Daytona
Daytona is secure, elastic sandbox infrastructure for running AI-generated code and agent workflows (isolated sandboxes with snapshots, volumes, computer use, MCP server). Pivoted from an open-source cloud development environment; as of June 2026 core development moved to a private codebase and the daytonaio/daytona repo was archived (2026-10-03). SDKs, API clients and CLI/MCP tools are published in the open daytona/clients repo. Founded by the ex-Codeanywhere team (Ivan Burazin).
Active · Verified 2026-10-29 · fresh as of 2026-10-29 · 33 cited facts, 1 with a third-party source · 2 recorded changes · Suggest a correction
At a glance
- Tier
- T2
- Created
- 2024 (founded; Codeanywhere predecessor 2009) vendor fix
- Latest release
- v0.226.1 (2026-10-23) registry fix
- License
- Apache-2.0 (SDKs in daytona/clients; CLI under AGPL-3.0); core platform closed-source since June 2026 (archived daytonaio/daytona repo remains AGPL-3.0 at v0.190.0) repo fix
- GitHub
- daytona/clients — ~15 stars (SDKs, API clients, CLI); the former daytonaio/daytona monorepo (~71k stars, last commit 2026-07) stopped development when core moved to a private codebase in 2026-06 repo fix
- Pricing
- Pay-as-you-go per-second billing (vCPU $0.0504/h, memory $0.0162/GiB-h, storage $0.000108/GiB-h, first 5 GiB free); $200 free compute; startup credits up to $50k; preemptible GPUs from $0.57/h; Enterprise custom (SSO, audit logs, BYOC) vendor fix
- Freshness
- 2026-10-29 fix
- Layer
- agent-infra repo fix
- Licensing
- commercial repo fix
- SDK languages
- go, java, python, rest, ruby, typescript vendor fix
- Protocols
- mcp-server, opentelemetry vendor fix
- Developer activity
- OpenRank 6.39 (12-mo avg 3.59) · 16 participants — 2026-09 third-party fix
When to use
Optimised for: self-hostable cloud dev envs + AI-agent sandboxes
Anti-fit: not applicable — sandbox/runtime, not memory product
Pros & cons
Pros
Apache 2.0 self-hostable (key differentiator vs Gitpod commercial / Codespaces / e2b); CDE heritage from Codeanywhere; AI-sandbox tier added 2024; EU founder presence (Croatian).
Cons
Smaller seed funding than peers; newer brand than Gitpod / Codespaces; AI-sandbox tier less specialized than e2b for agent use case.
Claims & capabilities
Apache 2.0 OSS CDE; self-hostable; AI-sandbox tier for agent code execution 2024; $5M seed 2024 (RTP Global); founded 2024 by Ivan Burazin (ex-Codeanywhere)
Technical surface
- API surface
- REST + CLI
- Backend storage
- not applicable — sandbox/runtime, not memory product
- Deployment
- Managed-only — Daytona cloud (pay-as-you-go); enterprise tier offers BYOC; archived OSS repo (v0.190.0) still forkable but unmaintained
- Embedding model
- not applicable — not a memory product
- Multi-tenancy
- not applicable — sandbox/runtime, not memory product
- MCP
- yes — Daytona MCP server (shipped with the CLI/MCP tools in daytona/clients) for agent sandbox control
- A2A
- not applicable — sandbox/runtime, not memory product
- OpenTelemetry
- not applicable — sandbox/runtime, not memory product
Alternatives to Daytona → live options ranked by shared design, licence, hosting and MCP support
Similar systems
Other ai sandbox & runtime environments in the catalog, ranked by inbound references.
- e2b T1
e2b provides secure, ephemeral sandboxes (Firecracker microVMs) for AI agent code execution. Each sandbox spins up in <200ms with full Linux environment, Python/Node/etc preinstalled. Substrate for code-agent products including Anthropic Claude Code (artifacts run on e2b), Perplexity, You.com Search, Cognition Devin (partially), and Hugging Face Spaces. Apache 2.0 OSS + managed cloud. $13M Seed + Series A 2024 (Sunflower Capital + a16z).
