent.yml"] + "my-agent-team": { + "command": "docker", + "args": ["agent", "serve", "acp", "agent.yml"] } } } ``` Replace: - - `my-cagent-team` with the name you want to use for the agent + - `my-agent-team` with the name you want to use for the agent - `agent.yml` with the path to your agent configuration file. If you have multiple agent files that you like to run separately, you can @@ -83,17 +83,19 @@ which has native support for Docker Agent through a built-in adapter: 1. [Install CodeCompanion](https://codecompanion.olimorris.dev/installation) through your plugin manager. -2. Extend the `cagent` adapter in your CodeCompanion config: +2. Extend the `dockeragent` adapter in your CodeCompanion config: ```lua require("codecompanion").setup({ adapters = { acp = { - cagent = function() - return require("codecompanion.adapters").extend("cagent", { + dockeragent = function() + return require("codecompanion.adapters").extend("dockeragent", { commands = { default = { - "cagent", + "docker", + "agent", + "serve", "acp", "agent.yml", }, @@ -115,7 +117,7 @@ which has native support for Docker Agent through a built-in adapter: :CodeCompanion ``` -4. Switch to the cagent adapter (keymap `ga` in the CodeCompanion buffer, by +4. Switch to the Docker Agent adapter (keymap `ga` in the CodeCompanion buffer, by default). See the [CodeCompanion ACP @@ -144,8 +146,8 @@ Use the same syntax in your editor configuration: { "agent_servers": { "myagent": { - "command": "cagent", - "args": ["acp", "agentcatalog/pirate"] + "command": "docker", + "args": ["agent", "serve", "acp", "agentcatalog/pirate"] } } } @@ -159,7 +161,7 @@ agents](../sharing-agents.md) for details on using OCI registries. Verify your configuration works: -1. Start the cagent ACP server using your editor's configured method +1. Start the Docker Agent ACP server using your editor's configured method 2. Send a test prompt through your editor's interface 3. Check that the agent responds 4. Verify filesystem operations work by asking the agent to read a file diff --git a/content/manuals/ai/docker-agent/integrations/mcp.md b/content/manuals/ai/docker-agent/integrations/mcp.md index 7f5dfa7b9d..6af2d3edac 100644 --- a/content/manuals/ai/docker-agent/integrations/mcp.md +++ b/content/manuals/ai/docker-agent/integrations/mcp.md @@ -14,7 +14,7 @@ keywords: weight: 50 --- -When you run cagent in MCP mode, your agents show up as tools in Claude Desktop +When you run Docker Agent in MCP mode, your agents show up as tools in Claude Desktop and other MCP clients. Instead of switching to a terminal to run your security agent, you ask Claude to use it and Claude calls it for you. @@ -23,7 +23,7 @@ embedded in your editor instead, see [ACP integration](./acp.md). ## How it works -You configure Claude Desktop (or another MCP client) to connect to cagent. Your +You configure Claude Desktop (or another MCP client) to connect to Docker Agent. Your agents appear in Claude's tool list. When you ask Claude to use one, it calls that agent through the MCP protocol. @@ -40,7 +40,7 @@ coordinator—depends on your agent descriptions and what you ask for. ## MCP Gateway Docker provides an [MCP Gateway](/ai/mcp-catalog-and-toolkit/mcp-gateway/) that -gives cagent agents access to a catalog of pre-configured MCP servers. Instead +gives agents access to a catalog of pre-configured MCP servers. Instead of configuring individual MCP servers, agents can use the gateway to access tools like web search, database queries, and more. @@ -54,7 +54,7 @@ agents: ref: docker:duckduckgo # Uses Docker MCP Gateway ``` -The `docker:` prefix tells cagent to use the MCP Gateway for this server. See +The `docker:` prefix tells Docker Agent to use the MCP Gateway for this server. See the [MCP Gateway documentation](/ai/mcp-catalog-and-toolkit/mcp-gateway/) for available servers and configuration options. @@ -77,12 +77,12 @@ Before configuring MCP integration, you need: ## MCP client configuration Your MCP client needs to know how to start Docker Agent and communicate with it. This -typically involves adding cagent as an MCP server in your client's +typically involves adding Docker Agent as an MCP server in your client's configuration. ### Claude Desktop -Add cagent to your Claude Desktop MCP settings file: +Add Docker Agent to your Claude Desktop MCP settings file: - macOS: `~/Library/Application Support/Claude/claude_desktop_config.json` - Windows: `%APPDATA%\Claude\claude_desktop_config.json` @@ -115,7 +115,7 @@ 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 - `args`: MCP command arguments: - - `mcp`: The subcommand to run cagent in MCP mode + - `mcp`: The subcommand to run `docker agent` in MCP mode - `dockereng/myagent`: Your agent configuration (local file path or OCI reference) - `--working-dir`: Optional working directory for agent execution @@ -128,13 +128,13 @@ appear as available tools. ### Claude Code -Add cagent as an MCP server using the `claude mcp add` command: +Add Docker Agent as an MCP server using the `claude mcp add` command: ```console $ claude mcp add --transport stdio myagent \ --env OPENAI_API_KEY=$OPENAI_API_KEY \ --env ANTHROPIC_API_KEY=$ANTHROPIC_API_KEY \ - -- cagent mcp /path/to/agent.yml --working-dir $(pwd) + -- docker agent serve mcp /path/to/agent.yml --working-dir $(pwd) ``` Command breakdown: @@ -144,7 +144,7 @@ Command breakdown: - `myagent`: Name for this MCP server in Claude Code - `--env`: Pass environment variables (repeat for each variable) - `--`: Separates Claude Code options from the MCP server command -- `docker agent serve mcp /path/to/agent.yml`: The cagent MCP command with the path to your +- `docker agent serve mcp /path/to/agent.yml`: The Docker Agent MCP command with the path to your agent configuration - `--working-dir $(pwd)`: Set the working directory for agent execution @@ -155,7 +155,7 @@ sessions. For other MCP-compatible clients, you need to: -1. Start cagent with `docker agent serve mcp /path/to/agent.yml --working-dir /project/path` +1. Start Docker Agent with `docker agent serve mcp /path/to/agent.yml --working-dir /project/path` 2. Configure the client to communicate with Docker Agent over stdio 3. Pass required environment variables (API keys, etc.) @@ -248,13 +248,13 @@ the right tools and that its instructions make sense when it's called directly. Verify your MCP integration works: 1. Restart your MCP client after configuration changes -2. Check that cagent agents appear as available tools +2. Check that agents appear as available tools 3. Invoke an agent with a simple test prompt 4. Verify the agent can access its configured tools (filesystem, shell, etc.) If agents don't appear or fail to execute, check: -- `cagent` binary path is correct and executable +- `docker agent` command is available and executable - Agent configuration file exists and is valid - All required API keys are set in environment variables - Working directory path exists and has appropriate permissions diff --git a/content/manuals/ai/docker-agent/model-providers.md b/content/manuals/ai/docker-agent/model-providers.md index 671a736dca..2ca872064c 100644 --- a/content/manuals/ai/docker-agent/model-providers.md +++ b/content/manuals/ai/docker-agent/model-providers.md @@ -5,7 +5,7 @@ keywords: [docker agent, model providers, api keys, anthropic, openai, google, g weight: 10 --- -To run cagent, you need a model provider. You can either use a cloud provider +To run Docker Agent, you need a model provider. You can either use a cloud provider with an API key or run models locally with [Docker Model Runner](local-models.md). @@ -14,7 +14,7 @@ models with Docker Model Runner](local-models.md). ## Supported providers -cagent supports these cloud model providers: +Docker Agent supports these cloud model providers: - Anthropic - Claude models - OpenAI - GPT models @@ -134,7 +134,7 @@ agents: base_url: https://your-provider.example.com/v1 ``` -By default, cagent uses the `OPENAI_API_KEY` environment variable for +By default, Docker Agent uses the `OPENAI_API_KEY` environment variable for authentication. If your provider uses a different variable, specify it with `token_key`: diff --git a/content/manuals/ai/docker-agent/rag.md b/content/manuals/ai/docker-agent/rag.md index 025535f52b..7769b14fb4 100644 --- a/content/manuals/ai/docker-agent/rag.md +++ b/content/manuals/ai/docker-agent/rag.md @@ -58,7 +58,7 @@ agents: rag: [codebase] ``` -When you reference `rag: [codebase]`, cagent: +When you reference `rag: [codebase]`, Docker Agent: 1. **At startup** - Indexes your documents (first run only, blocks until complete) 2. **During conversation** - Gives the agent a search tool @@ -70,7 +70,7 @@ what goes in context - the agent does. ### The indexing process -On first run, cagent: +On first run, Docker Agent: - Reads files from configured paths - Respects `.gitignore` patterns (can be disabled) @@ -78,13 +78,13 @@ On first run, cagent: - Creates searchable representations using your chosen strategy - Stores everything in a local database -Subsequent runs reuse the index. If files change, cagent detects this and +Subsequent runs reuse the index. If files change, Docker Agent detects this and re-indexes only what changed, keeping your knowledge base up to date without manual