Skip to main content
toolsSource-backedReview first Safety Privacy

Daytona

Open-source infrastructure for securely running AI-generated code in isolated sandboxes that start in milliseconds, with SDKs for Python, TypeScript, and other languages, persistent snapshots, and an optional managed cloud.

by Daytona·added 2026-06-05·
CLI
HarnessCLI
Review first review before installing

Open the source and read safety notes before installing.

Safety notes

  • Daytona is purpose-built to execute arbitrary, AI-generated code; only run untrusted code inside its isolated sandboxes, never on the host.
  • Each sandbox has its own kernel, filesystem, and network stack, but sandboxes can make outbound network requests unless network limits are configured.
  • Sandboxes support computer use, Git operations, and command execution; scope what an agent can do and review declarative builder configurations before use.
  • Self-hosting runs runner compute nodes and Docker services that need elevated host privileges; isolate the deployment from production systems.
  • Persistent snapshots retain sandbox filesystem state across sessions, which can preserve secrets or sensitive files written during execution.

Privacy notes

  • Using the managed cloud sends your code, files, and execution data to Daytona-operated infrastructure; review their terms before processing sensitive data.
  • The platform emits OpenTelemetry metrics, log streaming, and audit logs that can capture command output and activity.
  • API keys grant access to your sandboxes and organization; store them as secrets and never commit them to source control.
  • Self-hosting keeps execution data on your own infrastructure but you become responsible for log retention, access control, and isolation.

Prerequisites

  • A Daytona Cloud account and API key for the managed service, or self-hosted infrastructure for the open-source platform.
  • Python 3.8+ for the `daytona` SDK or Node.js 18+ for the `@daytona/sdk` TypeScript SDK.
  • Docker and Docker Compose to run supporting services (PostgreSQL, Redis) when self-hosting.
  • Nix with flakes enabled or a devcontainer-compatible editor for local development of the platform itself.

Schema details

Install type
copy
Troubleshooting
No
Source repository stats
Scope
Source repo
Tool listing metadata
Pricing
open-source
Disclosure
editorial
Application category
DeveloperApplication
Operating system
macOS, Windows, Linux
Full copyable content
## Overview

Daytona is open-source infrastructure for securely executing AI-generated code.
It provides sandboxes described as full composable computers with complete
isolation — a dedicated kernel, filesystem, network stack, and allocated vCPU,
RAM, and disk — that spin up in well under a second.

It is aimed at agent builders who need a safe place to run untrusted or
model-generated code at scale. You interact with sandboxes through SDKs, a REST
API, and a CLI, and with humans through a dashboard, web terminal, SSH, and VNC.
Daytona is released under AGPL-3.0; a managed cloud with usage-based pricing is
also available for teams that do not want to self-host.

## Features

- Isolated sandboxes with millisecond start times and per-sandbox kernel,
  filesystem, and network stack.
- Persistent snapshots for stateful agent operations across sessions.
- SDKs for Python (`pip install daytona`) and TypeScript
  (`npm install @daytona/sdk`), plus Ruby and Go.
- REST API and CLI for programmatic and scripted control.
- Built-in Git operations, LSP support, computer use, and MCP server
  integration.
- Organization governance: API keys, audit logs, and billing controls.

## Use Cases

- Give a coding agent a safe sandbox to run and test generated code.
- Execute untrusted user-submitted code without exposing host systems.
- Provide reproducible, snapshot-backed environments for long-running agents.
- Self-host execution infrastructure to keep code and data on your own systems.

## Disclosure

Editorial listing. No paid placement or affiliate relationship. Daytona's core
platform is open source (AGPL-3.0); the managed cloud is a separate paid,
usage-based service.

About this resource

Overview

Daytona is open-source infrastructure for securely executing AI-generated code. It provides sandboxes described as full composable computers with complete isolation — a dedicated kernel, filesystem, network stack, and allocated vCPU, RAM, and disk — that spin up in well under a second.

It is aimed at agent builders who need a safe place to run untrusted or model-generated code at scale. You interact with sandboxes through SDKs, a REST API, and a CLI, and with humans through a dashboard, web terminal, SSH, and VNC. Daytona is released under AGPL-3.0; a managed cloud with usage-based pricing is also available for teams that do not want to self-host.

Features

  • Isolated sandboxes with millisecond start times and per-sandbox kernel, filesystem, and network stack.
  • Persistent snapshots for stateful agent operations across sessions.
  • SDKs for Python (pip install daytona) and TypeScript (npm install @daytona/sdk), plus Ruby and Go.
  • REST API and CLI for programmatic and scripted control.
  • Built-in Git operations, LSP support, computer use, and MCP server integration.
  • Organization governance: API keys, audit logs, and billing controls.

Use Cases

  • Give a coding agent a safe sandbox to run and test generated code.
  • Execute untrusted user-submitted code without exposing host systems.
  • Provide reproducible, snapshot-backed environments for long-running agents.
  • Self-host execution infrastructure to keep code and data on your own systems.

Disclosure

Editorial listing. No paid placement or affiliate relationship. Daytona's core platform is open source (AGPL-3.0); the managed cloud is a separate paid, usage-based service.

#sandbox#code-execution#ai-agents#infrastructure#open-source#developer-tools

Source citations

Signals

Loading live community signals…

More like this, weekly

A short, calm digest of reviewed Claude resources. Unsubscribe any time.