Skip to content
SPECIFICTION
Get listed

Daytona

daytona.io

Free plan WebWindowsmacOSLinuxAPISelf-hosted
Visit daytona.io
Spec score 9.2 #1 of 27 in Cloud Development Environments

What it is

Daytona provides a secure, elastic runtime for executing AI-generated code and agent workflows. Its homepage states that sandbox creation takes under 90ms, and Daytona describes runtime isolation for code execution. Programmatic controls cover processes, file-system operations, Git integration, and built-in language-server support. SDK examples or interfaces are shown for Python, TypeScript, Ruby, Go, and Java. Listed uses include AI evaluations, code interpreter workloads, coding agents, and data analysis. The product's listed environments include API, Linux, macOS, self-hosted, web, and Windows; its CLI documentation supports macOS, Linux, and Windows. Documentation lists Claude, Cursor, and Windsurf as supported agents. Network options include IP and domain allow lists, outbound blocking, and chained proxies. Organization-scoped secrets are encrypted at rest and injected as placeholders into sandboxes, with plaintext substituted only for allowed HTTPS hosts. Daytona has free offerings and usage-based pricing; compute, memory, storage, and Windows rates are listed, while Enterprise pricing requires contacting sales.

Spec sheet

What it does
Daytona provides secure, elastic infrastructure for executing AI-generated code inside isolated sandboxes.Read 14 Oct 2026 · daytona.io
Compliance
Daytona's Trust Center lists GDPR, HIPAA, SOC 2, ISO/IEC 27001, SOC 2 Type 1, and SOC 2 Type 2 compliance materials.Read 1 Oct 2026 · trust.daytona.io
Support
The terms state that Daytona support may be provided through email, Slack, in-app chat, video support, and community forums.Read 1 Oct 2026 · daytona.io
Headquarters
New York, New York, United StatesRead 28 Sep 2026 · daytona.io
Founded
2023Read 28 Sep 2026 · daytona.io
Agent integration
The MCP server documentation lists Claude, Cursor, and Windsurf as supported AI agents.Read 1 Oct 2026 · daytona.io
AI use cases
Daytona lists AI evaluations, code interpreter workloads, coding agents, and data analysis as use cases.Read 1 Oct 2026 · daytona.io
CLI platforms
The Daytona CLI installation documentation supports macOS, Linux, and Windows.Read 1 Oct 2026 · daytona.io
Code execution
The platform runs commands and code with real-time output streaming and configurable execution controls.Read 14 Oct 2026 · daytona.io
Company founding
Daytona's own about page says the company was founded in 2023.Read 14 Oct 2026 · daytona.io
Company headquarters
Crunchbase lists Daytona's headquarters in New York, New York, United States.Read 14 Oct 2026 · crunchbase.com
Company legal name
Crunchbase lists the legal name as Daytona Platforms Inc.Read 14 Oct 2026 · crunchbase.com
Company size
LinkedIn lists Daytona as a privately held software-development company with 11–50 employees.Read 14 Oct 2026 · linkedin.com
Documentation depth
The official docs cover platform concepts, sandbox classes, agent tools, human tools, webhooks, security, observability, deployments, SDK references and CLI usage.Read 14 Oct 2026 · daytona.io
Documentation license
The public documentation repository states that its documentation website is covered by Apache License 2.0 while the product is distributed under commercial terms.Read 14 Oct 2026 · github.com
Execution APIs
Its programmatic control includes process execution, file-system operations, Git integration, and built-in LSP support.Read 1 Oct 2026 · daytona.io
Filesystem API
Daytona exposes programmatic filesystem CRUD operations with granular permissions.Read 14 Oct 2026 · daytona.io
Funding
Ry Walker Research reports a $24 million Series A in February 2026 led by FirstMark, with Datadog and Figma Ventures participating.Read 14 Oct 2026 · rywalker.com
Git integration
Native Git operations and credential handling are built into the sandbox tooling.Read 14 Oct 2026 · daytona.io
GPU capability
GPU sandboxes support NVIDIA and AMD accelerators, with up to eight GPUs for a sandbox.Read 14 Oct 2026 · daytona.io
Isolation
Daytona describes separated and isolated runtime protection for executing AI-generated code.Read 1 Oct 2026 · daytona.io
