From 0791b644cd6f836d715e56b9dab954f134a43392 Mon Sep 17 00:00:00 2001 From: Arthur Date: Fri, 29 Aug 2025 19:29:22 +0200 Subject: [PATCH 1/6] cagent: add docs --- assets/icons/cagent.svg | 14 +++ content/manuals/_index.md | 5 +- content/manuals/ai/cagent/_index.md | 123 +++++++++++++++++++++++ content/manuals/ai/mcp-gateway/_index.md | 1 + content/manuals/testcontainers.md | 7 +- 5 files changed, 146 insertions(+), 4 deletions(-) create mode 100644 assets/icons/cagent.svg create mode 100644 content/manuals/ai/cagent/_index.md diff --git a/assets/icons/cagent.svg b/assets/icons/cagent.svg new file mode 100644 index 000000000000..669a0e7b3fb7 --- /dev/null +++ b/assets/icons/cagent.svg @@ -0,0 +1,14 @@ + + + + + + + + + + + + + + diff --git a/content/manuals/_index.md b/content/manuals/_index.md index 58b911701cfe..5e750b8c6792 100644 --- a/content/manuals/_index.md +++ b/content/manuals/_index.md @@ -36,7 +36,10 @@ params: description: Manage and secure your AI tools with a single gateway. icon: /icons/toolkit.svg link: /ai/mcp-gateway/ - + - title: Cagent + description: The open-source multi-agent solution to assist you in your tasks. + icon: /icons/cagent.svg + link: /ai/cagent ai: - title: Ask Gordon description: Streamline your workflow and get the most out of the Docker ecosystem with your personal AI assistant. diff --git a/content/manuals/ai/cagent/_index.md b/content/manuals/ai/cagent/_index.md new file mode 100644 index 000000000000..ea37dc485ea2 --- /dev/null +++ b/content/manuals/ai/cagent/_index.md @@ -0,0 +1,123 @@ +--- +title: cagent +description: cagent lets you build, orchestrate, and share AI agents that work together as a team. +weight: 60 +params: + sidebar: + group: Open source +keywords: [ai, agent, cagent] +--- + +`cagent` is lets you build, orchestrate, and share AI agents. Use it to build AI +agents that can work as a team. Build a root agent that can delegate +tasks to sub-agents. Each agent can use the model of your choice, with the +parameters of your choice. + +## Key features + +- ️Multi-tenant architecture with client isolation and session management. +- Rich tool ecosystem via Model Context Protocol (MCP) integration. +- Hierarchical agent system with intelligent task delegation. +- Multiple interfaces including CLI, TUI, API server, and MCP server. +- Agent distribution via Docker registry integration. +- Security-first design with proper client scoping and resource isolation. +- Event-driven streaming for real-time interactions. +- Multi-model support (OpenAI, Anthropic, Gemini, DMR, Docker AI Gateway). + +## Get started with cagent + +1. Download the [latest release](https://github.com/docker/cagent/releases) + for your operating system. + + > [!NOTE] + > You may need to give the release executable permissions. + > On MacOS and Linux, do so by running: + + ```console + chmod +x /path/to/downloads/cagent-linux-64 + ``` + +1. Optional: Rename the binary as needed and update your PATH to include + cagent's executable. + +1. Set the following environment variables: + + ```bash + # If using the Docker AI Gateway, set this env var or use + # the `--models-gateway url_to_docker_ai_gateway` CLI flag + + export CAGENT_MODELS_GATEWAY=url_to_docker_ai_gateway + + # Alternatively, you to need set keys for remote inference services + # These are not needed if you are using Docker AI Gateway + + export OPENAI_API_KEY=your_api_key_here # For OpenAI models + export ANTHROPIC_API_KEY=your_api_key_here # For Anthopic models + export GOOGLE_API_KEY=your_api_key_here # For Gemini models + ``` + +1. Create an agent by saving this sample as `assistant.yaml`: + + ```yaml {title="assistant.yaml"} + agents: + root: + model: openai/gpt-5-mini + description: A helpful AI assistant + instruction: | + You are a knowledgeable assistant that helps users with various tasks. + Be helpful, accurate, and concise in your responses. + ``` + +1. Start your prompt with your agent: + + ```bash + cagent run my-agent.yaml + ``` + +## Create an agentic team + +```yaml {title="agentic-team.yaml"} +agents: + root: + model: claude + description: "Main coordinator agent that delegates tasks and manages workflow" + instruction: | + You are the root coordinator agent. Your job is to: + 1. Understand user requests and break them down into manageable tasks + 2. Delegate appropriate tasks to your helper agent + 3. Coordinate responses and ensure tasks are completed properly + 4. Provide final responses to the user + When you receive a request, analyze what needs to be done and decide whether to: + - Handle it yourself if it's simple + - Delegate to the helper agent if it requires specific assistance + - Break complex requests into multiple sub-tasks + sub_agents: ["helper"] + + helper: + model: claude + description: "Assistant agent that helps with various tasks as directed by the root agent" + instruction: | + You are a helpful assistant agent. Your role is to: + 1. Complete specific tasks assigned by the root agent + 2. Provide detailed and accurate responses + 3. Ask for clarification if tasks are unclear + 4. Report back to the root agent with your results + + Focus on being thorough and helpful in whatever task you're given. + +models: + claude: + provider: anthropic + model: claude-sonnet-4-0 + max_tokens: 64000 +``` + +[See the reference documentation](https://github.com/docker/cagent/blob/main/docs/user-guide.md#configuration-reference). + +## Learn more about cagent + +For more information, see the following documentation in the +[GitHub repository](https://github.com/docker/cagent): + +- [User guide](https://github.com/docker/cagent/blob/main/docs/user-guide.md) +- [Configuration reference](https://github.com/docker/cagent/blob/main/docs/user-guide.md#configuration-reference) diff --git a/content/manuals/ai/mcp-gateway/_index.md b/content/manuals/ai/mcp-gateway/_index.md index ad9689e92f75..1cad4703fc92 100644 --- a/content/manuals/ai/mcp-gateway/_index.md +++ b/content/manuals/ai/mcp-gateway/_index.md @@ -2,6 +2,7 @@ title: MCP Gateway description: "Docker's MCP Gateway provides secure, centralized, and scalable orchestration of AI tools through containerized MCP servers—empowering developers, operators, and security teams." keywords: MCP Gateway +weight: 50 params: sidebar: group: Open source diff --git a/content/manuals/testcontainers.md b/content/manuals/testcontainers.md index 52a5c26560dd..0ed99d9e98cc 100644 --- a/content/manuals/testcontainers.md +++ b/content/manuals/testcontainers.md @@ -1,5 +1,6 @@ --- title: Testcontainers +weight: 40 description: Learn how to use Testcontainers to run containers programmatically in your preferred programming language. keywords: docker APIs, docker, testcontainers documentation, testcontainers, testcontainers oss, testcontainers oss documentation, docker compose, docker-compose, java, golang, go @@ -12,7 +13,7 @@ intro: icon: feature_search link: https://testcontainers.com/getting-started/#what-is-testcontainers - title: The Testcontainers workflow - description: Understand the Testcontainers workflow + description: Understand the Testcontainers workflow icon: explore link: https://testcontainers.com/getting-started/#testcontainers-workflow quickstart: @@ -44,8 +45,8 @@ The rest are community-driven and maintained by independent contributors. ### Prerequisites -Testcontainers requires a Docker-API compatible container runtime. -During development, Testcontainers is actively tested against recent versions of Docker on Linux, as well as against Docker Desktop on Mac and Windows. +Testcontainers requires a Docker-API compatible container runtime. +During development, Testcontainers is actively tested against recent versions of Docker on Linux, as well as against Docker Desktop on Mac and Windows. These Docker environments are automatically detected and used by Testcontainers without any additional configuration being necessary. It is possible to configure Testcontainers to work for other Docker setups, such as a remote Docker host or Docker alternatives. From 363d33f13dbcd66901ac3020313843dab5c406f1 Mon Sep 17 00:00:00 2001 From: Arthur Date: Mon, 1 Sep 