Which sandbox providers offer “coding agents preinstalled”?

Claude Code, Codex or similar are already installed in the default image. Fully: Agent 37, Boat, InstaBox, Lizard, Sandboxer, Vercel Sandbox and boxd. With a catch: Daytona and E2B. Not at all: Blaxel, Cloudflare Sandbox, Modal, Morph, Runtime, Sprites and Tensorlake.

Which sandbox providers offer “send it a prompt”?

The provider runs an agent for you: you send a prompt, it does the work in the sandbox. Fully: Agent 37, Boat and Sandboxer. With a catch: Lizard. Not at all: Blaxel, Cloudflare Sandbox, Daytona, E2B, InstaBox, Modal, Morph, Runtime, Sprites, Tensorlake, Vercel Sandbox and boxd.

Which sandbox providers offer “one-click Hermes”?

Hermes Agent can be set up without a terminal. Fully: Agent 37. With a catch: Boat and E2B. Not at all: Blaxel, Cloudflare Sandbox, Daytona, InstaBox, Lizard, Modal, Morph, Runtime, Sandboxer, Sprites, Tensorlake, Vercel Sandbox and boxd.

Which sandbox providers offer “one-click OpenClaw”?

OpenClaw can be set up without a terminal. Fully: Agent 37 and Lizard. With a catch: Boat and Daytona. Not at all: Blaxel, Cloudflare Sandbox, E2B, InstaBox, Modal, Morph, Runtime, Sandboxer, Sprites, Tensorlake, Vercel Sandbox and boxd.

Which sandbox providers offer “browser built in”?

A web browser (Chrome or Chromium) ready for an agent to drive. Fully: Agent 37, Boat, InstaBox, Lizard, Runtime, Sandboxer, Tensorlake and boxd. With a catch: E2B and Morph. Not at all: Blaxel, Cloudflare Sandbox, Modal, Sprites and Vercel Sandbox.

Which sandbox providers offer “desktop for computer use”?

A graphical desktop an agent can see and click, for computer-use agents. Fully: Agent 37, Boat, Daytona, E2B, InstaBox, Lizard, Morph, Runtime, Sandboxer, Tensorlake and boxd. Not at all: Blaxel, Cloudflare Sandbox, Modal, Sprites and Vercel Sandbox.

Which sandbox providers offer “runs other platforms' agents”?

Documented as the machine for Cursor cloud agents, Devin, Claude Managed Agents or similar. Fully: Agent 37, Blaxel, Cloudflare Sandbox, Daytona, E2B, Modal, Runtime, Tensorlake, Vercel Sandbox and boxd. Not at all: Boat, InstaBox, Lizard, Morph, Sandboxer and Sprites.

Built-in agents

The idea

A preinstalled agent is not a hosted agent. Preinstalled means the binary is on the disk and a login may be configured; the agent loop still runs inside your sandbox and you still pay the model provider, or sign in with your own subscription. Hosted means the provider runs the loop and bills you for it.

The useful distinction is threefold: is an agent installed, can you prompt it through the provider's API rather than a terminal, and does the provider manage the model credentials? Very few do all three.

Preinstalled agents also change the setup story. A machine with Claude Code and Codex already on it is a working environment for a non-engineer who can type a request, even if nothing else is click-driven.

Where providers split

The claim on the left, the provider's own words on the right

Installed and promptable

Boat installs seven harnesses and exposes a prompt endpoint with steering, interrupts and multiple conversations. Sandboxer installs six and has a prompt API with an event stream. Agent 37 has six agent templates plus a separate managed-hosting product where the agent is the product.

Lizard installs five and prompts them from the CLI only; the SDK has no prompt method. boxd installs three and relies on the in-VM CLI.

Installed, not managed

InstaBox and Vercel put coding agents in their default images but publish no agent-run API: you open a terminal and use them. E2B documents how to run Claude Code, Codex and Amp, but does not claim to preinstall them.

That is enough for a technical user and not enough for a product that wants to start an agent on demand.

Bring your own

Runtime does not preinstall agents, and its own docs say no bridge harness has run on it yet. Sprites offers plugins and SDK integrations rather than a hosted agent. Morph exposes a tmux API so an agent can be driven programmatically, but the agent is yours.