Limit: enterprise access
Softwr reports that SSO, audit logs and BYOC require contacting sales rather than being self-serve.Read 14 Oct 2026 · softwr.com
Limit: G2 differentiation
One G2 reviewer said Daytona did not provide enough differentiation from competing products.Read 14 Oct 2026 · g2.com
Limit: pricing predictability
An independent Softwr review says usage-only pricing without a flat monthly plan can make steady-workload costs harder to predict.Read 14 Oct 2026 · softwr.com
Limits model
Organizations are assigned verification-based tiers with compute pools, per-sandbox limits and API rate limits.Read 14 Oct 2026 · daytona.io
LSP support
Built-in language-server support provides completion and real-time code analysis.Read 14 Oct 2026 · daytona.io
Network controls
Sandbox network controls include IPv4 CIDR allow lists, domain allow lists, block-all outbound traffic, and chained outbound proxies.Read 1 Oct 2026 · daytona.io
Notable news
The October 12, 2026 changelog release v0.224.0 added per-call region selection for sandbox and snapshot creation and fixed Python and TypeScript PTY and log streaming behavior.Read 14 Oct 2026 · daytona.io
Praise: G2 reviewers
G2 reviewers mention nearly instant reproducible workspace setup and reduced infrastructure friction.Read 14 Oct 2026 · g2.com
Praise: Product Hunt reviewers
Product Hunt feedback repeatedly highlights fast startup, easy Python and TypeScript integration, reliable sandboxing and less infrastructure work.Read 14 Oct 2026 · producthunt.com
Product purpose
Daytona provides a secure, elastic runtime for AI-generated code execution and agent workflows.Read 1 Oct 2026 · daytona.io
Public API
Daytona publishes an API reference at app.daytona.io/api and documents bearer-key REST calls.Read 14 Oct 2026 · daytona.io
Rating on G2
4.3 out of 5 from 24 reviews.Read 14 Oct 2026 · g2.com
Rating on GetApp
0.0 out of 5 from 0 reviews.Read 14 Oct 2026 · getapp.com
Rating on Product Hunt
5.0 out of 5 from 17 reviews.Read 14 Oct 2026 · producthunt.com
Rating on Software Advice
No reviews are listed for Daytona.Read 14 Oct 2026 · softwareadvice.com
Sandbox isolation
Each sandbox has an isolated kernel, filesystem, network stack, vCPU, memory and disk allocation.Read 14 Oct 2026 · daytona.io
Sandbox speed
The homepage states that Daytona provides sub-90ms sandbox creation from code to execution.Read 1 Oct 2026 · daytona.io
SDK languages
The homepage shows SDK examples or interfaces for Python, TypeScript, Ruby, Go, and Java.Read 1 Oct 2026 · daytona.io
SDKs
The sandbox documentation provides SDK examples for Python, TypeScript, Ruby, Go and Java, plus CLI and REST API usage.Read 14 Oct 2026 · daytona.io
Secrets security
Daytona encrypts organization-scoped secrets at rest and injects opaque placeholders into sandboxes, substituting plaintext only for allowed HTTPS hosts.Read 1 Oct 2026 · daytona.io
Security architecture
The company describes encrypted sandbox isolation and audited access controls as security measures.Read 14 Oct 2026 · daytona.io
Security certifications
Daytona says its Trust Center provides documentation for SOC 2 Type I and HIPAA certifications.Read 14 Oct 2026 · daytona.io
Self-hosting
Bring-your-own-compute custom regions let organizations attach their own runner machines and control locality and infrastructure.Read 14 Oct 2026 · daytona.io
Snapshots
Environment snapshots can save, restore and resume agent workflows while preserving state.Read 14 Oct 2026 · daytona.io
Source-availability change
On June 11, 2026, Daytona announced that its production code would become closed source and that the old repository would no longer be maintained.Read 14 Oct 2026 · daytona.io
Startup speed
The documentation says sandboxes can start from code to execution in under 90 milliseconds.Read 14 Oct 2026 · daytona.io
Supported runtimes
Daytona offers Linux containers by default plus Linux VM, Windows VM, macOS and GPU sandbox classes.Read 14 Oct 2026 · daytona.io
VPN integrations
Daytona supports Tailscale, OpenVPN, and Netbird VPN connections, with VPN connectivity requiring Tier 3 or higher.Read 1 Oct 2026 · daytona.io

