Open-source project
daytonaio/daytona avatar
daytonaio/daytona

Daytona: A Sandbox Runtime for AI Agents, Now Frozen in Public

GitHub describes it as Daytona is a Secure and Elastic Infrastructure for Running AI-Generated Code. This article stays within the project description and details documented in the GitHub repository README.

71,311 stars5,652 forksUnknownLicense varies

At a glance

What is it?
Daytona provides isolated, OCI-compatible sandboxes for running AI-generated code, but the core development has moved to a private codebase. This review covers what the open-source project offers, how it works, and what its unmaintained status means for adopters.
Who is it for?
Treat Daytona as a frozen reference rather than something to adopt: the repository is archived, receives no further updates, and its default branch contains only a README and assets, so any use depends on what the v0.190.0 tag holds. Do not adopt it if you require ongoing support, security patches, or new features.
Can I use it commercially?
Not without permission. GitHub finds no licence file in the repository, and without a licence all rights are reserved by default: you may read the code but not reuse it. Check the README, or ask the authors, before using it.
Is it still maintained?
No. The owners have archived the repository on GitHub, so it is read-only and no longer receives changes.
What is it written in?
GitHub does not report a main language for this repository.

Answers come from the project's GitHub data, last synced on November 15, 2026, and from our analysis. They are not legal advice.

From daily snapshots

Star history

  • daytonaio/daytona71,311 ★ · -717
Star history
Repository2026-08-132026-11-15
daytonaio/daytona72k71.3k

-717 Stars in the last 94 days, measured from the daily GitHub snapshot. Compare with other projects

Editorial analysis

The Problem: Running AI-Generated Code Safely

AI agents generate code that must run somewhere, but running it on a developer's laptop or a production server is risky. The code can be malicious, buggy, or simply unpredictable. Daytona addresses this by providing sandboxes: full, composable computers with complete isolation, a dedicated kernel, filesystem, network stack, and allocated vCPU, RAM, and disk. This is for teams building AI agent architectures that need to execute untrusted or unverified code without compromising the host system. The project targets developers and agents who need programmatic control over these environments, not just a simple container runner.

How Daytona Works: Sandboxes and Snapshots

The core mechanism is the sandbox, which spins up in under 90ms from code to execution, according to the README. Each sandbox is a full computer, not just a process, with its own kernel and network stack. This isolation is key for security. Built on OCI/Docker compatibility, sandboxes support massive parallelization and unlimited persistence. State can be saved via snapshots, which enable persistent agent operations across sessions. Agents interact with sandboxes through SDKs, an API, and a CLI. Operations include lifecycle management, filesystem operations, process and code execution, and runtime configuration through base images and packages. The system also offers human tools like a dashboard, web terminal, SSH, and VNC access, plus system tools like webhooks and network limits.

Getting Started: Commands and Configuration

The README links to the documentation for the SDKs, API and CLI, so installation commands and syntax live in the docs at daytona.io/docs rather than in the README. It lists a declarative builder among the sandbox features and describes runtime configuration through base images, packages, and tooling. The default branch contains only README.md and an assets folder, so there is no source to build from the branch itself.

Limitations: The Unmaintained Reality

The most significant limitation is that this repository is no longer maintained. As of June 2026, core development has moved to a private codebase, and this public repo receives no further updates, fixes, or releases. That means no security patches for vulnerabilities discovered after that date. This is the wrong tool if you need a supported, evolving platform. For a production deployment, the lack of upstream support is a serious risk, especially for security-sensitive workloads.

Alternatives: Comparing with Firecracker and gVisor

A real alternative is Firecracker, which provides microVMs for serverless workloads, offering stronger isolation than Docker containers because each microVM has its own kernel. gVisor is another alternative, a user-space kernel that intercepts system calls, providing isolation without full VM overhead. Daytona's README describes each sandbox as having a dedicated kernel. If you need strong isolation, microVMs or gVisor are alternatives worth evaluating. Daytona's advantage is the integrated agent tooling, but that comes with the maintenance risk.

Maintenance and License Considerations

The repository is public and free to use, fork, and build on under the LICENSE file, but the README does not specify the exact license type. The README states it is 'as is and without support or warranty.' The README says it is free to fork and build on, but the default branch holds only a README and assets, and you would inherit all bugs and security issues. The project has a history of releases, with v0.190.0 being the last, but there will be no more. For organizations, this means the upgrade path is dead. You must plan to either fork and maintain internally, or migrate to an alternative. The license allows forking, but the lack of updates means you are responsible for any compliance or security patches. Always check the LICENSE file in the repo for exact terms before using it commercially.

Editorial conclusion

Treat Daytona as a frozen reference rather than something to adopt: the repository is archived, receives no further updates, and its default branch contains only a README and assets, so any use depends on what the v0.190.0 tag holds. Do not adopt it if you require ongoing support, security patches, or new features. Before committing, verify the license terms, audit the code for your own security, and confirm that the documented APIs and SDKs match your workflow, since no upstream updates will address any gaps.

Frequently asked questions

Is Daytona still open source?

Not in the sense an adopter would want. The repository states that as of June 2026 Daytona's core development has moved to a private codebase, that the repository will receive no further updates, fixes or releases, and that it remains public and free to use, fork and build on without support or warranty. The file listing is only README.md and an assets folder, so the default branch contains no source to build.

What was Daytona used for?

It was an infrastructure runtime for AI-generated code execution and agent workflows. Its core component was sandboxes, described as full composable computers with complete isolation, each with a dedicated kernel, filesystem, network stack and allocated vCPU, RAM and disk, running Python, TypeScript and JavaScript. Agents and developers drove them through SDKs, an API and a CLI, and stateful snapshots let state persist across sessions.

What is the last version of Daytona released publicly?

v0.190.0, published on 2026-06-23, preceded by v0.189.0 on 2026-06-19 and v0.188.0 on 2026-06-16. Nothing has been released since. The README's licence link points at the LICENSE file on the v0.190.0 tag rather than on the default branch, and the repository metadata resolves no licence name, so that tag is also where the terms are readable.

Official sources

  1. Official documentation
  2. Official README
  3. Project repository
  4. Release notes
Add this badge to your README

If you maintain this project, the badge below links readers to this analysis and shows its maintenance status from the daily GitHub snapshot. Paste the markdown into your README; add ?metric=license or ?metric=stars to the image URL for a different field.

Add this badge to your README

markdown
[![Hysen Labs](https://hysenlabs.com/badge/daytonaio-daytona.svg)](https://hysenlabs.com/projects/daytonaio-daytona)

Star history chart for your README

markdown
[![Star history](https://hysenlabs.com/chart/daytonaio-daytona.svg)](https://hysenlabs.com/projects/daytonaio-daytona)

Was this useful?