At these providers the sandbox is the product and the agent is an application you install.

One worked case

The same job at every provider, from the documented defaults

Send a task and read the stream back

You want to post a prompt to a sandbox and receive the agent's output as a stream, without opening a terminal or holding a model key inside the machine.

Install
The agent binary is either on the disk already or something your setup script installs.
Prompt
One API call with a prompt, or a shell command typed by a person.
Pay
The model bill goes to the provider, to your API key, or to your subscription login.

Only a few providers do all three: installed, promptable through their API, and managing the model credentials. Everywhere else the sandbox is the product and the agent is an application you bring.

What each provider does

Agent 37: Six agent templates plus a separate managed-hosting product where the agent is the product; the templates are prompted through the API.
Blaxel: Every sandbox exposes an MCP server agents use to operate it, but Agent Runtime is labelled coming soon.
Boat: Seven harnesses preinstalled and promptable through one API call with steering, interrupts and parallel conversations.
boxd: Claude Code, Codex and OpenCode are preinstalled and the in-VM CLI is authenticated, but there is no prompt API.
Cloudflare Sandbox: No agent in the 1.0 base image; you install Claude Code in your Dockerfile, following a guide that also keeps the model credential in the Worker.
Daytona: No agent is preinstalled; you follow a first-party guide to install Claude Code or Codex, or drive the desktop through the computer-use API.
E2B: Guides show Claude Code, Codex and Amp running, but preinstallation is not claimed and there is no agent-run API.
InstaBox: Claude Code and Codex are in the default and agent templates, and logins persist because home is /data/home; no agent-run API.
Lizard: Five agent templates, prompted from the CLI with streaming and interrupts; the SDK has no prompt method.
Modal: No agent in the image and no agent API; the agent is code you run in the sandbox.
Morph: A tmux API lets you drive Claude Code or Codex programmatically, but nothing is preinstalled.
Runtime: No coding agents in the default image, and the vendor says no bridge harness has run on Runtime yet.
Sandboxer: Six harnesses in every sandbox, a prompt API that returns a prompt id, and steering for three of them.
Sprites: Plugins and SDK integrations, but no preinstalled agent and no managed agent API.
Vercel Sandbox: Coding agents are in the universal image, but you drive them yourself through a terminal.
Tensorlake: No agent ships in the images, but a first-party OpenCode plugin and guides for Claude Managed Agents, Cursor, Devin and Crabbox send an agent's tool calls into a sandbox.

What to watch for

The details that decide the answer in practice

01
Whether the agent is preinstalled, promptable through an API, or both.
02
Who pays for the model: the provider, your API key, or your subscription login.
03
Whether the provider manages model credentials or expects them in the environment.
04
Whether the agent runs as a hosted service or inside your sandbox.
05
Whether a non-engineer can start it without a terminal.