2025 11:27:14 +0200 Subject: [PATCH 2/6] updates --- content/manuals/ai/cagent/_index.md | 200 +++++++++++++++++++++----- content/manuals/ai/cagent/examples.md | 166 +++++++++++++++++++++ 2 files changed, 327 insertions(+), 39 deletions(-) create mode 100644 content/manuals/ai/cagent/examples.md diff --git a/content/manuals/ai/cagent/_index.md b/content/manuals/ai/cagent/_index.md index ea37dc485ea2..cd92c1df6cca 100644 --- a/content/manuals/ai/cagent/_index.md +++ b/content/manuals/ai/cagent/_index.md @@ -8,10 +8,19 @@ params: keywords: [ai, agent, cagent] --- -`cagent` is lets you build, orchestrate, and share AI agents. Use it to build AI -agents that can work as a team. Build a root agent that can delegate -tasks to sub-agents. Each agent can use the model of your choice, with the -parameters of your choice. +cagent lets you build, orchestrate, and share AI agents. Use it to define AI +agents that work as a team. + +cagent relies on the concept of a _root agent_ that acts as a team lead and +delegates tasks to the sub-agents you define. +Each agent: +- uses the model of your choice, with the parameters of your choice. +- has access to the [built-in tools](#built-in-tools) and MCP servers + configured in the [Docker MCP gateway](/manuals/ai/mcp-gateway.md). +- works in its own context. They do not share knowledge. + +The root agent is your main contact point. Each agent has its own context, +they do not share knowledge. ## Key features @@ -30,52 +39,75 @@ parameters of your choice. for your operating system. > [!NOTE] - > You may need to give the release executable permissions. - > On MacOS and Linux, do so by running: + > You might need to give the binary executable permissions. + > On macOS and Linux, run: ```console chmod +x /path/to/downloads/cagent-linux-64 ``` + > [!NOTE] + > You can also build cagent from the source. See the [repository](https://github.com/docker/cagent?tab=readme-ov-file#build-from-source). + 1. Optional: Rename the binary as needed and update your PATH to include cagent's executable. 1. Set the following environment variables: ```bash - # If using the Docker AI Gateway, set this env var or use - # the `--models-gateway url_to_docker_ai_gateway` CLI flag + # If using the Docker AI Gateway, set this environment variable or use + # the `--models-gateway ` CLI flag - export CAGENT_MODELS_GATEWAY=url_to_docker_ai_gateway + export CAGENT_MODELS_GATEWAY= - # Alternatively, you to need set keys for remote inference services - # These are not needed if you are using Docker AI Gateway + # Alternatively, set keys for remote inference services. + # These are not needed if you are using Docker AI Gateway. - export OPENAI_API_KEY=your_api_key_here # For OpenAI models - export ANTHROPIC_API_KEY=your_api_key_here # For Anthopic models - export GOOGLE_API_KEY=your_api_key_here # For Gemini models + export OPENAI_API_KEY= # For OpenAI models + export ANTHROPIC_API_KEY= # For Anthropic models + export GOOGLE_API_KEY= # For Gemini models ``` 1. Create an agent by saving this sample as `assistant.yaml`: ```yaml {title="assistant.yaml"} agents: - root: - model: openai/gpt-5-mini - description: A helpful AI assistant - instruction: | - You are a knowledgeable assistant that helps users with various tasks. - Be helpful, accurate, and concise in your responses. - ``` + root: + model: openai/gpt-5-mini + description: A helpful AI assistant + instruction: | + You are a knowledgeable assistant that helps users with various tasks. + Be helpful, accurate, and concise in your responses. + ``` 1. Start your prompt with your agent: ```bash - cagent run my-agent.yaml + cagent run assistant.yaml ``` ## Create an agentic team +You can use AI prompting to generate a team of agents with the `cagent new` +command: + +```console +$ cagent new + +For any feedback, please visit: https://docker.qualtrics.com/jfe/form/SV_cNsCIg92nQemlfw + +Welcome to cagent! (Ctrl+C to exit) + +What should your agent/agent team do? (describe its purpose): + +> I need a cross-functional feature team. The team owns a specific product + feature end-to-end. Include the key responsibilities of each of the roles + involved (engineers, designer, product manager, QA). Keep the description + short, clear, and focused on how this team delivers value to users and the business. +``` + +Alternatively, you can write your configuration file by hand. For example: + ```yaml {title="agentic-team.yaml"} agents: root: @@ -83,14 +115,14 @@ agents: description: "Main coordinator agent that delegates tasks and manages workflow" instruction: | You are the root coordinator agent. Your job is to: - 1. Understand user requests and break them down into manageable tasks - 2. Delegate appropriate tasks to your helper agent - 3. Coordinate responses and ensure tasks are completed properly - 4. Provide final responses to the user + 1. Understand user requests and break them down into manageable tasks. + 2. Delegate appropriate tasks to your helper agent. + 3. Coordinate responses and ensure tasks are completed properly. + 4. Provide final responses to the user. When you receive a request, analyze what needs to be done and decide whether to: - - Handle it yourself if it's simple - - Delegate to the helper agent if it requires specific assistance - - Break complex requests into multiple sub-tasks + - Handle it yourself if it's simple. + - Delegate to the helper agent if it requires specific assistance. + - Break complex requests into multiple sub-tasks. sub_agents: ["helper"] helper: @@ -98,10 +130,10 @@ agents: description: "Assistant agent that helps with various tasks as directed by the root agent" instruction: | You are a helpful assistant agent. Your role is to: - 1. Complete specific tasks assigned by the root agent - 2. Provide detailed and accurate responses - 3. Ask for clarification if tasks are unclear - 4. Report back to the root agent with your results + 1. Complete specific tasks assigned by the root agent. + 2. Provide detailed and accurate responses. + 3. Ask for clarification if tasks are unclear. + 4. Report back to the root agent with your results. Focus on being thorough and helpful in whatever task you're given. @@ -112,12 +144,102 @@ models: max_tokens: 64000 ``` -[See the reference documentation](https://github.com/docker/cagent/blob/main/docs/user-guide.md#configuration-reference). +[See the reference documentation](https://github.com/docker/cagent?tab=readme-ov-file#-configuration-reference). + +## Built-in tools + +cagent includes a set of built-in tools that enhance your agents' capabilities. +You do not need to configure any external MCP tools to use them. + +```yaml +agents: + root: + # ... other config + toolsets: + - type: todo + - type: transfer_task +``` + +### Think tool + +The think tool allows agents to reason through problems step by step: + +```yaml +agents: + root: + # ... other config + toolsets: + - type: think +``` + +### Todo tool + +The todo tool helps agents manage task lists: + +```yaml +agents: + root: + # ... other config + toolsets: + - type: todo +``` + +### Memory tool + +The memory tool provides persistent storage: + +```yaml +agents: + root: + # ... other config + toolsets: + - type: memory + path: "./agent_memory.db" +``` + +### Task transfer tool + +The task transfer tool is an internal tool that allows an agent to delegate a task +to sub-agents. To prevent an agent from delegating work, make sure it does not have +sub-agents defined in its configuration. + +### Using tools via the Docker MCP Gateway + +If you use the [Docker MCP gateway](/manuals/ai/mcp-gateway.md), +you can configure your agent to interact with the +gateway and use the MCP servers configured in it. See [docker mcp +gateway run](/reference/cli/docker/mcp/gateway/gateway_run.md). + +For example, to enable an agent to use Duckduckgo via the MCP Gateway: + +```yaml +toolsets: + - type: mcp + command: docker + args: ["mcp", "gateway", "run", "--servers=duckduckgo"] +``` + +## Share your agents + +Agent configurations can be packaged and shared via Docker Hub. +Before you start, make sure you have a [Docker repository](/manuals/docker-hub/repos/create.md). + +To