# Get started > Get started - Install the required components and learn how to build, deploy, and test agentic > workflows using DataRobot's pre-built templates for popular AI agent frameworks. This Markdown file sits beside the HTML page at the same path (with a `.md` suffix). It summarizes the topic and lists links for tools and LLM context. Companion generated at `2026-08-30T06:11:45.577619+00:00` (UTC). ## Primary page - [Get started](https://docs.datarobot.com/en/docs/agentic-ai/agentic-develop/agentic-get-started.html.md): Full documentation for this topic (Markdown sidecar). ## Sections on this page - [System requirements](https://docs.datarobot.com/en/docs/agentic-ai/agentic-develop/agentic-get-started.html.md#system-requirements): In-page section heading. - [Install prerequisite tools](https://docs.datarobot.com/en/docs/agentic-ai/agentic-develop/agentic-get-started.html.md#install-prerequisite-tools): In-page section heading. - [Windows prerequisites](https://docs.datarobot.com/en/docs/agentic-ai/agentic-develop/agentic-get-started.html.md#windows-prerequisites): In-page section heading. - [Detailed installation commands](https://docs.datarobot.com/en/docs/agentic-ai/agentic-develop/agentic-get-started.html.md#detailed-installation-commands): In-page section heading. - [Initialize your application](https://docs.datarobot.com/en/docs/agentic-ai/agentic-develop/agentic-get-started.html.md#initialize-your-application): In-page section heading. - [Run your agent](https://docs.datarobot.com/en/docs/agentic-ai/agentic-develop/agentic-get-started.html.md#run-your-agent): In-page section heading. - [Develop your agent](https://docs.datarobot.com/en/docs/agentic-ai/agentic-develop/agentic-get-started.html.md#develop-your-agent): In-page section heading. - [Deploy your agent](https://docs.datarobot.com/en/docs/agentic-ai/agentic-develop/agentic-get-started.html.md#deploy-your-agent): In-page section heading. - [Restricted network setup](https://docs.datarobot.com/en/docs/agentic-ai/agentic-develop/agentic-get-started.html.md#restricted-network-setup): In-page section heading. - [Python packages](https://docs.datarobot.com/en/docs/agentic-ai/agentic-develop/agentic-get-started.html.md#restricted-network-python-packages): In-page section heading. ## Related documentation - [Agentic AI](https://docs.datarobot.com/en/docs/agentic-ai/index.html.md): Linked from this page. - [Build](https://docs.datarobot.com/en/docs/agentic-ai/agentic-develop/index.html.md): Linked from this page. - [DataRobot codespace](https://docs.datarobot.com/en/docs/workbench/wb-notebook/codespaces/index.html.md): Linked from this page. - [DataRobot CLI getting started](https://docs.datarobot.com/en/docs/agentic-ai/cli/getting-started.html.md): Linked from this page. - [dr start](https://docs.datarobot.com/en/docs/agentic-ai/cli/commands/start.html.md): Linked from this page. - [CLI command reference](https://docs.datarobot.com/en/docs/agentic-ai/cli/commands/index.html.md): Linked from this page. - [Customize your agent](https://docs.datarobot.com/en/docs/agentic-ai/agentic-develop/agentic-development.html.md): Linked from this page. - [Add tools to your agent](https://docs.datarobot.com/en/docs/agentic-ai/agentic-develop/agentic-tools-integrate.html.md): Linked from this page. - [Configure LLM providers](https://docs.datarobot.com/en/docs/agentic-ai/agentic-develop/agentic-llm-providers.html.md): Linked from this page. - [Add Python requirements](https://docs.datarobot.com/en/docs/agentic-ai/agentic-develop/agentic-python-packages.html.md): Linked from this page. - [CLI task command](https://docs.datarobot.com/en/docs/agentic-ai/cli/commands/task.html.md): Linked from this page. - [CLI run command](https://docs.datarobot.com/en/docs/agentic-ai/cli/commands/run.html.md): Linked from this page. ## Documentation content The [Agentic Starter template repository](https://github.com/datarobot-community/datarobot-agent-application) provides a ready-to-use application template for building and deploying agentic workflows with multi-agent frameworks, a FastAPI backend server, a React frontend, and an MCP server. The template streamlines the process