diff --git a/content/manuals/agentic-platform/get-started.md b/content/manuals/agentic-platform/get-started.md index adc6c42269a..45ee64d51c5 100644 --- a/content/manuals/agentic-platform/get-started.md +++ b/content/manuals/agentic-platform/get-started.md @@ -1,43 +1,152 @@ --- title: Get started with Docker Agentic Platform linkTitle: Get started -description: Choose a kit and start a Docker Agentic Platform sandbox. -keywords: docker agentic platform, get started, kits, agents, sandbox, live terminal +description: Run your first cloud sandbox, ask an agent to review a sample project, save the result, and pause or delete the sandbox when you're finished. +keywords: docker agentic platform, get started, cloud sandboxes, agents, ssh, vscode, cursor weight: 10 aliases: - /agentic-platform/concepts/platform-model/ --- -Start a sandbox from the Console to work with an agent in the cloud. +Use a cloud sandbox to have an agent review a project without setting up the +project on your computer. In this walkthrough, you'll launch Claude Code, +clone a public sample application, and save a project review. Then you'll +pause the sandbox to return later or delete it when you're finished. + +You can complete the walkthrough in the browser. An optional step shows how +to open the same project in VS Code or Cursor over SSH. ## Before you begin -You need a personal Docker account with an active -[Docker Agentic Platform subscription](signup.md#activate-cloud-access). +You need: -If your kit needs a model provider API key, add it under **Secrets** or enter -it when you launch the sandbox. +- A personal Docker account with an active + [Docker Agentic Platform subscription](signup.md#activate-cloud-access). +- An Anthropic API key for the Claude Code kit. Add it under **Secrets** or + enter it when you launch the sandbox. Your model provider bills inference + separately from Docker's sandbox compute charges. -Browse [Kits](kits.md) to choose an agent such as Claude Code, Codex, or Hermes, -or use Shell to work without a pre-installed agent. The credentials you need -depend on the kit. For example, Hermes needs an Anthropic or OpenAI API key. +This example uses a public repository, so you don't need a GitHub token. +For other agents and their credentials, see [Kits](kits.md) and +[Secrets](secrets.md). ## Start a sandbox 1. Open [Docker Agentic Platform](https://agentic-platform.docker.com/) and select **New**. -2. Choose a kit. -3. Add any credentials requested by the launcher. -4. Review the [sandbox options](#sandbox-options), including the selected - network policies, and adjust them for your task. -5. Select **Run**. If a required credential is missing, the launcher opens its - input so you can add it. - -When the sandbox is ready, its terminal opens. Use it to work with your agent, -or run commands if you chose Shell. After launch, you can't change the selected -credentials, tools, network policies, or compute size. - -Return to **Sandboxes** to reopen the terminal. +2. Choose the Claude Code kit. +3. Add your Anthropic API key if it isn't already saved. Don't enter it in + the agent's prompt or in a file inside the sandbox. +4. Keep the defaults and select **Run**. + +On your first launch, the default **Open** network policy permits outbound +access to any host. If you're using a custom policy, make sure it permits +GitHub and your model provider. See [Network policies](policies.md). + +When the sandbox is ready, its terminal opens with Claude Code. After launch, +you can't change the selected credentials, tools, network policies, or compute +size. See [Sandbox options](#sandbox-options) for other launch settings. + +## Give the agent a task + +Your local files aren't mounted in a cloud sandbox. Ask Claude Code to clone +and review a public sample project: + +```text +Clone https://github.com/docker/welcome-to-docker.git into +/home/agent/workspace/project, then review the application. +Read the source, package.json, and Dockerfile. Don't modify the application +or install dependencies. +Write /home/agent/workspace/review.md with: +- A short explanation of what the application does. +- The commands defined in package.json for running and building it. +- An explanation of how the Dockerfile builds and serves the application. +- One small improvement you'd recommend, with the relevant file path. +Base the review on the files you read. Don't claim to have run the application. +Summarize your findings in your response. +``` + +Claude Code summarizes the project in the conversation and saves the review +at `/home/agent/workspace/review.md`. You can ask follow-up questions or give +it another task in the same session. + +## Keep your work + +The cloned project and review are stored in the sandbox. Files don't sync +automatically with your computer or a remote repository. They remain available +when you pause and resume the sandbox, but are lost when you delete it. + +To keep files outside the sandbox, use the CLI to +[transfer files](/manuals/ai/sandboxes/cloud/usage.md#transfer-files), or commit +and push changes to a repository. Include a +[GitHub credential](secrets.md#github-credential) when launching a sandbox that +needs to push changes. + +## Open the project in your editor (optional) + +Open the project and review in VS Code or Cursor over SSH. Your editor +runs on your computer, while the files and terminal commands stay in the +cloud sandbox. + +1. Install the [Docker Sandboxes CLI](/manuals/ai/sandboxes/install.md), + version 0.45.0 or later. +2. In a terminal on your computer, sign in with the same Docker account you + used in the Console and configure cloud SSH access: + + ```console + $ sbx login + $ sbx --cloud setup ssh + $ sbx --cloud ls + ``` + +3. Find your sandbox in the list and copy its `sbx_`-prefixed ID. Test the + connection, replacing `` with that ID: + + ```console + $ ssh @sbx_cloud + ``` + + A successful connection opens a shell inside the cloud sandbox. Run `exit` + to return to your computer's terminal. +4. In VS Code, install the + [Remote - SSH extension](https://marketplace.visualstudio.com/items?itemName=ms-vscode-remote.remote-ssh). + In Cursor, install its Remote - SSH support. +5. Open your editor's Command Palette and run **Remote-SSH: Connect to Host**. + Enter `@sbx_cloud`, using the same ID as in the SSH command. +6. Open `/home/agent/workspace` in the remote window. You'll find the cloned + application in `project` and the agent's output in `review.md`. + +The first connection installs the editor's server inside the sandbox. + +To download the review, run this command in a terminal on your computer: + +```console +$ sbx --cloud cp :/home/agent/workspace/review.md ./review.md +``` + +## Pause, keep running, or delete the sandbox + +Closing the browser or disconnecting your editor leaves the sandbox running. +An agent can continue working until you pause or delete the sandbox, or its +timer expires. Compute is billed while the sandbox runs, even when the agent +has finished its task. + +Return to **Sandboxes** in the Console and choose what to do next: + +- Pause the sandbox to stop compute charges and keep its files. Confirm that + it is paused in the list. To continue later, reopen the sandbox and resume + it. Resuming starts a fresh timer with the original duration. +- Leave it running if the agent still has work to do. Check the expiration + time: the default **Stop** action stops the sandbox after one hour, including + background processes, and keeps its files. +- Delete it when you no longer need it. Save the review or push any changes + you want to keep first. Deletion removes files stored only in the sandbox. + +For more detail, see [Lifecycle actions](sandboxes.md#manage-the-lifecycle). +To run a task from your own terminal, follow the +[cloud CLI walkthrough](/manuals/ai/sandboxes/cloud/_index.md#get-started). +For programmatic workflows, see the +[Sandboxes API quickstart](/manuals/ai/sandboxes-api/get-started.md). ## Sandbox options