Compare all 16

Docs read 28 October 2026

Some providers ship the machine with coding agents already installed and a way to prompt them. Others ship a computer and expect you to bring the agent.
Provider	Agents installed, and promptable?	Does it?	What that means
Agent 37	Six templateshosted	Yes	Six agent templates (Hermes, OpenClaw, Claude Code, Codex, Grok, OpenCode) plus Pi and n8n, and a separate managed-hosting product where the agent is the product. Claude Code and Codex use your own account.Agent 37 docs: Templates — system agent images (Hermes, OpenClaw, Claude Code, Codex, OpenCode, Grok, Pi) ↗ Agent 37's own wordspricing-page “Run OpenClaw, Hermes, Claude Code, Codex, OpenCode, or Grok around the clock. Yours is live in one click.” Agent 37pricing-page
Blaxel	MCP serverruntime soon	Partly	Every sandbox exposes an MCP server that agents use to operate it, and agent hosting is a separate product line, but Agent Runtime is labelled coming soon.Blaxel docs: Agents Hosting ↗ Blaxel's own wordsdocs-confirmed “Every Blaxel sandbox exposes a built-in MCP server so agents can operate the sandbox using tool calls for files, processes, ports, and previews.” Blaxeldocs-confirmed
Boat	Seven harnessesprompt API	Yes	Seven coding-agent harnesses preinstalled on every machine, promptable through one API call with steering, interrupts and parallel conversations.Boat docs: Integrated agents ↗ Boat's own wordsdocs-confirmed “Every sandbox has seven coding-agent harnesses, installed and ready” Boatdocs-confirmed
boxd	Three preinstalledno API	Yes	Claude Code, Codex and OpenCode are preinstalled, and an in-VM boxd CLI is pre-authenticated so an agent can create sibling machines. Claude logins are account-level and injected at boot.boxd docs: Coding agents ↗ boxd's own wordsdocs-confirmed “Every boxd machine ships with three coding agents” boxddocs-confirmed
Cloudflare Sandbox	Noneguides	Partly	No preinstalled agents in the 1.0 images. Guides cover Claude Code, Codex, OpenCode and Pi, plus templates where the vendor's loop runs in its own service. The Agents SDK exposes a sandbox tool.Cloudflare Sandbox docs: Run coding agents in a sandbox ↗ Cloudflare Sandbox's own wordsdocs-confirmed “Run Claude Code in a Linux sandbox to edit a GitHub repository from a prompt, then read its changes as a diff.” Cloudflare Sandboxdocs-confirmed
Daytona	Noneguides	Partly	No hosted agent or preinstalled harness. First-party guides cover Claude Code, Codex, Cursor, Devin, Gemini CLI, OpenCode, Amp and Kiro; computer use is a first-class API.Daytona docs: OpenClaw Guides (preinstalled in the default snapshot) ↗ Daytona's own wordsdocs-confirmed “Daytona does not ship AI-assisted features inside the product” Daytonadocs-confirmed
E2B	None preinstalledguides	Partly	Guides show Claude Code, Codex and Amp running in a sandbox, but preinstallation is not claimed and there is no hosted agent-run API.E2B docs: Hermes Agent (pre-built template) ↗ E2B's own wordsdocs-confirmed “Run AI coding agents like Claude Code, Codex, and Amp in secure E2B sandboxes” E2Bdocs-confirmed
InstaBox	Claude Code + Codex	Yes	Claude Code and Codex are in the default and agent templates, and sign-ins persist because home is /data/home. There is no hosted agent-run API.InstaBox docs: Limits — template table (Claude Code and Codex preinstalled; no managed agent hosting) ↗ InstaBox's own wordsdocs-confirmed “Claude Code, Codex” InstaBoxdocs-confirmed
Lizard	TemplatesCLI prompt	Yes	Five agent templates plus a base image and desktop variants. Agents are prompted from the CLI with streaming and interrupts; the SDK has no prompt method.Lizard docs: CLI agents — Claude Code, Codex, OpenCode, Pi and Prime ↗ Lizard's own wordsdocs-confirmed “base, interpreter, codex, claude, opencode, pi, prime, desktop, desktop-camoufox” Lizarddocs-confirmed
Modal	NoneSDK	No	No hosted agent, desktop, browser or computer-use API. The documented use cases are RL rollouts and coding agents, both as SDK code you write. Modal's own wordsdocs-confirmed “Sandboxes are useful for tasks like executing code generated by an LLM or isolating user-generated code.” Modaldocs-confirmed
Morph	Nonetmux API	Partly	A full tmux API lets you drive Claude Code or Codex programmatically, but no agent is preinstalled and no agent-run API exists. Morph's own wordsdocs-confirmed “Devboxes expose a full tmux API, which lets you programmatically manage coding agents like OpenAI Codex or Claude Code.” Morphdocs-confirmed
Runtime	None preinstalled	No	No preinstalled coding agents: the default image ships Python, Node, Bun, git, compilers and sudo, and agents are installed by you. The vendor says no bridge harness has run on Runtime yet. Runtime's own wordsdocs-confirmed “No bridge harness (Claude Code, Codex) has run on Runtime yet.” Runtimedocs-confirmed
Sandboxer	Six harnessesprompt API	Yes	Six harnesses installed in every sandbox, a prompt API that returns a prompt id, steering for Claude Code, Codex and Pi, and a live model catalogue.Sandboxer docs: Integrated agents ↗ Sandboxer's own wordsdocs-confirmed “Claude Code, Codex, OpenCode, Pi, Kimi Code and Mistral Vibe are installed in every sandbox” Sandboxerdocs-confirmed
Sprites	Noneplugins only	No	Plugins for coding agents and SDK integrations, but no preinstalled agent or provider-managed agent API is documented. Sprites's own wordsdocs-confirmed “Official plugins for every serious coding agent, plus SDKs and native integrations.” Spritesdocs-confirmed
Vercel Sandbox	Agents in imageno API	Partly	The default universal image includes coding agents and common utilities, but there is no agent-run API; you drive them yourself.Vercel Sandbox docs: Sandbox ecosystem (agent integrations) ↗ Vercel Sandbox's own wordsdocs-confirmed “The default image is vercel/sandbox/universal, which includes the current Node.js LTS, Python 3.14, coding agents, and common utilities.” Vercel Sandboxdocs-confirmed
Tensorlake	Nonefive integrations	Partly	Nothing is preinstalled: the images are Ubuntu, Debian and a VNC desktop. The routes are a tensorlake-opencode plugin that intercepts bash, read, write and edit, self-hosted environments for Claude Managed Agents and Cursor Cloud Agents, Devin Outposts, Crabbox for test suites, and a page on preloading skill files into images.Tensorlake docs: Run OpenCode with Tensorlake Sandboxes — the tool-intercepting plugin ↗ Tensorlake's own wordsdocs-confirmed “The model edits, runs, and searches inside an isolated environment instead of on your machine.” Tensorlakedocs-confirmed

