Cursor Cloud Agents, formerly Background Agents: what they cost
Cursor renamed Background Agents to Cloud Agents. How you start one, what a month costs on each plan, the Teams token rate on your own key, and where it stops.
Cursor Cloud Agents are the half of Cursor that works while you are not looking. You hand one a task from the editor, from Linear, from a GitHub comment, or from Slack, it clones your repository into an isolated machine on Cursor's infrastructure, and it comes back with a branch and a pull request. They used to be called Background Agents; Cursor's docs now say so in one line and everything else on the page uses the new name. If you are deciding whether Cloud Agents are the right place to send the tickets nobody has started, the questions are how you start one, what it costs on each plan, and the handful of things it will not do.
Checked in early September 2026 against Cursor's own docs and pricing pages, linked throughout. Cursor ships changes weekly; the pages are the source of truth.
Sinatra is our product and it competes with Cloud Agents on the Linear-to-pull-request loop, so this is a competitor writing about a competitor. We have tried to be plain about where Cursor is the better choice, which for many readers of this post it will be.
The rename, and what did not change
Cursor's Cloud Agents page opens with "Cloud Agents were formerly called Background Agents." The product underneath is the same idea: an agent that runs on Cursor's machines rather than yours, so it can keep working after you close the laptop, and so several can run at once without fighting over your checkout.
The name change matters for one practical reason. A lot of the writing online, including forum threads about pricing, uses the old name, and Cursor's own pricing docs have moved on. If you are searching for Cursor background agents, the current docs are under Cloud Agents.
Where you start one
Cursor lists seven entry points, which is more than any other agent in this category ships. From its docs: Cursor for iOS, Cursor Web at cursor.com/agents, the desktop app by selecting Cloud under the agent input, Slack with the @cursor command, a comment of @cursor on a GitHub pull request or issue (or a Bitbucket pull request), Linear, and an API.
The Linear path is the one a product manager will use. Per the Linear integration docs, you open the issue, click the assignee field, and select Cursor. You can also mention @Cursor in a comment to start a new agent or give an existing one more instructions. The agent shows real-time status in Linear and creates the pull request automatically when it finishes.
The GitHub path is a comment. Mention @cursor on a pull request or on an issue and an agent kicks off with that context. It is a mention rather than a label or an assignment, which is a small difference in a demo and a larger one when you want a non-engineer to be able to hand work over without writing a prompt.
What happens after you press go
The agent gets an isolated virtual machine with your repository cloned and, if you have set one up, your environment configured. It works, it pushes a branch, and it opens a pull request. Per the GitHub integration docs, pull requests opened by Cloud Agents are attributed to the person who started the agent, and the agent posts progress comments on the pull request as it goes.
Steering is by mention. Reply @cursor on the pull request or @Cursor on the Linear issue and the agent picks up the instruction. The docs do not describe the agent acting on a plain changes-requested review by itself; every documented follow-up is a mention. Automatic review of pull requests is a separate Cursor product, Bugbot, which reads diffs rather than writing them.
Models are "a curated selection," in the docs' words. You pick from the list Cursor offers for cloud work, which is not the same as the list you get in the editor.
What Cursor Cloud Agents cost
Cloud Agents need a paid plan. The docs say so directly, and the pricing page lists them under Pro, Pro Plus, Ultra, Teams, and Enterprise, with the free Hobby plan offering limited agent requests and no cloud agents.
| Plan | Price | Cloud Agents |
|---|---|---|
| Hobby | Free | No |
| Pro | $20/mo | Yes |
| Pro Plus | $60/mo | Yes |
| Ultra | $200/mo | Yes |
| Teams Standard | $40 a user a month | Yes |
| Teams Premium | $120 a user a month | Yes |
| Enterprise | Custom | Yes |
The plan is the entry fee. The agent's actual work is metered on top, and Cursor is unusually clear about how. Per the pricing docs, each plan includes a usage pool for third-party models "charged at the model's API price," with the option to pay for additional usage past the pool. The Cloud Agents page says the same thing from the other direction: Cloud Agents are charged at API pricing for the selected model.
Cursor even publishes an expectation, which very few vendors in this market do: its pricing docs put daily agent users at $60 to $100 a month of total usage. Read that as the plan plus the usage, for one person who leans on agents every day. It is a useful number for a budget.