- Modal Sandboxes T1
Modal Labs ships a serverless container platform with first-class GPU support; Sandboxes feature (2024) adds ephemeral, AI-agent-friendly compute sandboxes. Founded 2021 by Erik Bernhardsson (ex-Spotify ML, author of Luigi + Annoy). $87M total raised through Series B (Lux Capital + Redpoint + Definition + Amplify). Used by major LLM apps for batch inference + agent code execution.
- Anchor (Anchor Browser) T3
Anchor Browser provides cloud-hosted Chromium instances optimised for AI agent use — anti-detect, persistent sessions, residential proxies, CAPTCHA handling. Founded 2023, YC W24. $2.6M seed disclosed. Distinct from Browserless by adding persistent-state + anti-detect optimised for AI-agent web workflows.
- Browserless.io T2
Browserless is a headless-browser-as-a-service — managed Chromium / Playwright / Puppeteer endpoints for web scraping, screenshots, PDF generation, web automation. Increasingly used as substrate for browser-agent products. Founded 2017 by Joel Griffith. Bootstrapped + small seed. Distinct from Playwright OSS — Browserless ships managed Chromium farms with anti-bot circumvention.
- Coder.com T2
Coder.com (formerly Coder Technologies) provides enterprise self-hosted cloud development environments — VS Code Server + dev workspaces on K8s / VMs. $30M Series B 2021 (Redpoint + Founders Fund + Coatue). Founded 2017 by Kyle Carberry + Ammar Bandukwala. 2024 launched 'Coder AI' for agent-execution inside workspaces. Self-hostable AGPL OSS + commercial enterprise.
- CodeSandbox AI T2
CodeSandbox is the long-running browser-based dev sandbox (founded 2017 by Ives van Hoorne + Bas Buursma in Amsterdam). **Acquired by Together AI Oct-2024** to anchor Together's agent-execution stack alongside its GPU inference cloud. AI features include AI-assisted coding, agent-execution sandboxes, and instant-preview for AI-generated apps.
Sources (32 cited facts, 1 third-party)
Each fact links to the page it came from; the badge says who published it (how to read sources).
- What it is Self-hostable development environment manager (cloud dev envs, AI sandbox tier) vendor
- What it does & what's distinct Daytona is secure, elastic sandbox infrastructure for running AI-generated code and agen… repo
- Claims / benefits Apache 2.0 OSS CDE; self-hostable; AI-sandbox tier for agent code execution 2024; $5M se… vendor
- Created 2024 (founded; Codeanywhere predecessor 2009) vendor
- Latest release v0.226.1 (2026-10-23) registry
- License Apache-2.0 (SDKs in daytona/clients; CLI under AGPL-3.0); core platform closed-source si… repo
- GitHub daytona/clients — ~15 stars (SDKs, API clients, CLI); the former daytonaio/daytona monor… repo
- Funding $5M seed 2024 (RTP Global + Lighthouse Ventures + 500 Startups) vendor
- Pricing Pay-as-you-go per-second billing (vCPU $0.0504/h, memory $0.0162/GiB-h, storage $0.00010… vendor
- Compliance SOC 2 Type II (in-progress); GDPR vendor
- Data handling Self-host: deployer-controlled; managed cloud never trains on customer code vendor
- Deployment Managed-only — Daytona cloud (pay-as-you-go); enterprise tier offers BYOC; archived OSS … vendor
- HQ Split, Croatia + US vendor
- Founders / pedigree Ivan Burazin (CEO; ex-Codeanywhere CEO 2009-23); Vedran Jukic (CTO) vendor
- Code/weights release Apache 2.0 — OSS vendor
- API surface REST + CLI vendor
- MCP support yes — Daytona MCP server (shipped with the CLI/MCP tools in daytona/clients) for agent s… repo
- Runtimes TypeScript, Python, Ruby, Go, Java repo
- Optimised for self-hostable cloud dev envs + AI-agent sandboxes vendor