of setting up new agentic applications with minimal configuration requirements and supports local development and testing, as well as one-command deployments to production environments within DataRobot. This guide covers installing the prerequisite tools and configuring your environment, then creating, deploying, and testing an agentic application using DataRobot's pre-built templates. ## System requirements Ensure your system meets the minimum requirements for running the Agentic Starter template: - Operating system: macOS, Linux, or Windows - Python: Version 3.10 or higher - Memory: At least 4 GB of RAM > [!NOTE] Windows development > On Windows, complete the [Windows prerequisites](https://docs.datarobot.com/en/docs/agentic-ai/agentic-develop/agentic-get-started.html.md#windows-prerequisites) before you clone the repository or run `dr start`. The rest of the installation and quickstart flow matches macOS and Linux. > > If you prefer a Linux environment on Windows, you can also use a [DataRobot codespace](https://docs.datarobot.com/en/docs/workbench/wb-notebook/codespaces/index.html.md), [Windows Subsystem for Linux (WSL)](https://learn.microsoft.com/en-us/windows/wsl/install), a dev container, or a virtual machine. > [!NOTE] Restricted network environments > If you're working from an environment with no direct internet access (for example, an air-gapped environment), see [Restricted network setup](https://docs.datarobot.com/en/docs/agentic-ai/agentic-develop/agentic-get-started.html.md#restricted-network-setup) before you install, initialize, or deploy. ## Install prerequisite tools Before you begin, you'll need the following tools installed. If you already have these tools installed, ensure that they are at the required version (or newer) indicated in the table below. For example commands to install the tools, see the [Detailed installation commands](https://docs.datarobot.com/en/docs/agentic-ai/agentic-develop/agentic-get-started.html.md#detailed-installation-commands) section. > [!TIP] Install tools system-wide > Make sure to install the tools system-wide, rather than in a virtual environment, so they are available in your terminal sessions. | Tool | Version | Description | Installation guide | | --- | --- | --- | --- | | dr-cli | >= 0.2.77 | The DataRobot CLI. | DataRobot CLI getting started (install and configure); GitHub dr-cli (alternative) | | git | >= 2.30.0 | A version control system. | git installation guide | | uv | >= 0.10.0 | A Python package manager. | uv installation guide | | Pulumi | >= 3.163.0 | An Infrastructure as Code tool. | Pulumi installation guide | | Taskfile | >= 3.43.3 | A task runner. | Taskfile installation guide | | NodeJS | >= 24 | JavaScript runtime for frontend development. | NodeJS installation guide | | C++ build tools | N/A | A C++ compiler and build tools, required to compile some Python packages. | macOS: Xcode Command Line Tools (xcode-select --install); Linux: build-essential (sudo apt-get install build-essential); Windows: Visual Studio Build Tools with the Desktop development with C++ workload | ### Windows prerequisites Complete these steps on Windows before you clone the repository. Skipping them checks symlinks out as plain text files and leaves the working tree broken. 1. Enable symlink support in Git: ``` git config --global core.symlinks true ``` 1. Grant permission to create symlinks using one of the following options: 2. Developer Mode (recommended): On Windows 11, openSettings → System → Advanced → Developer Modeand turn Developer Mode on. SeeEnable your device for developmentfor details. 