Daytona

What is Daytona about?

Daytona offers a cloud‑native platform for executing AI‑generated code in fully isolated runtimes. Sandboxes are spun up in milliseconds, can live indefinitely, and are completely detached from the host environment, eliminating risk to production infrastructure.

How to use Daytona?

1. Sign up at https://app.daytona.io and generate an API key.
2. Install the SDK for your language:
   • Python: pip install daytona
   • TypeScript/JavaScript: npm install @daytonaio/sdk
3. Initialise the client with the API key, create a sandbox (specify language), run code via the process.codeRun method, and delete the sandbox when finished.

Key Features

• Lightning‑fast sandbox creation – sub‑90 ms from request to execution.
• Zero‑risk isolation – each sandbox runs in a separate runtime with no impact on host resources.
• Unlimited persistence – sandboxes can be kept alive indefinitely.
• OCI/Docker image support – any container image can be used as the execution environment.
• Programmatic control – full API for file handling, Git integration, LSP, and code execution.
• Scalable parallelism – upcoming ability to fork filesystem and memory state for massive concurrent AI workflows.

Use Cases

• AI workflow orchestration – run generated scripts safely as part of larger pipelines.
• Secure code evaluation – test untrusted AI‑generated snippets without exposing core systems.
• Dynamic plugin execution – let AI agents create and execute plugins on‑the‑fly.
• Educational sandboxes – provide students with instant, isolated coding environments.
• Rapid prototyping – spin up disposable environments for debugging AI‑generated code.

FAQ

• Do I need to host Daytona myself? No, Daytona is offered as a managed service; you interact via the public API using your API key.
• Which languages are supported? Any language for which you can provide a compatible OCI/Docker image; the SDK includes built‑in support for popular runtimes like Python.
• How is data persisted? Sandboxes can be kept alive indefinitely, and all files remain accessible until you explicitly delete the sandbox.
• Is there a limit on concurrent sandboxes? Limits are defined by your subscription tier; the platform is designed for massive parallelism.
• Can I run GPU‑accelerated workloads? Yes, by using Docker images that include GPU drivers and requesting appropriate resources from the platform.

 

---

Installation

Python SDK

pip install daytona

TypeScript SDK

npm install @daytonaio/sdk

---

Features

• Lightning-Fast Infrastructure: Sub-90ms Sandbox creation from code to execution.
• Separated & Isolated Runtime: Execute AI-generated code with zero risk to your infrastructure.
• Massive Parallelization for Concurrent AI Workflows: Fork Sandbox filesystem and memory state (Coming soon!)
• Programmatic Control: File, Git, LSP, and Execute API
• Unlimited Persistence: Your Sandboxes can live forever
• OCI/Docker Compatibility: Use any OCI/Docker image to create a Sandbox

---

Quick Start

1. Create an account at https://app.daytona.io
2. Generate a new API key
3. Follow the Getting Started docs to start using the Daytona SDK

Creating your first Sandbox

Python SDK

from daytona import Daytona, DaytonaConfig, CreateSandboxParams

# Initialize the Daytona client
daytona = Daytona(DaytonaConfig(api_key="YOUR_API_KEY"))

# Create the Sandbox instance
sandbox = daytona.create(CreateSandboxParams(language="python"))

# Run code securely inside the Sandbox
response = sandbox.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(sandbox)

Typescript SDK

import { Daytona } from '@daytonaio/sdk'

async function main() {
  // Initialize the Daytona client
  const daytona = new Daytona({
    apiKey: 'YOUR_API_KEY',
  })

  let sandbox
  try {
    // Create the Sandbox instance
    sandbox = await daytona.create({
      language: 'python',
    })
    // Run code securely inside the Sandbox
    const response = await sandbox.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('Sandbox flow error:', error)
  } finally {
    if (sandbox) await daytona.remove(sandbox)
  }
}

main().catch(console.error)

---

Contributing

Daytona is Open Source under the GNU AFFERO GENERAL PUBLIC LICENSE, and is the copyright of its contributors. If you would like to contribute to the software, read the Developer Certificate of Origin Version 1.1 (https://developercertificate.org/). Afterwards, navigate to the contributing guide to get started.