Getting Started

The Daytona SDK provides official Python and TypeScript interfaces for interacting with Daytona, enabling you to programmatically manage development environments and execute code.

View the Daytona SDK repository on GitHub.

Follow the step by step guide to create and run your first Daytona Sandbox for an AI Agent.

Install Daytona

Install Daytona by following the installation instructions. If you have Beta access to the Daytona platform, create an account and log in.

Set Up Your Environment Variables

To authenticate with Daytona, you need an API key. You can obtain an API key from the Daytona platform or generate one using the Daytona CLI.

daytona api-key generate

Install the Daytona SDK

Daytona provides official Python and TypeScript SDKs for interacting with the Daytona platform. Install the SDK using your preferred method.

pip install daytona-sdk

# Using npm
npm install @daytonaio/sdk

# Using yarn

yarn add @daytonaio/sdk

# Using pnpm

pnpm add @daytonaio/sdk

Write Code to Create a Sandbox

Create and run your code within Daytona Sandboxes using the SDK. Daytona provides a simple and intuitive interface for interacting with Daytona.

Use the Daytona SDK Python examples or TypeScript/JavaScript examples to create a Sandbox and run your code.

Execute Commands

Run the following code to create a Daytona Sandbox and execute commands:

from daytona_sdk import Daytona, CreateWorkspaceParams

# Initialize the Daytona client
daytona = Daytona()

# Create the Sandbox instance
params = CreateWorkspaceParams(language="python")
workspace = daytona.create(params)

# Run the code securely inside the Sandbox
response = workspace.process.code_run('print("Sum of 3 and 4 is " + str(3 + 4))')
if response.exit_code != 0:
    print(f"Error running code: {response.exit_code} {response.result}")
else:
    print(response.result)

# Clean up the Sandbox
daytona.remove(workspace)

import { Daytona } from '@daytonaio/sdk'

async function main() {
  // Initialize the Daytona client
  const daytona = new Daytona()

  try {
    // Create the workspace instance
    const workspace = await daytona.create({
      language: 'python',
    })
    // Run the code securely inside the workspace
    const response = await workspace.process.codeRun(
      'print("Sum of 3 and 4 is " + str(3 + 4))',
    )
    if (response.exitCode !== 0) {
      console.error('Error running code:', response.exitCode, response.result)
    } else {
      console.log(response.result)
    }
  } catch (error) {
    console.error('Workspace flow error:', error)
  } finally {
    // Clean up the workspace
    await daytona.remove(workspace)
  }
}

main()

Start your Sandbox

Daytona provides two methods for starting your Sandbox:

• Using Python
• Using TypeScript/JavaScript

Choose the appropriate method based on your preferred language.

python main.py

npx tsx ./index.ts