3. Administrator terminal: Launch PowerShell or Windows Terminal withRun as administratorand run every repo operation from that elevated session. At minimum, use an elevated session forgit clone,dr start,dr run deploy, and anygit checkoutorgit pullthat touches symlinked paths. This template uses Git symlinks at.claude/skills,fastapi_server/core,infra/infra/llm.py, andinfra/infra/oauth.py. 4. After Git is installed, ensure that the following directory is present in your system PATH:[path_of_git_installation]\usr\bin. For example, if Git is installed inC:\Program Files\Git, addC:\Program Files\Git\usr\binto your PATH using the following commands: ``` $dir = 'C:\Program Files\Git\usr\bin' # Change if Git is installed elsewhere. $p = [Environment]::GetEnvironmentVariable('PATH', 'User') [Environment]::SetEnvironmentVariable('PATH', "$p;$dir", 'User') ``` This location provides Linux helper commands required for the Agentic Starter to work correctly. Close and reopen the terminal (or IDE) after running the command so new processes pick up the change. ### Detailed installation commands The following sections provide example installation commands for macOS, Linux (Debian/Ubuntu/DataRobot codespace), and Windows (PowerShell). Click the tab below that corresponds to your operating system: **macOS:** macOS users can install the prerequisite tools using Homebrew. First, install Homebrew if you don't already have it. ``` /bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/HEAD/install.sh)" # If homebrew is not already installed ``` Then, install the prerequisite tools with it: ``` brew install datarobot-oss/taps/dr-cli uv pulumi/tap/pulumi go-task node git ``` You also need the Xcode Command Line Tools to compile some Python packages: ``` xcode-select --install ``` **Linux:** Linux users can install the prerequisite tools using the package manager for their distribution. ``` curl https://cli.datarobot.com/install | sh sudo apt-get update sudo apt-get install -y python3 python3-pip python3-venv sudo apt-get install -y build-essential sudo apt-get install -y git curl -LsSf https://astral.sh/uv/install.sh | sh curl -fsSL https://get.pulumi.com | sh sh -c "$(curl --location https://taskfile.dev/install.sh)" -- -d sudo apt-get install -y nodejs npm ``` **Windows (PowerShell):** Complete [Windows prerequisites](https://docs.datarobot.com/en/docs/agentic-ai/agentic-develop/agentic-get-started.html.md#windows-prerequisites) before you run `dr start`. Windows users can install the prerequisite tools with PowerShell: ``` irm https://cli.datarobot.com/winstall | iex powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex" winget install Git.Git winget install Pulumi.Pulumi winget install Task.Task winget install OpenJS.NodeJS winget install Microsoft.VisualStudio.2022.BuildTools --force --override "--wait --passive --add Microsoft.VisualStudio.Component.VC.Tools.x86.x64 --add Microsoft.VisualStudio.Component.Windows11SDK.22621" ``` > [!NOTE] After installing the tools > uv: Run > uv tool update-shell > once so your shell picks up the updated > PATH > before using > uv tool run > or invoking tools installed via > uv tool install > . > Pulumi: If you don't have a Pulumi account, use > pulumi login --local > for local login, or create a free account at > the Pulumi website > . ## Initialize your application > [!WARNING] Installation process > Before starting, complete all installation and setup steps above. Skipping this process can cause errors and prevent your agentic application from running correctly. Run the following command to start the local development environment: ``` dr start ``` This command starts the DataRobot CLI's interactive wizard ( [dr start](https://docs.datarobot.com/en/docs/agentic-ai/cli/commands/start.html.md) in the [CLI command reference](https://docs.datarobot.com/en/docs/agentic-ai/cli/commands/index.html.md)). It automatically clones the application repository and creates a `.env` file in the root directory populated with environment variables you specify. The wizard provides guidance and context for each step; expand the reference below for the complete list of steps. **Full wizard step reference** 1. Specify whether you wish to use the "low-code" agent template: 2. After a few moments, the wizard opens a web browser window to automatically configure your API endpoint and key. Click Proceed to continue. 3. Specify the port for the local web application and press Enter . The default is 8842 . 4. If desired, specify the default execution environment for your agent and press Enter . The default is [DataRobot] Python 3.11 GenAI Agents . 