boxes.dev vs Claude Code

At a glance

As of September 2026. This page compares boxes.dev with Claude Code's cloud sessions, also called Claude Code on the web.

What the cloud machine starts from

Claude Code's cloud sessions start from a fresh copy of your repository, and boxes.dev starts from a copy of a machine where your app already runs.

Each Claude Code cloud session gets a fresh Ubuntu virtual machine with your repository cloned and common language toolchains installed. The session counts toward your Claude plan's usage limits, with no separate charge for the machine. A cloud environment can add environment variables and a setup script whose output Anthropic caches for later sessions. Services start fresh in every session, and configuration that lives only on your computer, such as user-level MCP servers and skills, doesn't carry over.

boxes.dev first sets up your full development environment on a cloud machine called the Template box, with the tools, databases, services, and data your app needs, so an agent can run the app and test its changes end to end. A setup agent can port the environment from your laptop, including the files, local data, agent settings, and skills you choose to upload, or build it from a GitHub repository. boxes.dev then saves the Template box as a snapshot, and every task runs on its own devbox, a full, isolated copy of that machine. A maintenance script can keep the Template box current as your code changes, running on a schedule or when files such as a lockfile change, and each successful run saves a new snapshot.

You'd never let an engineer ship code they hadn't run, and a full environment holds the agent to the same standard. On a boxes.dev devbox, the agent runs your app and tests its changes in the browser as it builds, and it reproduces bugs in the real app to find the root cause instead of guessing from the code, so it writes better code and makes fewer mistakes. It can also take screenshots and record video for you to review, so you can hand it most repetitive manual testing.

When the machine goes idle

A boxes.dev devbox keeps its running programs through sleep, while an idle Claude Code cloud session loses its virtual machine.

Claude Code's cloud sessions stop after a period of inactivity, and Anthropic reclaims the VM. Reopening the session starts a fresh VM with your conversation, but running work such as subagents and shell commands isn't restored.

A boxes.dev devbox sleeps once no agent is working and nobody is using it. Sleep keeps the machine's files and memory, so dev servers, databases, and terminal sessions resume where they left off when it wakes. It stays yours until you delete it, so you can pick up the next day where you left off.

Working in the machine

In a Claude Code cloud session, Claude runs the commands in the VM, and on boxes.dev, you can also work in the devbox yourself.

Claude Code's docs say that you don't get a shell into a cloud session's VM, so you ask Claude to run tests or start services.

On boxes.dev, you can open a terminal on the devbox, edit its files, and run your app alongside the agent, with the tools listed under What comes with every boxes.dev devbox, over SSH, or in VS Code or a JetBrains IDE with dvb ide.

Reaching the running app

boxes.dev puts the running app in a browser you share with the agent, and Claude Code's desktop app previews apps on your computer.

Claude Code's desktop app can start a dev server in a session on your computer and open it in its Browser pane, where Claude checks its changes and you can use the app. For cloud sessions, you review Claude's messages and diffs.

Each boxes.dev devbox runs a browser that you and the agent share, so you can watch the agent test the app, click through it yourself, or comment on page elements to show the agent what to change. Ports forwards the app to the same localhost port on your laptop and gives each devbox stable .localhost addresses. A public link shares a devbox's running app with anyone, and a Project URL gives your project one stable public address that you can point at any devbox, which suits OAuth callbacks and webhooks.

Claude Code and Codex together

boxes.dev runs Claude Code with your Claude login and Codex with your ChatGPT login, or either with an API key, and you choose the agent for each thread on the same devboxes.

Working with your team

Both bring agents into Slack and share work as links. Claude Tag works in shared channels under service accounts, and boxes.dev runs work in your project with your access, including requests from teammates you allow.

On Team and Enterprise plans, you can share a Claude Code cloud session's link with your organization, and recipients see its latest state. @Claude in Slack starts a cloud session on the account of the person who mentions it. Claude Tag, in public beta, works in shared channels through service accounts that an organization Owner sets up in each connected tool, so its pull requests come from the Claude GitHub App. Claude uses your personal connectors only for your own tasks, after you allow it, and requests from other people in the thread run with the channel's access.

