Daytona review

Q: How do I install Daytona?

Run pip install daytona. The install section above has the other options from the project's README.

Daytona is infrastructure for running AI-generated code in isolated sandboxes, controlled through SDKs, a REST API, and a CLI.

Updated Nov 1, 2026. Review written Oct 22, 2026 from the project's own sources; usage data refreshed every Monday.

TL;DR

Daytona is a runtime that runs AI-generated code and agent workflows inside isolated sandboxes. Each sandbox has its own kernel, filesystem, and network stack. It suits developers building AI agents that need to execute code safely. Note that the public GitHub repository is no longer maintained, because core development moved to a private codebase in June 2026.

71.4kGitHub stars
+13new stars, week of Oct 25
~980.1kdownloads a week, +17% vs 4-week avg
#9in Sandboxes and runtimes this week

Daytona at a glance

Category: Sandboxes and runtimes
Maintained by: Daytona (organization, @daytonaio on GitHub)
Repository: github.com/daytonaio/daytona
Website: daytona.io
npm package: @daytonaio/sdk 0.225.0
Latest release: @daytonaio/sdk 0.225.0 on npm, Oct 16, 2026
First published: Feb 6, 2024

What Daytona does

Daytona creates isolated sandboxes with a dedicated kernel, filesystem, network stack, and allocated vCPU, RAM, and disk.
Daytona runs code in Python, TypeScript, and JavaScript, and the README states sandboxes go from code to execution in under 90ms.
Daytona supports filesystem operations, process and code execution, Git operations, and language server protocol features inside sandboxes.
Daytona saves stateful environment snapshots so agents can keep working across sessions.
Daytona offers human access through a dashboard, web terminal, SSH, VNC, VPN connections, and previews.
Daytona includes an MCP server, computer use, a pseudo terminal, and log streaming as agent tools.
Daytona provides organizations, API keys, limits, audit logs, webhooks, and network limits for operational control.

How it works

Daytona is used programmatically through SDKs for Python, TypeScript, Ruby, Go, and Java, or through a REST API and a CLI. The platform has three parts. The interface plane provides clients, the control plane orchestrates sandbox operations, and the compute plane runs the sandboxes. Sandboxes are OCI/Docker compatible and are configured through base images, packages, and tooling.

How to install and start using Daytona

With pip

pip install daytona

With npm

npm install @daytona/sdk

With gem

gem install daytona

Requirements

A Daytona account at app.daytona.io
A Daytona API key

First steps

Create an account at app.daytona.io.
Generate an API key in the Daytona dashboard.
Create a sandbox with an SDK, the API, or the CLI command daytona create.
Run code in the sandbox, for example with sandbox.process.code_run in the Python SDK.

Who Daytona is for

Developers building AI agents that need to execute generated code in isolated environments.
Agent workflows that need persistent state across sessions through snapshots.
Teams that want sandbox control from Python, TypeScript, Ruby, Go, or Java code.

Limitations to know

The Daytona GitHub repository is archived and will receive no further updates, fixes, or releases.
Daytona's core development moved to a private codebase in June 2026. The public code is provided as is, without support.
The quick start requires a Daytona account and API key on app.daytona.io.
The README lists Python, TypeScript, and JavaScript as the languages for running code in sandboxes.

Is Daytona growing? Usage data

In the week of Oct 25–31, 2026, Daytona ranked #276 on the Devtoolwatch Board and #9 in Sandboxes and runtimes, with a momentum score of 35 out of 100. Its main package had about 980.1k downloads that week, +17% against its own 4-week average.

New GitHub stars per week for the last 12 weeks, from GitHub's stargazer history (today's stargazers by the week they starred).

Show the weekly numbers

New GitHub stars per week for Daytona
Week of	New stars
Aug 9, 2026	96
Aug 16, 2026	41
Aug 23, 2026	56
Aug 30, 2026	52
Sep 6, 2026	45
Sep 13, 2026	87
Sep 20, 2026	49
Sep 27, 2026	55
Oct 4, 2026	14
Oct 11, 2026	19
Oct 18, 2026	21
Oct 25, 2026	13

On Hacker News

Show HN: Daytona – Open-source dev env manager from a 15-year journey, 73 points and 24 comments (Mar 6, 2024)
Creating Your Own Remote Dev Environment with Visual Studio Code and Docker, 8 points and 3 comments (Feb 26, 2024)
Daytona is going closed source, 7 points and 3 comments (Jun 12, 2026)
Daytona Raises $2M in Pre-Seed, 7 points and 0 comments (Nov 6, 2023)
Daytona sandbox is closed-source, 5 points and 1 comments (Jun 30, 2026)

The Board ranks tools by four signals each week: new stars, new stars for the repo's size, added downloads and download growth beyond the market. How the ranking works.

