boxes.dev vs Ellipsis

At a glance

As of September 2026.

Agents as code, or a machine you work in

Ellipsis runs agents that you define in files and start from events, and a boxes.dev devbox is a lasting machine that you and the agent work in together.

An Ellipsis automation is a YAML file in your repository with a prompt, an environment, permissions, a budget, and an optional trigger. Merging the file deploys it, and each run starts a new session that ends after its first turn. You can also start an interactive session from the dashboard or the CLI and send follow-ups until the work is done. Individuals pay nothing beyond a Claude or ChatGPT subscription. Organizations pay for each sandbox's CPU and memory while it runs, including while it waits for the next message, and automations use credits for model usage.

On boxes.dev, each task gets a devbox where Claude Code or Codex works while you watch, steer, and review the diff. Automations, @boxes.dev in Slack, and assigned Linear issues can also start agents on their own devboxes, and you can open any of those threads to continue the work.

How environments are made

Both save a prepared environment for new sessions, and boxes.dev can also start from the environment already on your laptop.

An Ellipsis environment runs three setup scripts, saves the result of each, and reruns only what a change affects, so a session with no changes runs just the short per-session script. Saved results keep files and running services.

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.

Reaching the running app

Ellipsis reports a session's work as messages, diffs, commits, and pull requests, and boxes.dev also lets you and the agent use the running app.

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 take work from Slack threads, and they differ in who can steer a session and what the team shares.

Mentioning @ellipsis in a Slack thread, a GitHub issue or pull request, or a Linear issue starts a session that answers in that thread, and replies there continue it. A session started from the dashboard or the CLI takes messages only from the person who started it. Sessions are searchable across the organization, including the session behind any pull request. Costs break down by developer, and owners and admins can set spending limits for each one.

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 Ellipsis shines

• Agents as code. Automations, environments, and mention handlers live in YAML, go through pull request review, and take effect on merge.
• Hard spending caps. Budgets for each session, each automation by day, week, and month, the whole account, and each developer, with alerts at 80% and 100%.
• Scoped credentials. Each session gets its own GitHub token, limited to the repositories and permissions its configuration names.
• Cost tracking. Each session records its cost and tokens, and usage breaks down by session, developer, and automation.
• Typed output and SDKs. Automations can return JSON that matches your schema, and Python and TypeScript SDKs start, stream, and read sessions.

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.

Ellipsis's pricing page says there are no idle charges, while its docs bill an organization's sandbox while it waits for your next message. See Ellipsis's pricing and pricing docs.

Using both

Ellipsis and boxes.dev can work on the same repositories and pull requests. You can keep Ellipsis for automations and mention handlers defined in your repository, and use boxes.dev to work with Claude Code or Codex on a lasting copy of your full environment.

Frequently asked questions

Can I use my Claude and ChatGPT subscriptions with both?

Yes. Ellipsis connects a Claude subscription with a token from claude setup-token and a ChatGPT sign-in for Codex. boxes.dev runs Claude Code with your Claude plan and Codex with your ChatGPT plan, or with an API key.

Does an Ellipsis session keep its machine?

An Ellipsis sandbox runs for up to an hour, and a later follow-up resumes the session with its workspace. A boxes.dev devbox sleeps when idle, keeping its files and memory, so dev servers and databases resume where they left off, and it 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

• Ellipsis: home, docs, quick start, sessions, lifecycle, environments, environment schema, automations, triggers, models, budgets, permissions, account settings, GitHub, Slack, Linear, start a session API, observability, pricing docs, and pricing.
• boxes.dev: How boxes.dev works, Choose how to set up your project, Set up from a local folder, Create a project from GitHub, 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, Work from Slack, Work from Linear, Organize and share threads, Team access and roles, Create and publish a Team Template, Environment files and secrets, Add MCP servers, Connect Codex and Claude, Create an automation, Trigger an automation through the API, Commit, push, and open a pull request, Branch a conversation, Shared project storage, Install and use the CLI, Use boxes.dev on your phone, and Plans, seats, and box-hours.