5. Provide a secret key to sign cookies for your session and press Enter . If you do not provide a value, a randomly generated one is used. 6. Enter the URI for a database to use for the application and press Enter . The default is sqlite+aiosqlite:///.data/database.sqlite . 7. Select your backend OAuth provider and press Enter . 8. Specify your authorization server by selecting it from the list and pressing Space . Press Enter to confirm. 9. Enter a passphrase (or leave blank if you don't want to use a passphrase) for your Pulumi stack and press Enter . 10. Specify the ID of a DataRobot Use Case (for example, 69331fad5e07469e7c4f5c6f ), if one is available, and press Enter . 11. Specify your LLM integration and press Enter . 12. Specify the port for the MCP server and press Enter . The default is 9000 . 13. Review the .env configuration summary displayed and press Enter to confirm. 14. Once the configuration finishes, choose a Pulumi stack to use for your application and press Enter . If you wish to create a new stack, press Enter and you are prompted to enter a name for it. The name cannot match any existing stack name. > [!NOTE] First-time initialization > When run for the first time, the `dr start` command prepares your development environment to develop and deploy your application. > This includes both environment and agent component configuration. > After this first initialization, future `dr start` operations only set up your local environment. > For subsequent updates to the configuration of your agent component, run the `dr component update` command. After `dr start` completes successfully, verify the following: - A .env file in your project root. - Your application directory created (typically named datarobot-agent-application or based on your application name). Now that your application is configured, proceed to the next section. ## Run your agent > [!WARNING] Running your agent > Do not proceed to this section until you have run `dr start`, detailed in the previous section. Navigate to the application directory created during `dr start`: ``` cd datarobot-agent-application # or the custom directory name you specified during the wizard, if different ``` Then, run the following command to start all components of the application: ``` dr run dev ``` > [!NOTE] Note > `task dev` runs the same development stack if your template exposes that task. This starts four processes, running in parallel: - Application frontend - Application backend - Agent - MCP server Once all services are running: 1. Open your web browser and navigate to http://localhost:5173 . 2. Confirm that the agent application interface appears. 3. Try sending a test message to verify everything is working. From here, start customizing your agent by adding your own logic and functionality. See the [Develop your agent](https://docs.datarobot.com/en/docs/agentic-ai/agentic-develop/agentic-get-started.html.md#develop-your-agent) section for more details. > [!NOTE] Starting individual services > Start individual services in separate terminal windows; for example, `task agent:dev` starts only the agent. ## Develop your agent Now that your agent has been built and tested, you are ready to customize it by adding your own logic and functionality. See the following documentation for more details: - Customize your agent - Add tools to your agent - Configure LLM providers - Add Python requirements - Manage prompts ## Deploy your agent > [!WARNING] Testing your agent > Ensure that you have tested your agent locally before deploying. Next, deploy your agent to DataRobot, which requires a Pulumi login. Run the following command to deploy your agent: ``` dr task run deploy ``` For more on the `task` and `run` commands, see the [CLI task command](https://docs.datarobot.com/en/docs/agentic-ai/cli/commands/task.html.md) and [CLI run command](https://docs.datarobot.com/en/docs/agentic-ai/cli/commands/run.html.md). > [!NOTE] Deployment process > The deployment process takes several minutes to complete. Once deployment is complete, the script displays the deployment details, as shown in the example below. The deployment details vary based on your configuration. ``` Outputs: AGENT_DEPLOYMENT_ID : "69331fad5e07469e7c4f5c6f" Agent Custom Model Chat Endpoint [apptest] [agent]: "https://datarobot.com/api/v2/genai/agents/fromCustomModel/69331f816e1bf9f1890d5d1d/chat/" Agent Deployment Chat Endpoint [apptest] [agent] : "https://datarobot.com/api/v2/deployments/69331fad5e07469e7c4f5c6f/chat/completions" Agent Execution Environment ID [apptest] [agent] : "680fe4949604e9eba46b1775" Agent Playground URL [apptest] [agent] : "https://datarobot.com/usecases/69331e4c3be0efe3b95a7be0/agentic-playgrounds/69331e4d1c036307186c9b16/comparison/chats" Agentic Starter [apptest] : "https://datarobot.com/custom_applications/6933204a9e21e9b59b5a7bee/" DATABASE_URI : "sqlite+aiosqlite:////tmp/agent_app/.data/agent_app.db" DATAROBOT_APPLICATION_ID : "6933204a9e21e9b59b5a7bee" DATAROBOT_OAUTH_PROVIDERS : (json) [] LLM_DEFAULT_MODEL : "azure/gpt-4o-2024-11-20" SESSION_SECRET_KEY : "secretkey123" USE_DATAROBOT_LLM_GATEWAY : "1" [apptest] [mcp_server] Custom Model Id : "69331eebb49131d3d5430ac7" [apptest] [mcp_server] Deployment Id : "69331f1f30548f83b668d9dc" [apptest] [mcp_server] MCP Server Base Endpoint : "https://datarobot.com/api/v2/deployments/69331f1f30548f83b668d9dc/directAccess/" [apptest] [mcp_server] MCP Server MCP Endpoint : "https://datarobot.com/api/v2/deployments/69331f1f30548f83b668d9dc/directAccess/mcp" ``` > [!NOTE] Note > The sample output above reflects an agent using the LLM gateway ( `USE_DATAROBOT_LLM_GATEWAY` is `"1"`). If you use the DataRobot Deployed LLM option instead, `USE_DATAROBOT_LLM_GATEWAY` is automatically set to `0`. ## Restricted network setup Complete this section only if you're installing, initializing, or deploying from an environment with no direct internet access (for example, an air-gapped environment); otherwise, skip it. Configure Pulumi to install the DataRobot plugin from an internal proxy instead of GitHub. Setting these environment variables redirects all Pulumi plugin downloads to your internal proxy and disables external update checks. Add the following variables to your `.env` file: ``` # .env PULUMI_SKIP_UPDATE_CHECK=1 PULUMI_DATAROBOT_DEFAULT_URL=http://internal-proxy-for-pulumi # OPTIONAL PULUMI_DATAROBOT_PLUGIN_VERSION=v0.10.27 ``` | Environment variable | Required | Description | | --- | --- | --- | | PULUMI_SKIP_UPDATE_CHECK | Yes | Enables air-gapped mode when set to 1, disabling external update checks and allowing use of a custom plugin server. | | PULUMI_DATAROBOT_DEFAULT_URL | Yes | The base URL of your internal proxy server hosting the DataRobot Pulumi plugin. This replaces the default GitHub releases source. | | PULUMI_DATAROBOT_PLUGIN_VERSION | No | The specific version of the DataRobot Pulumi plugin to install. If not specified, it defaults to the version bundled with the templates. | > [!NOTE] How it works > When `PULUMI_SKIP_UPDATE_CHECK=1` is set, deployment tasks execute `pulumi plugin install resource datarobot --server `. This ensures that plugin downloads are routed through your internal proxy instead of external sources. > [!NOTE] Internal proxy requirements > The internal proxy must host the DataRobot Pulumi plugin files in a structure compatible with Pulumi's plugin installation. It should mirror the directory and file structure of the [official GitHub releases](https://github.com/datarobot-community/pulumi-datarobot/releases). ### Python packages In restricted network environments, `uv sync` operations fail when attempting to reach the public PyPI. To resolve this, configure `uv` to use your internal PyPI proxy. To configure the proxy, edit the `agent/pyproject.toml` file in your agent project and uncomment the `[tool.uv.pip]` section, replacing the URL with your internal PyPI proxy. For example: ``` # agent/pyproject.toml [tool.uv.pip] extra-index-url = ["https://your-internal-pypi-proxy.example.com/simple/"] ``` > [!NOTE] Configuration impact > Once configured, this setting ensures that all Python package installations are routed through your proxy. This applies to: > > Local development ( > uv sync > ) > Docker image builds > Custom model deployments > Playground operations > Infrastructure deployments > [!TIP] Finding the configuration > The `[tool.uv.pip]` section is located at the end of the `pyproject.toml` file. If it is missing, add it manually.