Installation¶

The DataRobot Agentic Workflow Templates repository provides ready-to-use templates for building and deploying AI agents with multi-agent frameworks. These templates streamline the process of setting up your own agents with minimal configuration requirements and support both local development and testing, as well as deployment to production environments within DataRobot.

Before running task start (quickstart.py), you can perform the following installation and setup steps.

System requirements¶

Ensure your system meets the minimum requirements for running DataRobot Agent Templates.

• Operating System: macOS or Linux (Windows not supported)
• Python: Version 3.10 or higher

Required tools¶

Before running any agentic workflow commands, you must have the following tools installed system-wide (not in a virtual environment) so they are always available in your terminal session.

Installation instructions¶

Follow the OS-specific installation commands to install all required tools.

macOS¶

Install using Homebrew package manager.

brew install git uv pulumi go-task/tap/go-task
xcode-select --install

Linux¶

Install using package manager and official installation scripts.

sudo apt-get update && sudo apt-get install git build-essential
curl -LsSf https://astral.sh/uv/install.sh | sh
curl -fsSL https://get.pulumi.com/ | sh
curl -sL https://taskfile.dev/install.sh | sh

sudo dnf install git
sudo dnf groupinstall "Development Tools"
curl -LsSf https://astral.sh/uv/install.sh | sh
curl -fsSL https://get.pulumi.com/ | sh
curl -sL https://taskfile.dev/install.sh | sh

sudo yum install git
sudo yum groupinstall "Development Tools"
curl -LsSf https://astral.sh/uv/install.sh | sh
curl -fsSL https://get.pulumi.com/ | sh
curl -sL https://taskfile.dev/install.sh | sh

Configure an environment¶

Configure your development environment with the repository and credentials.

Clone the repository¶

The first step when developing an agentic workflow locally is to clone the DataRobot agentic templates repository.

git clone https://github.com/datarobot-community/datarobot-agent-templates.git
cd datarobot-agent-templates

git clone -b release/11.3 https://github.com/datarobot-community/datarobot-agent-templates.git
cd datarobot-agent-templates

Configure environment variables¶

Set up your DataRobot API credentials in a local environment file. Create a .env file in the root directory:

nano .env  # or vim .env, code .env, etc.

Alternatively, copy and rename the sample environment file (.env.template) and provide the necessary environment variables in the file.

cp .env.template .env  
# Previously, .env.template was .env.sample

In the .env file, add the required environment variables:

1
2
3
4
5

# Refer to https://docs.datarobot.com/en/docs/api/api-quickstart/index.html#create-a-datarobot-api-key
# and https://docs.datarobot.com/en/docs/api/api-quickstart/index.html#retrieve-the-api-endpoint
# Can be deleted in a DataRobot codespace
DATAROBOT_API_TOKEN=<DATAROBOT_API_TOKEN>
DATAROBOT_ENDPOINT=<DATAROBOT_ENDPOINT>

Restricted network setup¶

In environments without direct internet access (i.e., air-gapped environments), 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:

PULUMI_SKIP_UPDATE_CHECK=1
PULUMI_DATAROBOT_DEFAULT_URL=http://internal-proxy-for-pulumi
# OPTIONAL
PULUMI_DATAROBOT_PLUGIN_VERSION=v0.10.27

Python packages¶

In restricted network environments, uv sync operations will 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:

[tool.uv.pip]
extra-index-url = ["https://your-internal-pypi-proxy.example.com/simple/"]