The specific capabilities

Each one checked for every provider, with the catch where a version falls short. All capabilities

Built-in agents: capabilities by provider
Capability	Agent 37	Blaxel	Boat	boxd	Cloudflare Sandbox	Daytona	E2B	InstaBox	Lizard	Modal	Morph	Runtime	Sandboxer	Sprites	Tensorlake	Vercel Sandbox
Coding agents preinstalled	Agent 37: Yes. 6 templates	Blaxel: No. The default image is a bare sandbox; agents are code you deploy or an MCP server you connect.	Boat: Yes. 7 harnesses	boxd: Yes. 3 agents	Cloudflare Sandbox: No. The current base images ship no coding agent; you add one in your own Dockerfile, as the guides do.	Daytona: With a catch. OpenClaw is in the default snapshot, but Claude Code and Codex are not; those need an install step.	E2B: With a catch. A prebuilt Hermes template exists, but the default image has no agent and there is no Claude Code or Codex template.	InstaBox: Yes	Lizard: Yes. 5 agents	Modal: No. Nothing is preinstalled and there is no agent API; the agent is code you run.	Morph: No. Devboxes boot from templates you build; no agent is in the default image.	Runtime: No. The default image ships languages and tools but no coding agent; you install the agent yourself.	Sandboxer: Yes. 6 harnesses	Sprites: No. Sprites provide plugins and integrations for agents, but no agent is in the image.	Tensorlake: No. The managed images ship an OS, a desktop and tooling; no coding agent is installed.	Vercel Sandbox: Yes
Send it a prompt	Agent 37: Yes	Blaxel: No. There is no prompt endpoint; Agent Runtime, the product that would run the loop, is marked Soon.	Boat: Yes	boxd: No. boxd runs the machine, not the agent loop; Anthropic or OpenAI runs the loop in the documented integrations.	Cloudflare Sandbox: No. Your Worker holds the credentials and the agent runs as a process you start; there is no prompt endpoint.	Daytona: No. No agent is hosted and there is no prompt call; you install and drive the agent.	E2B: No. Guides show agents running in a sandbox, but no API takes a prompt and runs one for you.	InstaBox: No. There is no prompt endpoint; the API offers exec, files, desktop and snapshots.	Lizard: With a catch. You can send a prompt from the command line, but the SDK and API have no prompt call, so a program cannot start an agent.	Modal: No. Modal sells the computer, not an agent loop; the docs show SDK code you write.	Morph: No. The tmux API lets your program type into an agent, but Morph runs no agent loop of its own.	Runtime: No. Runtime has no agent-run API; its own docs say no bridge harness has run on it yet.	Sandboxer: Yes	Sprites: No. Sprites host an agent you install; there is no prompt endpoint.	Tensorlake: No. Tensorlake exposes a sandbox as a tool for your own agent; it does not run an agent from a prompt.	Vercel Sandbox: No. Agents are in the image but there is no API that runs one; you open a terminal or use the CLI.
One-click Hermes	Agent 37: Yes. $0-99.99/mo	Blaxel: No. No Hermes template or guide is published; you would install it yourself.	Boat: With a catch. Hermes is already installed on every machine, but you still need a terminal command to start it and prompt it.	boxd: No. No Hermes template, harness or guide is documented.	Cloudflare Sandbox: No. No Hermes template; you would install it in your own Dockerfile.	Daytona: No. Daytona documents OpenClaw but not Hermes, so there is no one-click route.	E2B: With a catch. A prebuilt template is ready, but you still create the sandbox with a command and pay by usage.	InstaBox: No. No Hermes template, guide or one-click route is documented.	Lizard: No. The deploy catalog has no Hermes template; only a manual install in a sandbox.	Modal: No. Hermes lists Modal as a terminal backend, not as a one-click host.	Morph: No. No Hermes template or guide is published.	Runtime: No. No Hermes template or guide is published.	Sandboxer: No. Its six harnesses do not include Hermes, and there is no template.	Sprites: No. Hermes is named on the marketing page, but there is no template or guided route.	Tensorlake: No. No Hermes template or guide is published.	Vercel Sandbox: No. A Hermes guide exists, but you follow terminal steps; nothing is one click.