Plans and prices

Pay-as-you-go Price not published 5 GiB storage free before storage charges Read 22 Sep 2026 · daytona.io
Free compute credit Free included for new signups $200 compute credit Read 14 Oct 2026 · daytona.io
Start-ups Free Credits Up to $50k in credits for free Read 1 Oct 2026 · daytona.io
Storage Free per GiB per hour after first 5 free GiB; billing calculated per second disk storage · pay-as-you-go Read 14 Oct 2026 · daytona.io
Memory $0.02 a month per GiB per hour; billing calculated per second RAM · pay-as-you-go Read 14 Oct 2026 · daytona.io
Compute vCPU $0.05 a month per hour; billing calculated per second vCPU compute · pay-as-you-go Read 14 Oct 2026 · daytona.io
Windows compute $0.09 a month per vCPU per hour; billing calculated per second Windows sandbox surcharge Read 14 Oct 2026 · daytona.io
Enterprise Priced on request contact sales custom resources · custom limits Read 14 Oct 2026 · daytona.io
Pay as you go Price not published Usage-based; billed per second · vCPU $0.0504/h · Memory $0.0162/h · Storage $0.000108/h · Windows $0.0858/vCPU/h First 5 GiB storage free · $200 in free compute included · GPU rates vary by model and preemptible/on-demand Read 1 Oct 2026 · daytona.io

Every Daytona plan and price →

Strong points and limits

Strong points

  • Sandbox creation is stated at under 90ms.
  • Execution controls include processes, files, and Git.
  • SDK interfaces cover five listed languages.
  • Network controls include IP and domain allow lists.
  • A self-hosted option is available.

Limits

  • Usage-based rates apply to compute and storage.
  • VPN connectivity requires Tier 3 or higher.
  • Enterprise pricing requires contacting sales.

Who it suits

Daytona suits teams building AI agents or code-execution workflows that need isolated sandboxes and programmatic execution controls. Its self-hosted option and network controls may also fit deployments with specific environment or outbound-traffic requirements.

Daytona in depth

Read the full write-up

Overview

Daytona is a runtime for executing AI-generated code and agent workflows. It suits teams building code execution into AI products or developer tools, especially when they need sandbox controls and programmatic integration. Its broad execution interfaces and network safeguards are strong points; usage-based billing and tier-gated VPN connectivity need careful consideration.

Key features

Daytona says it can create sandboxes in under 90 milliseconds, a useful target for interactive agents and other workflows where waiting for an execution environment can slow the experience. It describes separated, isolated runtimes for generated code and names evaluations, code interpreters, coding agents and data analysis as use cases. Fast provisioning does not make execution free: compute, memory and some storage are usage-billed.

Execution APIs cover process execution, filesystem operations and Git integration, with built-in language-server protocol support. SDK examples span Python, TypeScript, Ruby, Go and Java. The CLI supports macOS, Linux and Windows, while the MCP server documentation names Claude, Cursor and Windsurf as supported agents. This breadth is useful for teams integrating Daytona into varied toolchains, although it matters most when those interfaces fit an existing workflow.

Network controls include IPv4 CIDR and domain allow lists, the option to block all outbound traffic, and chained outbound proxies. Organization-scoped secrets are encrypted at rest; sandboxes receive opaque placeholders, with plaintext substituted only for allowed HTTPS hosts. Together, these controls provide specific ways to limit sandbox access and secret exposure. VPN connections support Tailscale, OpenVPN and Netbird, but require Tier 3 or higher, which may rule them out for teams on lower tiers.

Daytona also supports Dockerfile workspace configuration, multiple VCS hosts, prebuilds, persistent storage, GPU workspaces and self-hosting. Its Trust Center lists GDPR, HIPAA, SOC 2 and ISO/IEC 27001 compliance materials. Support may be provided through email, Slack, in-app chat, video support or community forums.