The line that matters is on the team plans. From the same pricing docs: "On Teams and Enterprise plans, third-party model requests include a Cursor Token Rate of $0.25 per million tokens. This rate applies on top of model API pricing for included usage, on-demand usage, and BYOK usage."
So on Teams, every token the agent uses carries a quarter of a dollar per million on top of the provider's price, and the sentence says explicitly that this includes tokens bought with your own key. The fee is small and it is published, and it is still a per-token charge on a credential you brought yourself, which a CTO comparing invoices should know about.
On your own key more generally: Cursor supports custom API keys for OpenAI, Anthropic, Google, Azure OpenAI, and AWS Bedrock, and its API keys page says "custom API keys only work with chat models." Nothing on that page or the Cloud Agents page says a custom key runs a Cloud Agent. Treat it as unsupported until Cursor says otherwise.
What Cloud Agents are good at
The editor. Cursor is one of the best places to write code with a model, and Cloud Agents share its rules, its configuration, and its habits, so a task you hand off behaves like a task you would have done yourself in the same repository. You can be halfway through a change in the editor and send the rest to the cloud without leaving the window, and no standalone agent can offer that.
It is also one configuration. Rules, skills, hooks, and MCP servers are set up once and apply locally and in the cloud. A team that has already invested in Cursor's conventions gets its cloud agents for the price of a plan upgrade and no new vendor in the security review.
And the pricing is legible: at-cost model pricing, a published usage estimate, and usage you can cap. Compared with credit units and unpublished quotas elsewhere, that is a relief.
Where it stops
A subscription you already pay for does nothing here. If your developers hold Claude Max or ChatGPT plans, Cursor's usage pool cannot draw on them; the model bill is Cursor's and lands on Cursor's invoice at API price, plus the token rate on Teams. For a team that bought subscriptions precisely so the model line would be paid once, that is buying the same tokens twice.
There is no free way to try one on a real ticket, because Hobby excludes Cloud Agents. Cursor is entitled to that choice, and it is friction for someone who wants to see a pull request before asking for a card.
The GitHub issue path is a comment, not a handoff. A label or an assignment lets someone start work without composing anything; a mention asks them to write a prompt in the issue. It works, and it is a different gesture.
And the review loop wants a mention. A changes-requested review on its own does not, as far as the docs describe, send the agent back to work.
Who should use Cloud Agents
If your team writes code in Cursor, use them. The integration with the editor is the product, the pricing is honest, and the Linear assignment is as good as anyone's. Most people reading this should stop here.
If your backlog lives in GitHub Issues and you want a label-driven handoff, or your developers already pay for Claude or ChatGPT and you want those subscriptions to do the work, or you want the agent to act on a review without being asked, that is the gap. Those are the three things Sinatra does differently: a Sinatra label on a GitHub issue or an assignment in Linear, your key or your subscription running every hosted task with nothing added, and a follow-up commit from a changes-requested review. The seat is $20 per workspace member and the free tier is 5 tasks a day on your own key or subscription, no card. It has no editor, so for most teams it runs alongside Cursor rather than instead of it. The full comparison has the table and the sources, and the alternatives hub has the same table against ten other agents.
Common questions
Are Cloud Agents included in Cursor's free plan?
No. Hobby is free with limited agent requests and no cloud agents. Cloud Agents start on Pro at $20 a month.
Do Cloud Agents run on my own API key?
Cursor documents custom keys for chat models and does not say they cover Cloud Agents. On Teams and Enterprise, the $0.25 per million token rate applies to BYOK usage as well, per Cursor's pricing docs.
What is the difference between Cloud Agents and Bugbot?
Cloud Agents write code: they take a task and return a pull request. Bugbot reviews pull requests your team opens and flags bugs and security issues. They are separate products with separate pricing.
Can I start a Cloud Agent from a GitHub issue?
Yes, by commenting @cursor on the issue with what you want done. There is no label or assignee trigger; the comment is the prompt.
If you want to run the same tickets through both and compare the pull requests, Cloud Agents and Sinatra do not collide: one answers to @cursor and a Linear assignee, the other to a label and an assignee of its own. Start free and put your own key or subscription behind it, then read the two invoices side by side.