push an agent: + +```bash +cagent push ./.yaml / +``` + +To pull an agent: + +```bash +cagent pull / +``` -## Learn more about cagent +The agent's configuration file is named `_.yaml`. Run +it with the `cagent run ` command. -For more information, see the following documentation in the -[GitHub repository](https://github.com/docker/cagent): +## Related pages -- [User guide](https://github.com/docker/cagent/blob/main/docs/user-guide.md) -- [Configuration reference](https://github.com/docker/cagent/blob/main/docs/user-guide.md#configuration-reference) +For more information about cagent, see the +[GitHub repository](https://github.com/docker/cagent). \ No newline at end of file diff --git a/content/manuals/ai/cagent/examples.md b/content/manuals/ai/cagent/examples.md new file mode 100644 index 000000000000..8f0388852a2a --- /dev/null +++ b/content/manuals/ai/cagent/examples.md @@ -0,0 +1,166 @@ +--- +title: cagent examples +description: Get inspiration from agent examples +keywords: [ai, agent, cagent] +weight: 10 +--- + +Get inspiration from the following agent examples. + +## Agentic development team + +```yaml {title="dev-team.yaml"} +agents: + root: + model: claude + description: Technical lead coordinating development + instruction: | + You are a technical lead managing a development team. + Coordinate tasks between developers and ensure quality. + sub_agents: [developer, reviewer, tester] + + developer: + model: claude + description: Expert software developer + instruction: | + You are an expert developer. Write clean, efficient code + and follow best practices. + toolsets: + - type: filesystem + - type: shell + - type: think + + reviewer: + model: gpt4 + description: Code review specialist + instruction: | + You are a code review expert. Focus on code quality, + security, and maintainability. + toolsets: + - type: filesystem + + tester: + model: gpt4 + description: Quality assurance engineer + instruction: | + You are a QA engineer. Write tests and ensure + software quality. + toolsets: + - type: shell + - type: todo + +models: + gpt4: + provider: openai + model: gpt-4o + + claude: + provider: anthropic + model: claude-sonnet-4-0 + max_tokens: 64000 +``` + +## Research assistant + +```yaml {title="research-assistant.yaml"} +agents: + root: + model: claude + description: Research assistant with web access + instruction: | + You are a research assistant. Help users find information, + analyze data, and provide insights. + toolsets: + - type: mcp + command: mcp-web-search + args: ["--provider", "duckduckgo"] + - type: todo + - type: memory + path: "./research_memory.db" + +models: + claude: + provider: anthropic + model: claude-sonnet-4-0 + max_tokens: 64000 +``` + +## Technical blog writer + +```yaml {title="tech-blog-writer.yaml"} +#!/usr/bin/env cagent run +version: "1" + +agents: + root: + model: anthropic + description: Writes technical blog posts + instruction: | + You are the leader of a team of AI agents for a technical blog writing workflow. + + Here are the members in your team: + + - web_search_agent: Searches the web + - writer: Writes a 750-word technical blog post based on the chosen prompt + + + + 1. Call the `web_search_agent` agent to search the web to get + important information about the task that is asked + + 2. Call the `writer` agent to write a 750-word technical blog + post based on the research done by the web_search_agent + + + - Use the transfer_to_agent tool to call the right agent at the right + time to complete the workflow. + - DO NOT transfer to multiple members at once + - ONLY CALL ONE AGENT AT A TIME + - When using the `transfer_to_agent` tool, make exactly one call + and wait for the result before making another. Do not batch or + parallelize tool calls. + sub_agents: + - web_search_agent + - writer + toolsets: + - type: think + + web_search_agent: + model: anthropic + add_date: true + description: Search the web for information + instruction: | + Search the web for information + + Always include sources + toolsets: + - type: mcp + command: uvx + args: ["duckduckgo-mcp-server"] + + writer: + model: anthropic + description: Writes a 750-word technical blog post based on the chosen prompt. + instruction: | + You are an agent that receives a single technical writing prompt + and generates a detailed, informative, and well-structured technical blog post. + + - Ensure the content is technically accurate and includes relevant + code examples, diagrams, or technical explanations where appropriate. + - Structure the blog post with clear sections, including an introduction, + main content, and conclusion. + - Use technical terminology appropriately and explain complex concepts clearly. + - Include practical examples and real-world applications where relevant. + - Make sure the content is engaging for a technical audience while + maintaining professional standards. + + Constraints: + - DO NOT use lists + +models: + anthropic: + provider: anthropic + model: claude-3-5-sonnet-latest +``` + +See more examples in the [repository](https://github.com/docker/cagent/tree/main/examples). \ No newline at end of file From 427af5f9c39e294865bfbbe572d56b97ab488a52 Mon Sep 17 00:00:00 2001 From: Arthur Date: Mon, 1 Sep 2025 15:39:19 +0200 Subject: [PATCH 3/6] add summary bar --- content/manuals/ai/cagent/_index.md | 16 +++++++++++++++- data/summary.yaml | 2 ++ 2 files changed, 17 insertions(+), 1 deletion(-) diff --git a/content/manuals/ai/cagent/_index.md b/content/manuals/ai/cagent/_index.md index cd92c1df6cca..3efce45be6e5 100644 --- a/content/manuals/ai/cagent/_index.md +++ b/content/manuals/ai/cagent/_index.md @@ -8,6 +8,8 @@ params: keywords: [ai, agent, cagent] --- +{{< summary-bar feature_name="cagent" >}} + cagent lets you build, orchestrate, and share AI agents. Use it to define AI agents that work as a team. @@ -219,6 +221,18 @@ toolsets: args: ["mcp", "gateway", "run", "--servers=duckduckgo"] ``` +## CLI interactive commands + +You can use the following CLI commands, during +CLI sessions with your agents: + +| Command | Description | +|----------|------------------------------------------| +| /exit | Exit the program | +| /reset | Clear conversation history | +| /eval | Save current conversation for evaluation | +| /compact | Compact the current session | + ## Share your agents Agent configurations can be packaged and shared via Docker Hub. @@ -230,7 +244,7 @@ To push an agent: cagent push ./.yaml / ``` -To pull an agent: +To pull an agent to the current directory: ```bash cagent pull / diff --git a/data/summary.yaml b/data/summary.yaml index aaab67eeb85b..96dca7f1084f 100644 --- a/data/summary.yaml +++ b/data/summary.yaml @@ -59,6 +59,8 @@ Buildx no default: requires: Docker Buildx [0.10.4](/manuals/build/release-notes.md#0104) and later Cache backend API: availability: Experimental +cagent: + availability: Experimental Company: subscription: [Business] for: Administrators From 951bb8437570bcff26ceb5fcd7b999275f53a9e1 Mon Sep 17 00:00:00 2001 From: Arthur Date: Mon, 1 Sep 2025 15:54:19 +0200 Subject: [PATCH 4/6] update --- content/manuals/ai/cagent/_index.md | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/content/manuals/ai/cagent/_index.md b/content/manuals/ai/cagent/_index.md index 3efce45be6e5..7379d5fb0813 100644 --- a/content/manuals/ai/cagent/_index.md +++ b/content/manuals/ai/cagent/_index.md @@ -10,15 +10,15 @@ keywords: [ai, agent, cagent] {{< summary-bar feature_name="cagent" >}} -cagent lets you build, orchestrate, and share AI agents. Use it to define AI -agents that work as a team. +[cagent](https://github.com/docker/cagent) lets you build, orchestrate, and share +AI agents. Use it to define AI agents that work as a team. cagent relies on the concept of a _root agent_ that acts as a team lead and delegates tasks to the sub-agents you define. Each agent: - uses the model of your choice, with the parameters of your choice. - has access to the [built-in tools](#built-in-tools) and MCP servers - configured in the [Docker MCP gateway](/manuals/ai/mcp-gateway.md). + configured in the [Docker MCP gateway](/manuals/ai/mcp-gateway/_index.md). - works