intervention. ## Retrieval strategies -Different content requires different retrieval approaches. cagent supports +Different content requires different retrieval approaches. Docker Agent supports three strategies, each optimized for different use cases. The defaults work well, but understanding the trade-offs helps you choose the right approach. diff --git a/content/manuals/ai/docker-agent/reference/config.md b/content/manuals/ai/docker-agent/reference/config.md index 09be1981e6..4ebaaf1e43 100644 --- a/content/manuals/ai/docker-agent/reference/config.md +++ b/content/manuals/ai/docker-agent/reference/config.md @@ -1,7 +1,7 @@ --- title: Configuration file reference linkTitle: Configuration file -description: Complete reference for the cagent YAML configuration file format +description: Complete reference for the Docker Agent YAML configuration file format keywords: [ai, agent, cagent, configuration, yaml] weight: 10 --- @@ -210,7 +210,7 @@ thinking_budget: 0 # Disabled ### Docker Model Runner (DMR) -Run local models. If `base_url` is omitted, cagent auto-discovers via Docker +Run local models. If `base_url` is omitted, Docker Agent auto-discovers via Docker Model plugin. ```yaml diff --git a/content/manuals/ai/docker-agent/reference/examples.md b/content/manuals/ai/docker-agent/reference/examples.md index 82fa44dbe0..a224965311 100644 --- a/content/manuals/ai/docker-agent/reference/examples.md +++ b/content/manuals/ai/docker-agent/reference/examples.md @@ -6,7 +6,7 @@ weight: 40 --- Get inspiration from the following agent examples. -See more examples in the [cagent GitHub repository](https://github.com/docker/cagent/tree/main/examples). +See more examples in the [Docker Agent GitHub repository](https://github.com/docker/cagent/tree/main/examples). ## Development team diff --git a/content/manuals/ai/docker-agent/reference/toolsets.md b/content/manuals/ai/docker-agent/reference/toolsets.md index cb4bd5dc2d..fb1a9703a2 100644 --- a/content/manuals/ai/docker-agent/reference/toolsets.md +++ b/content/manuals/ai/docker-agent/reference/toolsets.md @@ -23,7 +23,7 @@ Tool invocation flow: 1. Agent analyzes the task and determines which tool to use 2. Agent constructs tool parameters based on requirements -3. cagent executes the tool and returns results +3. Docker Agent executes the tool and returns results 4. Agent processes results and decides next steps Agents can call multiple tools in sequence or make decisions based on tool @@ -32,10 +32,10 @@ task and available capabilities. ## Tool types -cagent supports three types of toolsets: +Docker Agent supports three types of toolsets: Built-in toolsets -: Core functionality built directly into cagent (`filesystem`, `shell`, +: Core functionality built directly into Docker Agent (`filesystem`, `shell`, `memory`, etc.). These provide essential capabilities for file operations, command execution, and state management. MCP toolsets @@ -224,7 +224,7 @@ processes, interact with CLI tools, or perform system operations. The agent can run commands in the foreground or background. Commands execute in the current working directory and inherit environment -variables from the cagent process. This toolset is powerful but should be used +variables from the Docker Agent process. This toolset is powerful but should be used with appropriate security considerations. #### Configuration @@ -283,7 +283,7 @@ relationships between tasks, and automatically track which tasks are blocked by incomplete dependencies. Tasks are sorted by priority and blocking status, making it easy to identify the next actionable work. -Tasks are stored in a JSON file and persist across cagent sessions. +Tasks are stored in a JSON file and persist across Docker Agent sessions. #### Configuration @@ -331,7 +331,7 @@ context, previous decisions, and other information that should persist. Useful for agents that interact with users over time or need to maintain state about a project or environment. -Memories are stored in a local database file and persist across cagent +Memories are stored in a local database file and persist across Docker Agent sessions. #### Configuration diff --git a/content/manuals/ai/docker-agent/sharing-agents.md b/content/manuals/ai/docker-agent/sharing-agents.md index 44cadf21b8..07cd8003c0 100644 --- a/content/manuals/ai/docker-agent/sharing-agents.md +++ b/content/manuals/ai/docker-agent/sharing-agents.md @@ -67,8 +67,8 @@ the latest version: { "agent_servers": { "myagent": { - "command": "cagent", - "args": ["acp", "agentcatalog/pirate"] + "command": "docker", + "args": ["agent", "aserve", "acp", "agentcatalog/pirate"] } } }