Cloud Agents
- Desktop, mobile and web
- Free, Plus, Pro
What it does
A cloud run is a job, not a remote session: a throwaway machine clones your repository from its remote, runs Claude Code or Codex headless on your prompt, commits, pushes a branch, writes a report and destroys itself. Your own computer can be off; the meeting point is git. What comes back is code and a written account, never the agent's memory, so you review the work and pick one of three actions: get the branch, run again in the cloud with an extra instruction, or continue locally in a normal agent with the task, report and branch pre-loaded. Because it reads the AgentsRoom API rather than your desktop, the phone can start a cloud run from a backlog ticket with every computer you own switched off, and your CI/CD takes the pushed branch from there.
Where to find it
- Inside a project, the agents list has a Cloud group with New cloud run; each run shows its status (Queued, Running, Ready to review, Nothing to change, Failed, Timed out, Cancelled) and opens in the central panel as a conversation, laid out exactly like a local agent's conversation view: the agent's full messages, and each tool call with what it ran on (the shell command, the file edited, the search query), plus the report. Since 2026-10-01 the panel looks like a local agent's: the same header (the run's avatar with a small cloud badge, the task as its name, Cloud agent as its role, provider, model and account in the model pill, then status, files, duration and branch), the agent's face on its messages, the report as its own collapsible block after the conversation (open by default), and the bottom of the panel always where the composer sits: the composer while the machine accepts messages, then a bar with the three closing actions.
- On a backlog ticket, next to Start (this computer), the cloud icon starts it in the cloud (its tooltip reads "Start this task on a cloud machine"); the agent menu has The cloud next to Launch agent (greyed with a reason: Claude and Codex only, not a git repository, no git remote).
- Mobile: a Cloud screen ("Agents running on throwaway machines") lists runs by project, plus Start in the cloud from a ticket or a free prompt.
- Setup lives in the Cloud agents card of Settings > Account (agent credential, repository access, and Your own Fly.io account).
- The New agent menu has a Cloud agent entry in the group of agents that work without you.
How to use it
First run only, a one-time setup ("Cloud agents are not set up yet" > Set it up now):
-
Agent credential: give the account a Label ("Personal, Work, Client A..."), then Create the token opens a short sign-in in your browser and mints an automation token for the agent, separate from your keychain login and revocable on its own. The account the token stands for is the one you sign in with in that browser window, not a profile of the desktop app. Codex has no such command: paste an API key. You can save several accounts per agent: the card lists them ("N accounts saved", label, provider, masked token, Remove the token) and an empty label takes the provider's name.
-
Repository access: a token for the host your repository lives on. AgentsRoom reads the host from the project's own git remote, writes the instructions for that family, and offers Open the token page pointing at your instance, not at a domain it guessed: GitHub (a fine-grained token with Contents: Read and write), GitLab and self-hosted GitLab (
write_repository), Bitbucket (Repositories in read and write), Gitea, Forgejo and Codeberg (the repository permission in Read and Write), OneDev (Read/Write Code), and any other https server, where you are simply asked for a token that can read and write the repository. Fill Host, Token, and User name when the form says it is required by this host: GitHub accepts any user name, GitLab usesoauth2, and Bitbucket, Gitea, OneDev and unknown forges need the login of the account the token belongs to. Test the access tells you whether it can clone and push. -
Your own Fly.io account (optional at first, required once your free minutes are spent): create an account on fly.io, type an App name, run the two commands the block shows (
fly apps create <app>, thenfly tokens create deploy -a <app>), paste the whole token (it starts withFlyV1) and click Connect. AgentsRoom asks Fly whether the token opens that app before saving anything. Use a dedicated, empty app, in a personal Fly organization.
Then, per run:
- New cloud run or the cloud icon on a ticket. Write What should the agent do (or let the ticket fill it), pick the Agent (Claude or Codex) and Model. When that agent has two or more saved accounts, an Account row appears between them with one pill per label; with a single account the row is not shown. The preselected account is the oldest one you saved, and switching agent resets the choice.