- Adjacent infrastructure Gitpod (closest CDE peer, commercial); GitHub Codespaces; competes with e2b for AI-sandb… vendor
- Pros Apache 2.0 self-hostable (key differentiator vs Gitpod commercial / Codespaces / e2b); C… vendor
- Cons Smaller seed funding than peers; newer brand than Gitpod / Codespaces; AI-sandbox tier l… vendor
- Project & sources www.daytona.io/ vendor
- cost-pricing-model subscription vendor
- cost-last-verified 2026-06-29 vendor
- architecture-deployment-locus cloud vendor
- licensing-bucket commercial repo
- positioning-platform-vs-product platform vendor
- taxonomy-three-layer-rollup agent-infra repo
- developer-activity-opendigger {"activity":82.33,"as_of":"2026-09","openrank_12mo":3.59,"openrank_current":6.39,"partic… third-party
- sdk-languages go,java,python,rest,ruby,typescript vendor
- protocol-support mcp-server,opentelemetry vendor
What changed
Changes to this record's lifecycle, licence, release, pricing and hosting facts, from the catalog's git history. Subscribe (Atom)
- 2026-10-29
- License “Apache-2.0 (SDKs in daytona/clients; CLI under AGPL-3.0); core platform closed-source since June 2026 (archived OSS repo remains under its original license at v0.190.0)” → “Apache-2.0 (SDKs in daytona/clients; CLI under AGPL-3.0); core platform closed-source since June 2026 (archived daytonaio/daytona repo remains AGPL-3.0 at v0.190.0)” source
- 2026-10-27
- License “Apache 2.0” → “Apache-2.0 (SDKs in daytona/clients; CLI under AGPL-3.0); core platform closed-source since June 2026 (archived OSS repo remains under its original license at v0.190.0)” source
- Latest release “not applicable — sandbox/runtime, not memory product” → “v0.226.1 (2026-10-23)” source
- Pricing “OSS (free); Daytona Cloud managed paid tier; enterprise on-prem (quote)” → “Pay-as-you-go per-second billing (vCPU $0.0504/h, memory $0.0162/GiB-h, storage $0.000108/GiB-h, first 5 GiB free); $200 free compute; startup credits up to $50k; preemptible GPUs from $0.57/h; Enterprise custom (SSO, audit logs, BYOC)” source
- Deployment “Self-hostable (Apache 2.0) + managed cloud” → “Managed-only — Daytona cloud (pay-as-you-go); enterprise tier offers BYOC; archived OSS repo (v0.190.0) still forkable but unmaintained” source
- MCP support “not applicable — sandbox/runtime, not memory product” → “yes — Daytona MCP server (shipped with the CLI/MCP tools in daytona/clients) for agent sandbox control” source
Related systems
References (23)
- Anthropic Claude (foundation models) integrates with — Daytona docs have a guide for running Anthropic Claude (foundation models) with Daytona sandboxes. (verified 2026-10-29)
- AutoGen / AG2 integrates with — Daytona docs have a guide for running AutoGen / AG2 with Daytona sandboxes. (verified 2026-10-29)
- Claude Agent SDK integrates with — Daytona docs have a guide for running Claude Agent SDK with Daytona sandboxes. (verified 2026-10-29)
- Claude Code (Anthropic) integrates with — Daytona docs have a guide for running Claude Code (Anthropic) with Daytona sandboxes. (verified 2026-10-29)
- Cursor (IDE) integrates with — Daytona docs have a guide for running Cursor (IDE) with Daytona sandboxes. (verified 2026-10-29)
- Devin (Cognition) integrates with — Daytona docs have a guide for running Devin (Cognition) with Daytona sandboxes. (verified 2026-10-29)
- DSPy integrates with — Daytona docs have a guide for running DSPy with Daytona sandboxes. (verified 2026-10-29)
- Fireworks AI integrates with — Daytona docs have a guide for running Fireworks AI with Daytona sandboxes. (verified 2026-10-29)