One-click OpenClaw	Agent 37: Yes. $0-99.99/mo	Blaxel: No. A tutorial walks through OpenClaw in a sandbox, but it is terminal work, not one click.	Boat: With a catch. OpenClaw is installed on every machine, but its gateway does not start by itself and you need a terminal.	boxd: No. No OpenClaw template, harness or guide is documented.	Cloudflare Sandbox: No. No OpenClaw template; the guides cover Claude Code, Codex, OpenCode and Pi.	Daytona: With a catch. OpenClaw is in the default snapshot, but you still run a command to start and configure it.	E2B: No. No OpenClaw template or guide is published.	InstaBox: No. No OpenClaw template or guide is published.	Lizard: Yes	Modal: No. No OpenClaw template or guide is published.	Morph: No. No OpenClaw template or guide is published.	Runtime: No. No OpenClaw template or guide is published.	Sandboxer: No. Its harness list does not include OpenClaw, and there is no template.	Sprites: No. OpenClaw is named on the marketing page, but there is no template or guided route.	Tensorlake: No. No OpenClaw template or guide is published.	Vercel Sandbox: No. No OpenClaw template or one-click route is documented.
Browser built in	Agent 37: Yes	Blaxel: No. No browser is installed or offered; you would add Chrome to your own image.	Boat: Yes. Chrome 151	boxd: Yes	Cloudflare Sandbox: No. The base images ship no browser; you install one in your own Dockerfile.	Daytona: Not published	E2B: With a catch. A browser comes with the desktop image or through Kernel cloud browsers, not in the default sandbox image.	InstaBox: Yes	Lizard: Yes	Modal: No. No browser, desktop or computer-use API is documented; the sandbox is a headless container.	Morph: With a catch. A documented example runs headless Chrome in a container, but no browser is installed for you.	Runtime: Yes	Sandboxer: Yes	Sprites: No. No browser is installed or offered; a browser is something you run and reach through a proxy.	Tensorlake: Yes	Vercel Sandbox: No. No browser is documented in the image or as an API; agents in the image are terminal tools.
Desktop for computer use	Agent 37: Yes	Blaxel: No. No graphical desktop is documented; the browser surfaces are a terminal and preview URLs.	Boat: Yes. 1080p 60 fps	boxd: Yes	Cloudflare Sandbox: No. No desktop or computer-use surface is documented.	Daytona: Yes	E2B: Yes	InstaBox: Yes	Lizard: Yes	Modal: No. No desktop, VNC or computer-use API is documented.	Morph: Yes	Runtime: Yes	Sandboxer: Yes	Sprites: No. No desktop is documented; interactive access is a terminal console.	Tensorlake: Yes	Vercel Sandbox: No. No desktop, VNC or computer-use API is published for Sandbox.
Runs other platforms' agents	Agent 37: Yes	Blaxel: Yes	Boat: No. No page documents another platform's cloud agents using Boat as their machine.	boxd: Yes	Cloudflare Sandbox: Yes	Daytona: Yes	E2B: Yes	InstaBox: No. No page documents another platform's cloud agents using InstaBox.	Lizard: No. No page documents another platform's cloud agents using Lizard.	Modal: Yes	Morph: No. No page documents another platform's cloud agents using Morph.	Runtime: Yes	Sandboxer: No. Its agent pages cover SDKs and frameworks, not another platform's hosted cloud agents.	Sprites: No. Its ecosystem lists coding tools, not another platform's cloud agents.	Tensorlake: Yes	Vercel Sandbox: Yes