Daytona alternatives

Other AI sandboxes and runtimes on the Board in the week of Oct 25–31, 2026, by momentum:

Sandboxes and runtimes ranked by momentum, the week of Oct 25–31, 2026
Rank	Tool	Stars	Downloads/wk
#1	OpenSandboxOpenSandbox is a sandbox runtime that gives AI agents isolated environments to run code, commands, files, browsers, and desktops on your…	16.3k	328.9k
#2	microsandboxmicrosandbox is a local-first microVM runtime and library for running untrusted workloads like AI agents, user code, and CI jobs in…	8.9k	26.8k
#3	E2BE2B is open-source infrastructure for running AI-generated code in secure, isolated cloud sandboxes, controlled through JavaScript and…	14.6k	5M
#4	Agent Sandboxagent-sandbox enables easy management of isolated, stateful, singleton workloads, ideal for use cases like AI agent runtimes and…	4.5k	–
#5	Trigger.devTrigger.dev is an open-source TypeScript platform for building and deploying durable AI agents, workflows, and long-running background…	16.7k	1.7M
#6	InngestInngest is a workflow orchestration platform for running durable step functions, background jobs, and AI workflows on serverless,…	6k	3.7M

All AI sandboxes and runtimes, ranked

Recent Daytona releases

v0.190.0, Jun 23, 2026
v0.189.0, Jun 19, 2026
v0.188.0, Jun 16, 2026
v0.187.0, Jun 11, 2026
v0.186.0, Jun 10, 2026

Daytona FAQ

Is Daytona free and open source?

Daytona's code is on GitHub (daytonaio/daytona), but the repository doesn't declare a standard open-source license. Check its license file before using it commercially. Its website links to a pricing page: https://daytona.io/pricing.

How do I install Daytona?

Run pip install daytona. The install section above has the other options from the project's README.

Is Daytona still maintained?

No. The daytonaio/daytona repository is archived, so it's read-only.

How popular is Daytona?

Daytona has 71.4k GitHub stars as of Nov 1, 2026. It gained 13 new stars in the week of Oct 25–31, 2026, against a 12-week average of 46 a week. Its main package had about 980.1k downloads that week, +17% against its own 4-week average. That made it #9 among AI sandboxes and runtimes on the Devtoolwatch Board.

What are the best alternatives to Daytona?

Other AI sandboxes and runtimes on the Devtoolwatch Board in the week of Oct 25–31, 2026, by momentum: OpenSandbox (#1), microsandbox (#2), E2B (#3), Agent Sandbox (#4), Trigger.dev (#5). The alternatives table above has their numbers.

Is Daytona still open source?

Daytona's public repository remains free to use, fork, and build on under its license, as is. As of June 2026, core development moved to a private codebase, and the repository gets no further updates.

What is a Daytona sandbox?

A Daytona sandbox is an isolated, composable computer. Each one has a dedicated kernel, filesystem, network stack, and allocated vCPU, RAM, and disk. Sandboxes are the core component of the platform.

Which languages do Daytona SDKs support?

Daytona provides SDKs for Python, TypeScript, Ruby, Go, and Java. A REST API and a CLI are also available.

Does Daytona have an MCP server?

Yes. The Daytona README lists an MCP server among its agent tools.

How do I run code in a Daytona sandbox?

Create a sandbox with an SDK, then call the process API. In Python, sandbox.process.code_run runs code and returns a response with the result.

Sources

Daytona README badge

Maintainers can show the tool's weekly Board rank in their README:

[![Devtoolwatch](https://index.devtoolwatch.com/badge/daytona.svg)](https://index.devtoolwatch.com/tools/daytona/)

How this page is made: Devtoolwatch writes each review from the project's README, releases, package metadata and website, with an AI model, then checks every claim against the source it cites and drops what the sources don't support. The numbers come from Devtoolwatch's daily GitHub snapshots, GitHub's stargazer history, and the npm and PyPI download APIs. Spotted an error? Email [email protected].