- Branch: Dedicated branch (default, the agent pushes its own branch) or Current branch (commits onto the branch it started from; refused on a protected branch).
- Attach a file if useful: up to four screenshots, sketches or logs, copied to the machine and destroyed with it.
- Pick the Machine when you have a Fly.io account connected: AgentsRoom (your free or included minutes) or your Fly.io account (billed by Fly at cost). Read "What this run spends" (included minutes used this month, free minutes left, the maximum duration), then start. A "Before your first cloud run" note is shown once.
- When the notification arrives (its title is the run title followed by the project name, its body "Ready to review on <branch>"), open the run: Get the branch checks it out locally, Run again in the cloud relaunches, Continue here opens a local agent with the handover pre-filled. While it runs, you can reply to the agent in the run's view (it resumes the same session, and every step is pushed as it ends); End session lets it push and shut down now. Cancel run stops a run in flight; Remove run deletes a finished one. The run detail names the Account it ran with, and keeps that name even after the token is removed.
Settings
cloudRunIdleTimeoutMinutes(global, synced with the account, default 15): Settings > Account > Cloud agents > Wait for your reply, pills 5 / 15 / 30 / 60 min (any whole minute from 5 to 60 over MCP). How long a cloud machine waits for your reply after each step of the agent before it pushes the work and shuts down. Read by the server when a run starts, so it also applies to runs started from the phone; changing it does not affect a run already in flight.cloudRunIntroSeen(global, internal): whether the one-off explanation before the first cloud run was confirmed; set it back to false to see it again.
Agent tools (MCP)
None.
Providers
Claude and Codex only, on the cloud machine. A ticket pinned to another provider is run on a supported one and the launch sheet says so ("This ticket runs on X, which has no cloud harness").
Mobile
Present, and it is where the feature earns its place: runs listed by project, run detail with events and report, start from a ticket or a free prompt, cancel, and a push when a run ends that opens the detail. The same ACCOUNT chips appear in the start sheet when an agent has two or more accounts, and the run detail shows the Account; adding or removing accounts is desktop only ("Accounts are added from the desktop app, in Settings > Account > Cloud agents"). The start sheet also has the Machine chips once a Fly.io account is connected; connecting one is done on the desktop, where the fly commands run. The phone words allowances as "your account" and never names a plan. The diff itself is reviewed on the desktop.
Limits
- Open to every signed-in account. Every account gets 60 free minutes once to try it; Plus includes 150 minutes a month and Pro 1,200, spent before the free minutes. Runs on AgentsRoom machines are counted in minutes of machine time (at least one minute per run).
- After that, runs go on your own Fly.io account: Fly bills you directly, at cost (about $0.03 per hour of machine). AgentsRoom resells no compute and takes no margin, so there are no minutes to buy. Without minutes left and without a Fly.io account, the cloud is blocked until you connect one.
- Every run has a maximum duration of agent work (waiting for your reply is not counted; 60 minutes on your own Fly.io account) and each plan a cap on concurrent runs, wherever the machine lives; "Too many runs at once" means wait or run the task locally.
- The machine only sees what you pushed: uncommitted changes, local commits, ignored files, your database and your
.envdo not exist for it. It can ask you a question between two steps, but the machine only waits a few minutes for the answer, so a scoped ticket is still a far better brief than a hurried line. - Never force-pushes, never writes to a protected branch (
main,master,develop,productionin Current branch mode). - No live terminal on a cloud agent: you reply between two of its steps, you do not type into its console. No session migration, no sharing of a run between accounts. The project must be a git repository with a remote.
- Saved agent accounts are capped per AgentsRoom account ("You already have the maximum number of accounts. Remove one first."). Removing a token does not touch the runs it produced.
