ToolsCompaniesAbout

Daytona

by Daytona@daytonaioNew York, NYNo ratings yet

Secure, elastic sandboxes for running AI-generated code

Visit daytona.io
Tool type
Sandbox infrastructure for AI-generated code
Made for
Developers and teams building AI agents
Runs on
Daytona cloud, customer cloud (BYOC), Linux, Windows, and macOS sandboxes
Sandboxes are controlled programmatically; Daytona provides the control plane and sandboxes can run on customer-managed compute in the customer's cloud.
Last checked
29 Oct 2026
6 product sources

What it does

Daytona takes code and commands from developers or AI agents, usually sent through its Python, TypeScript, Ruby, Go, or Java SDKs, its REST API, or its CLI, and runs them inside isolated sandboxes. Each sandbox is described as a full composable computer with its own kernel, filesystem, network stack, and allocated vCPU, RAM, and disk. Output comes back as real-time streams and results, and sandboxes can be saved as snapshots and resumed later.

People typically use Daytona to run untrusted or generated code for coding agents, code interpreters, evaluations, data analysis, and reinforcement learning workflows. Distinct features include Linux, Windows, and macOS computer-use sandboxes that can be controlled by code, SSH and browser-based access for human oversight, Docker-compatible image support, and secrets that are substituted at network egress so plaintext credentials stay out of the sandbox.

Daytona suits developers and teams building AI agents or evaluation pipelines who need programmatic sandbox control. Access requires creating an account and an API key at app.daytona.io. Compute is billed per second on a pay-as-you-go basis, with free compute credit on signup; the pricing page also lists a Startup Program and an Enterprise tier with SSO, audit logs, and BYOC. Trial length is not stated, so confirm current credit terms when signing up.

What it can do

  • Create isolated sandboxes from code and run code or OS commands with real-time output streaming
  • Persist sandboxes with snapshots and resume agent workflows across runs
  • Provide Linux, Windows, and macOS computer-use sandboxes controllable by code
  • Offer file system operations, Git integration, and built-in LSP support through the SDK
  • Give humans SSH, VS Code browser, and web terminal access for oversight
  • Substitute secrets at network egress so plaintext credentials stay out of sandboxes

Works with

  • Docker and Dockerfile / Docker Compose image support
  • VS Code (browser access to sandboxes)

Before you choose

  • Pricing is usage-based per second for compute; check the pricing page rate table for current vCPU, memory, storage, and GPU rates before estimating costs.
  • Sandboxes run in selected regions (India, EU Central Frankfurt, EU West London, US East, US West); confirm your region supports your data requirements.
  • Customer-Managed Compute and enterprise features such as SSO and audit logs are described for the Enterprise tier, not the default plan.

Listed under

Get started

Sign up at app.daytona.io, create an API key, set DAYTONA_API_KEY, then install an SDK or the CLI.

  1. Create an account at app.daytona.io and generate an API key at app.daytona.io/dashboard/keys.
  2. Save the key as the DAYTONA_API_KEY environment variable or in a .env file.
  3. Install the SDK for your language (for example, pip install daytona for Python) and create a sandbox to run a test command.
Create account and API key

Plans and prices

Prices in USD

Pricing page describes a free trial with no credit card required and $200 in free compute included, which is signup credit rather than a permanent free tier. Compute is billed per second on usage. Startup Program offers up to $50k in credits. Enterprise is contact-sales.

Usage-based computeUsage-basedNamed meter vCPU; see https://www.daytona.io/pricing rate table.Named meter memory; see https://www.daytona.io/pricing rate table.Preemptible and on-demand GPU rates listed separately on the pricing page; see rate table.
  • Per-second billing
  • Pay-as-you-go

Source: daytona.io/pricing, checked 29 Oct 2026. Prices can change; check before you buy.

Sources for this overview

Product pages, documentation, and pricing checked 29 Oct 2026. Each source supports part of the overview; availability and prices can change.

Ratings and reviews

No ratings for Daytona yet.

Be the first to rate it

What’s changed

Free account

See what’s changed at Daytona

Launches, price moves and pivots, each with a date and a source. Free with an account.

Signals

Free account

See Daytona’s signals

Launch traction, hiring and release activity, tracked over time. Free with an account.

Data and security

Free account

See how Daytona handles your data

Training on your files, compliance, hosting and the models behind it. Free with an account.

Compare with similar tools

Free account

Compare Daytona side by side

Prices, platforms and features against similar tools, with sources. Free with an account.

Where this comes from

How we research
Company website
daytona.io: product, pricing and policy pages
YC directory mirror
Batch and company name
Social accounts
Accounts the company links, and its posts on X
Human review
Checked by a person
knowledge_base
manual_review

Last checked 29 Oct 2026. Every field keeps its source and date; unknown means we couldn’t confirm it.