Pricing

Daytona offers freemium access, but its usage-based plans make the actual cost depend on workload. The Pay-as-you-go plan gives 5 GiB of storage free before storage charges. Another Pay as you go plan includes $200 in free compute and the first 5 GiB of storage free, then bills per second at vCPU $0.0504/h, Memory $0.0162/h, Storage $0.000108/h and Windows $0.0858/vCPU/h. GPU rates vary by model and whether capacity is preemptible or on-demand. These rates make resource use and GPU choice important budgeting inputs.

The Start-ups plan is free, billed in credits, with up to $50k in credits for free; it is the clearest fit for eligible startups seeking credits rather than a fixed usage price. Enterprise has custom pricing and offers larger limits, SSO, audit logs and BYOC, making it the option for organizations that need those controls. The free storage allowance and compute credits help lower initial costs, but they do not turn ongoing usage into a flat-rate plan.

Platforms

Daytona supports API, Linux, macOS, self-hosted, web and Windows environments. Its CLI specifically supports macOS, Linux and Windows. This range suits teams working across local, hosted and self-managed setups, while the self-hosted option provides an alternative to relying solely on a hosted environment.

Who it's for

Daytona is a good fit for teams building AI agents or code-execution products that need isolated runtimes, execution APIs and explicit outbound network rules. Its SDK range, integrations and workspace capabilities suit developers connecting execution to an established toolchain. Teams that need VPN connectivity should account for the Tier 3 requirement, and those seeking predictable flat-rate costs may prefer a different pricing model.

Pros and cons

Pros: Sub-90ms sandbox creation targets responsive workflows, while isolated execution is designed for AI-generated code.

Pros: Process, filesystem and Git APIs, five SDK languages, and named MCP integrations give teams several integration paths.

Pros: CIDR and domain allow lists, outbound blocking, proxy chaining and constrained secret injection provide practical security controls.

Cons: Usage-based vCPU, memory, storage and Windows charges make costs depend on workload; GPU rates vary by model and billing mode.

Cons: VPN connectivity requires Tier 3 or higher, limiting access to a useful network integration on lower tiers.

Alternatives

ANY.RUN is a freemium option with a Community plan at free and support for Android, API, iOS, Linux, macOS, web and Windows; consider it when that platform range and community plan better suit your needs. Docker Desktop offers a free Personal plan and a Pro plan at $9 a month, so it may suit readers who want its Docker Desktop, Docker Engine and Kubernetes, Docker Hub, Docker Scout and Docker Debug bundle.

Context Agent Sandboxes has a free plan for one agent at a time and a Plus plan at $20 a month per person for three agents at a time; choose it when those stated concurrency limits match your use. Northflank offers a free Sandbox plan with two services, one database, two cron jobs and always-on compute, a better fit when those hosted resources are the priority.

Zscaler Private Access is a paid alternative for readers looking for private-access software. microsandbox has a free plan at free with 5 vCPU-hours, 20 memory GiB-hours, 20 disk GiB-hours and up to three sandboxes capped at 1 vCPU and 512 MiB memory each; consider it when those explicit sandbox limits meet the workload. Anthropic Sandbox Runtime is a free alternative for readers comparing sandbox runtimes.

Vercel has a free Hobby plan for personal, non-commercial use with 1M CDN requests per month, 100 GB data transfer per month and 1M function invocations per month; choose it when those web and API allowances fit better than Daytona's code-execution focus.

For broader comparisons, see Sandbox Software, Cloud Development Environments and Coding Playgrounds.

Verdict

Choose Daytona if you are building AI-code workflows and need isolated execution, broad APIs and detailed outbound network controls. Its speed claim and integration range are compelling, but usage-based costs require workload budgeting, and VPN access comes with a Tier 3 threshold. Teams that need flat-rate pricing or VPN access at a lower tier should look elsewhere.

Verdict

Daytona specifies execution controls, isolation, integrations, and network restrictions for AI-code workflows. Usage-based rates and a Tier 3 VPN requirement are important considerations.

Where Specifiction places it

Alternatives to DaytonaAll alternatives →