boxes.dev vs Vorflux

At a glance

As of September 2026.

Whose agent does the work

Vorflux runs its own multi-model harness, and boxes.dev runs Claude Code and Codex.

A Vorflux harness assigns a model and instructions to each role, such as planning, building, reviewing, and testing. In Plan Mode, the agent writes a versioned plan and waits for your approval. Build subagents then take independent tasks in parallel, and a review agent checks the result. Machine time and model usage come out of one credit balance.

boxes.dev runs the Claude Code and Codex CLIs on your devboxes, signed in with your Claude or ChatGPT plan or an API key, so your CLAUDE.md or AGENTS.md, skills, and settings work as they do on your computer.

How environments are made

Both use a setup agent and save a snapshot for new work, and boxes.dev can also start from the environment already on your laptop.

During onboarding, a Vorflux setup agent clones your repositories, installs dependencies, smoke-tests each repository until it runs, and recommends the secrets it needs. You save the machine, or it saves itself after 30 minutes, and that snapshot becomes the team's machine image for new sessions.

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 whole app, with its databases and services, and tests its changes in the browser as it builds. 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.

Reaching the running app

Both let you and the agent use the app on the cloud machine and share it by link, and boxes.dev adds a Project URL that you can move between devboxes.

In a Vorflux session, the Desktop tab shows the machine's screen live, so you can watch the agent drive its browser or take over yourself. Public preview links for its ports stop working when the session's machine ends.

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. 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.

Working with your team

Both bring agents into Slack and let teammates follow the work.

Vorflux is a shared workspace where teammates can follow each other's sessions live. Mentioning @Vorflux in Slack starts a session, and people in the thread can steer it. Forking a session carries its context to a new one, which you can hand to a teammate.

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. Team Templates let an admin prepare one starting environment for everyone on the team, while each member's own credentials go only to that member's project.

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 port forwarding, stable .localhost addresses, and public links.
• Activity, which shows the processes using the machine's CPU and memory.

You can branch a conversation onto a new devbox that starts with the current files, including uncommitted work.

Where Vorflux shines

• Ticket to merged pull request. Plan review, parallel build subagents, a review agent, testing, and a merge queue that lands pull requests in order.
• A separate testing phase. After the build, a testing agent writes a test report of what passed, with screenshots and video for each claim, and tests Android apps on an emulator and iOS builds on remote Macs.
• Design review. For UI work, agents draw live mockups side by side on a design canvas before building.
• Memory that tidies itself. Agents write what they learn to an account-wide /memory/ volume, and a daily pass merges duplicates and resolves contradictions.
• Auto Review for any pull request. Vorflux reviews your team's pull requests, whoever wrote them, with inline comments and an optional risk score.

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.

Vorflux runs Anthropic models on credits at provider prices or your own API key. On boxes.dev, Claude Code uses your Claude plan, which is heavily discounted. By our estimate, a fully utilized Claude Max plan is at least 40x cheaper than the same usage at API prices, so you'll pay far less for the same tokens.

Each Vorflux session has a spending cap, $1,000 by default. Its docs and pricing page give different idle stop times, four hours and one hour. See Vorflux's pricing and billing docs.

Using both

Vorflux and boxes.dev can work on the same repositories and pull requests. You can keep Vorflux for tickets that should run from plan to merge on their own, and use boxes.dev to work with Claude Code or Codex on a copy of your full environment.

Frequently asked questions

Can Vorflux run Claude Code or Codex?

Vorflux runs its own harness, which can use Claude and GPT models. boxes.dev runs Claude Code and Codex themselves, with your Claude or ChatGPT plan or an API key.

What happens to a machine when nobody is using it?

A Vorflux machine stops after hours without activity, and a new message resumes the work. A boxes.dev devbox sleeps after about five minutes, keeps its files and memory, and stays until you delete it.

Can I open a devbox in my own editor?

Yes. dvb ide opens a devbox in VS Code or a JetBrains IDE over SSH. See Install and use the CLI.

Sources

• Vorflux: home, machine setup, session workspace, session lifecycle, first session, harness configurator, Plan Mode, subagents, testing, design canvas, memory, PR reviews, merge queue, integrations, automations, ACP, billing, pricing, iOS app, and Android app.
• 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, Browse, edit, and transfer files, Preview your app, Project URLs, Connect Codex and Claude, Organize and share threads, Team access and roles, Create and publish a Team Template, Work from Slack, Work from Linear, Branch a conversation, Install and use the CLI, Use boxes.dev on your phone, and Plans, seats, and box-hours.