- Running on the provider's own cloud (Claude Code on the web, Codex Cloud) is not offered: a cloud run rents a machine on AgentsRoom's account or on your own Fly.io account. Only Fly.io is supported as your own cloud for now.
Common questions
- Do my agents still run locally? Yes, by default. The cloud is a per-run choice, task by task.
- Can I really start an agent with my computer off? Yes, from the phone: the mobile app reads the API and the run happens on a rented machine.
- What comes back? A pushed branch with real commits and a report; not a resumable session.
- Is my code safe on that machine? The machine is dedicated to one run and destroyed with its clone and attachments; git credentials are held per host and never handed to the agent as text.
- How does it fit my CI/CD? It pushes an ordinary branch; whatever your pipeline does on a push happens as usual.
- I have several Claude accounts, which one does a cloud run use? The one you pick in the Account row of the launch dialog, when at least two are saved for that agent; otherwise the only one, or the oldest saved. Adding a second account never changes what already runs.
- Can I see the commands a cloud agent ran? Yes. Each tool row shows its argument (the command, the file, the query), on the desktop and on the phone. Runs recorded before 2026-09-30 only show the tool names.
- Can I send a message to a cloud agent while it works? Yes. While the machine is up, the run's view has the same composer as a local agent (the reply bar on the phone). The agent reads your message when its current step ends; if it is already waiting ("Waiting for your reply"), it resumes at once. Attachments cannot be sent during a run.
- What happens if I do not reply? After each step the machine waits for your reply (15 minutes by default), then pushes the work, writes its report and shuts down. End session does the same right away. Waiting for you is not billed and does not count against the run's maximum duration; a session can hold up to 2 hours of waiting in total.
- Can I make the machine wait longer for my reply? Yes: Settings > Account > Cloud agents > Wait for your reply (5, 15, 30 or 60 minutes). It applies to the next runs, including those started from the phone.
- Why was my cloud run refused with "This token can clone but not push"? Before starting the machine, AgentsRoom runs the same check as Test the access on the access the machine would use. A token that is rejected, cannot see the repository, or can clone but not push is refused right there, before anything is billed, instead of failing inside the machine. Fix the token's permissions (write access to the repository), then start the run again. A host that does not answer the check does not block the run.
- Can a cloud run use a precise model version, such as Opus 4.8? Yes. The version picked in the Model row is translated into the exact model id the CLI expects, the same way as for a local agent. Before 2026-11-08 such a run failed after about twenty seconds on "model not found".
- Do you charge for cloud compute? No margin, ever. You try with 60 free minutes (plus your monthly minutes on Plus and Pro); after that the machine runs on your own Fly.io account and Fly bills you directly, at cost, about half a cent for a ten-minute run. AgentsRoom does not sell minutes.
- Can I buy more cloud minutes? No. Connect your own Fly.io account in Settings > Account > Cloud agents > Your own Fly.io account: there is nothing to buy from AgentsRoom.
- My free cloud minutes are used up, what now? Connect your Fly.io account ("Connect my Fly.io account" in the window that opens), then start the run again with your Fly.io account as the Machine. Upgrading to Plus or Pro also adds monthly minutes.
- Fly.io refused my token, why? Paste the whole token printed by
fly tokens create deploy -a <app>(it starts withFlyV1), created for the same app name. "Secrets named like the variables AgentsRoom sets" means the app is not empty: use a dedicated app. - Can I remove my Fly.io account? Yes, from the same block, once no cloud run is using it ("A cloud run is still using this account. Stop it first.").
- Does a cloud run use my desktop Claude profiles? No. A cloud account is a token minted by signing in during Create the token; the multi-account profiles of the desktop app play no part.
Related
- Backlog Task Board and Public Remote Backlog: the natural source of cloud runs.
- Mobile Companion: the remote control of the chain.
- Plans and Pricing: included minutes per plan.
- Remote Fleet: agents on your other machines, which do need those machines on.
- Multiple Accounts: the desktop Claude profiles, separate from cloud accounts.