- Google Agent Development Kit (ADK) integrates with — Daytona docs have a guide for running Google Agent Development Kit (ADK) with Daytona sandboxes. (verified 2026-10-29)
- Inngest integrates with — Daytona docs have a guide for running Inngest with Daytona sandboxes. (verified 2026-10-29)
- LangChain (framework) integrates with — Daytona docs have a guide for running LangChain (framework) with Daytona sandboxes. (verified 2026-10-29)
- LangGraph (orchestration) integrates with — Daytona docs have a guide for running LangGraph (orchestration) with Daytona sandboxes. (verified 2026-10-29)
- Letta Code integrates with — Daytona docs have a guide for running Letta Code with Daytona sandboxes. (verified 2026-10-29)
- Mastra integrates with — Daytona docs have a guide for running Mastra with Daytona sandboxes. (verified 2026-10-29)
- Model Context Protocol (MCP spec) integrates with — Daytona docs have a guide for running Model Context Protocol (MCP spec) with Daytona sandboxes. (verified 2026-10-29)
- OpenAI Agents SDK integrates with — Daytona docs have a guide for running OpenAI Agents SDK with Daytona sandboxes. (verified 2026-10-29)
- OpenAI Codex CLI integrates with — Daytona docs have a guide for running OpenAI Codex CLI with Daytona sandboxes. (verified 2026-10-29)
- OpenAI GPT family (GPT-5 / GPT-4o / o3 / o4) integrates with — Daytona docs have a guide for running OpenAI GPT family (GPT-5 / GPT-4o / o3 / o4) with Daytona sandboxes. (verified 2026-10-29)
- Opencode (SST) integrates with — Daytona docs have a guide for running Opencode (SST) with Daytona sandboxes. (verified 2026-10-29)
- SGLang integrates with — Daytona docs have a guide for running SGLang with Daytona sandboxes. (verified 2026-10-29)
- TRL (Hugging Face) integrates with — Daytona docs have a guide for running TRL (Hugging Face) with Daytona sandboxes. (verified 2026-10-29)
- Vercel AI SDK integrates with — Daytona docs have a guide for running Vercel AI SDK with Daytona sandboxes. (verified 2026-10-29)
- vLLM integrates with — Daytona docs have a guide for running vLLM with Daytona sandboxes. (verified 2026-10-29)
Referenced by (11)
- Arcade.dev integrates with — Arcade docs have a Daytona integration page. (verified 2026-10-29)
- Arize Phoenix integrates with — Arize Phoenix docs have a Daytona integration page. (verified 2026-10-29)
- AutoGen / AG2 integrates with — AG2 code execution docs list Daytona as a hosted code execution environment (DaytonaEnvironment). (verified 2026-10-29)
- CrewAI integrates with — CrewAI docs have a Daytona sandbox tools page. (verified 2026-10-29)
- Google Agent Development Kit (ADK) integrates with — ADK integrations catalog has a "Daytona plugin for ADK" page (Execute code, run shell commands, and manage files in secure sandboxes). (verified 2026-10-29)
- Inngest integrates with — Inngest AgentKit docs: "Using AgentKit with Daytona" integration guide. (verified 2026-10-29)
- LangChain (framework) integrates with — LangChain docs have a Daytona integration provider page (Secure and elastic infrastructure for running your AI-generated code). (verified 2026-10-29)
- Mastra integrates with — Mastra repo ships the Daytona workspace sandbox package. (verified 2026-10-29)
- OpenAI Agents SDK integrates with — OpenAI Agents SDK sandbox clients docs list DaytonaSandboxClient (openai-agents[daytona]). (verified 2026-10-29)
- Phidata (now Agno) integrates with — Agno ships a daytona toolkit (agno.tools.daytona). (verified 2026-10-29)
- Pydantic-AI integrates with — Pydantic AI harness docs have a Daytona sandbox integration page. (verified 2026-10-29)