in its own context. They do not share knowledge. The root agent is your main contact point. Each agent has its own context, @@ -255,5 +255,6 @@ it with the `cagent run ` command. ## Related pages -For more information about cagent, see the -[GitHub repository](https://github.com/docker/cagent). \ No newline at end of file +- For more information about cagent, see the +[GitHub repository](https://github.com/docker/cagent). +- [Docker MCP Gateway](/manuals/ai/mcp-gateway/_index.md) \ No newline at end of file From 82c4fa8c67acab7afbd3b3c1f871736c809f0ad1 Mon Sep 17 00:00:00 2001 From: Arthur Date: Mon, 1 Sep 2025 16:11:53 +0200 Subject: [PATCH 5/6] vale --- _vale/config/vocabularies/Docker/accept.txt | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/_vale/config/vocabularies/Docker/accept.txt b/_vale/config/vocabularies/Docker/accept.txt index 71d9af1cf1c6..d041857da3df 100644 --- a/_vale/config/vocabularies/Docker/accept.txt +++ b/_vale/config/vocabularies/Docker/accept.txt @@ -1,6 +1,5 @@ (?i)[A-Z]{2,}'?s -[Dd]ev Adreno Aleksandrov Amazon @@ -17,6 +16,7 @@ Bugsnag BuildKit buildkitd BusyBox +cagent CD CentOS Ceph @@ -64,6 +64,7 @@ dockerignore Dockerize Dockerized Dockerizing +Duckduckgo Entra EPERM ESXi @@ -129,11 +130,11 @@ MySQL nameserver namespaced? namespacing +Neovim netfilter netlabel netlink Netplan -Neovim NFSv\d Nginx npm @@ -218,6 +219,7 @@ Zsh [Aa]nonymized? [Aa]utobuild [Aa]llowlist +[Aa]gentic [Aa]utobuilds? [Aa]utotests? [Bb]uildx @@ -265,6 +267,7 @@ Zsh [Ss]yscalls? [Ss]ysfs [Tt]eardown +[Tt]odo [Tt]oolchains? [Uu]narchived? [Uu]ngated From 25cb3033f76cb379e2a874f1fd95663c84c1b99a Mon Sep 17 00:00:00 2001 From: Usha Mandya <47779042+usha-mandya@users.noreply.github.com> Date: Thu, 4 Sep 2025 15:43:01 +0100 Subject: [PATCH 6/6] Apply suggestions from code review --- content/manuals/ai/cagent/_index.md | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/content/manuals/ai/cagent/_index.md b/content/manuals/ai/cagent/_index.md index 7379d5fb0813..f5fb8c112591 100644 --- a/content/manuals/ai/cagent/_index.md +++ b/content/manuals/ai/cagent/_index.md @@ -11,7 +11,7 @@ keywords: [ai, agent, cagent] {{< summary-bar feature_name="cagent" >}} [cagent](https://github.com/docker/cagent) lets you build, orchestrate, and share -AI agents. Use it to define AI agents that work as a team. +AI agents. You can use it to define AI agents that work as a team. cagent relies on the concept of a _root agent_ that acts as a team lead and delegates tasks to the sub-agents you define. @@ -22,7 +22,7 @@ Each agent: - works in its own context. They do not share knowledge. The root agent is your main contact point. Each agent has its own context, -they do not share knowledge. +they don't share knowledge. ## Key features @@ -96,7 +96,7 @@ command: ```console $ cagent new -For any feedback, please visit: https://docker.qualtrics.com/jfe/form/SV_cNsCIg92nQemlfw +For any feedback, visit: https://docker.qualtrics.com/jfe/form/SV_cNsCIg92nQemlfw Welcome to cagent! (Ctrl+C to exit) @@ -108,7 +108,7 @@ What should your agent/agent team do? (describe its purpose): short, clear, and focused on how this team delivers value to users and the business. ``` -Alternatively, you can write your configuration file by hand. For example: +Alternatively, you can write your configuration file manually. For example: ```yaml {title="agentic-team.yaml"} agents: @@ -151,7 +151,7 @@ models: ## Built-in tools cagent includes a set of built-in tools that enhance your agents' capabilities. -You do not need to configure any external MCP tools to use them. +You don't need to configure any external MCP tools to use them. ```yaml agents: @@ -202,7 +202,7 @@ agents: ### Task transfer tool The task transfer tool is an internal tool that allows an agent to delegate a task -to sub-agents. To prevent an agent from delegating work, make sure it does not have +to sub-agents. To prevent an agent from delegating work, make sure it doesn't have sub-agents defined in its configuration. ### Using tools via the Docker MCP Gateway