YesWith a catchNoNot publishedHover or select a mark to see the catch.

Questions to ask before you sign

Each one targets something the documentation does not answer

Is the agent preinstalled, promptable through your API, or both?
Who pays for the model — you, my API key, or my subscription login?
Does the provider manage model credentials, or expect them in the environment?
Does the agent loop run inside my sandbox or as a hosted service, and what does that change about billing?
Can a non-engineer start it without a terminal, and what is the first screen they see?

Common questions

Answered from the capability checks; each links to the provider-by-provider detail and its sources

Which sandbox providers offer “coding agents preinstalled”?: Claude Code, Codex or similar are already installed in the default image. Fully: Agent 37, Boat, InstaBox, Lizard, Sandboxer, Vercel Sandbox and boxd. With a catch: Daytona and E2B. Not at all: Blaxel, Cloudflare Sandbox, Modal, Morph, Runtime, Sprites and Tensorlake. See each provider's catch
Which sandbox providers offer “send it a prompt”?: The provider runs an agent for you: you send a prompt, it does the work in the sandbox. Fully: Agent 37, Boat and Sandboxer. With a catch: Lizard. Not at all: Blaxel, Cloudflare Sandbox, Daytona, E2B, InstaBox, Modal, Morph, Runtime, Sprites, Tensorlake, Vercel Sandbox and boxd. See each provider's catch
Which sandbox providers offer “one-click Hermes”?: Hermes Agent can be set up without a terminal. Fully: Agent 37. With a catch: Boat and E2B. Not at all: Blaxel, Cloudflare Sandbox, Daytona, InstaBox, Lizard, Modal, Morph, Runtime, Sandboxer, Sprites, Tensorlake, Vercel Sandbox and boxd. See each provider's catch
Which sandbox providers offer “one-click OpenClaw”?: OpenClaw can be set up without a terminal. Fully: Agent 37 and Lizard. With a catch: Boat and Daytona. Not at all: Blaxel, Cloudflare Sandbox, E2B, InstaBox, Modal, Morph, Runtime, Sandboxer, Sprites, Tensorlake, Vercel Sandbox and boxd. See each provider's catch
Which sandbox providers offer “browser built in”?: A web browser (Chrome or Chromium) ready for an agent to drive. Fully: Agent 37, Boat, InstaBox, Lizard, Runtime, Sandboxer, Tensorlake and boxd. With a catch: E2B and Morph. Not at all: Blaxel, Cloudflare Sandbox, Modal, Sprites and Vercel Sandbox. See each provider's catch
Which sandbox providers offer “desktop for computer use”?: A graphical desktop an agent can see and click, for computer-use agents. Fully: Agent 37, Boat, Daytona, E2B, InstaBox, Lizard, Morph, Runtime, Sandboxer, Tensorlake and boxd. Not at all: Blaxel, Cloudflare Sandbox, Modal, Sprites and Vercel Sandbox. See each provider's catch
Which sandbox providers offer “runs other platforms' agents”?: Documented as the machine for Cursor cloud agents, Devin, Claude Managed Agents or similar. Fully: Agent 37, Blaxel, Cloudflare Sandbox, Daytona, E2B, Modal, Runtime, Tensorlake, Vercel Sandbox and boxd. Not at all: Boat, InstaBox, Lizard, Morph, Sandboxer and Sprites. See each provider's catch

Part of Running it. Next: put two or three providers side by side.