Daytona - Secure Infrastructure for Running AI-Generated Code

Secure and Elastic Infrastructure for Running Your AI-Generated Code.

Fast, Scalable, Stateful Infrastructure for AI Agents.

Lightning-Fast Infrastructure for AI Development

Sub 90ms sandbox creation from code to execution.

pip install daytona
from daytona import Daytona

daytona = Daytona()
sandbox = daytona.create()
response = sandbox.process.exec("echo 'Hello, World!'")
print(response.result)
sandbox.delete()

Programmatic Control. File, Git, LSP, and Execute API.

from daytona import Daytona, CreateSandboxParams

daytona = Daytona()
params = CreateSandboxParams(
    language="python",
)
sandbox = daytona.create(params)

# Run the code securely inside the sandbox
response = sandbox.process.code_run('print("Hello World!")')
if response.exit_code != 0:
    print(f"Error:{response.exit_code}{response.result}")
else:
    print(response.result)

# Execute an os command in the sandbox
response = sandbox.process.exec('echo "Hello World from exec!"', cwd="/home/daytona", timeout=10)
if response.exit_code != 0:
    print(f"Error:{response.exit_code}{response.result}")
else:
    print(response.result)
daytona.remove(sandbox)

AI-First Infrastructure. Optimized for LLMs, Agents, and Evals.

More Than a Sandbox. The Runtime AI Agents Actually Need.

Computer Use Sandbox

Secure virtual desktops (Linux, Windows, macOS) you can control with code. Deploy desktop automation with full programmatic access and isolated environments.

Human in the Loop. Full Access for Debugging, Oversight, or Intervention—Without Breaking Autonomy.

Built to Run Untrusted Code. Protected Secrets. Your Cloud. Certified Security.

Pricing

What Builders Say About Daytona.

FAQs