Each boxes.dev devbox belongs to one person and works with their access, such as their GitHub login and cloud credentials. Anyone who can prompt its agent could act with that access, so in the app, teammates get read-only access to your work. You can share a thread as a link, and a team admin can let teammates read every thread that isn't marked private and browse each other's projects in a Team workbench. Teammates can't send prompts, open your terminal, or control your devbox.

In Slack, mentioning @boxes.dev in a thread starts Codex or Claude Code on a new devbox, and later mentions in that thread send follow-ups to the same conversation. By default, only you can start work in your project from Slack or follow up on it. If you allow teammates, they can also start work there with @boxes.dev @YourName and send follow-ups, and their requests run with your access and usage. boxes.dev sends you a DM with links to each task a teammate starts, and commits can link to the thread that produced them.

What comes with every boxes.dev devbox

The boxes.dev desktop app opens the same set of tools for whichever devbox you select:

• Terminal, with tabs that keep running after you close the app.
• Files, a file browser and editor with search across the workspace.
• Git/Review, for branch history and diffs, where comments on changed lines go to the agent together as one message.
• Browser, the browser on the devbox that you and the agent share.
• Ports, for the forwarding, .localhost addresses, and public links described above.
• Activity, which shows the processes using the machine's CPU and memory.

The iOS and Android apps can reply to agents, browse files, and open a shell on a devbox. AWS, Tailscale, and the MCP servers and Claude plugins you add for the project reach every devbox, and agents can leave each other notes in a shared /project folder. You can branch a conversation onto a new devbox that starts with the current files, including uncommitted work.

Where Claude Code shines

• One command from your terminal. claude --cloud sends a task to a new cloud session, and --teleport brings a cloud session back.
• Claude Tag for team channels. On Team and Enterprise, Claude works in Slack channels under your organization's identity, and people without a Claude seat can hand it work.
• Routines with GitHub triggers. Routines, a research preview, can run a saved prompt when a GitHub event such as a new pull request happens.
• Code Review. On Team and Enterprise, a research preview reviews pull requests with several agents and comments on the lines where it found issues, billed by usage.

Pricing

As of September 2026.

A box-hour is one default devbox awake for an hour, and sleeping devboxes don't use any. On Starter, 40 box-hours works out to about two hours of devbox time each working day, and Pro's 250 to about twelve, spread across as many as ten devboxes at once. Your Claude or ChatGPT plan covers the agents' usage. See Plans, seats, and box-hours.

Anthropic's docs say cloud sessions share rate limits with all your other Claude usage, so parallel sessions use those limits proportionately faster. See Claude's pricing.

Using both

We recommend using both. Claude Code is a great agent, and boxes.dev runs the real Claude Code CLI on every devbox with your Claude subscription, so your CLAUDE.md, skills, hooks, and settings work the same way in both places. You can keep claude --cloud and @Claude for quick tasks from your terminal, Slack, and GitHub, and use boxes.dev for tasks that need your full environment, a terminal, or the running app.

Frequently asked questions

Is boxes.dev affiliated with Anthropic?

No. boxes.dev is an independent product and isn't affiliated with or endorsed by Anthropic.

Does boxes.dev use my Claude subscription?

Yes. Sign in with Claude to connect Claude Code, or use an API key. Claude Code's usage on boxes.dev counts toward your Claude plan, and boxes.dev charges only for machine time. See Connect Codex and Claude.

Do skills, hooks, subagents, and MCP servers work?

Yes. Claude Code on a devbox reads your repository's CLAUDE.md, skills, and hooks, and project setup can copy agent settings, skills, and MCP definitions from your computer.

Sources

• Claude Code: cloud sessions, cloud environments, desktop app, routines, Code Review, Claude Code in Slack, Claude Tag, Claude Tag's identity, projects, cross-session messaging, mobile, and Claude's pricing.
• boxes.dev: How boxes.dev works, Update your Template box and snapshots, Startup, teardown, and maintenance, Sleep, wake, and recover a devbox, Review a page with your agent, Preview your app, Project URLs, Shared project storage, Use the agent's terminal view, Install agent plugins, Organize and share threads, Team access and roles, Commit, push, and open a pull request, Install and use the CLI, Work from Slack, Work from Linear, Use boxes.dev on your phone, and Plans, seats, and box-hours.