Configure one Cloud Agent, point it at a repo, optionally add environment variables, and click Set up environment. Once it shows "Active", teammates who can manage documents can ship a Brief or Task from the cloud, in parallel, without anyone's laptop in the loop.
A Cloud Agent is a saved environment for delivery: your repositories, environment variables, and build and test commands. The AI works from your Brief, its Technical Spec, and the Plan's tasks. When a teammate chooses Hamster Cloud to deliver, the agent runs the work and publishes its changes to the connected code host.
Cloud Agents complement the IDE flow rather than replacing it. Most engineers ship from their IDE using the Hamster plugin — they want control. Cloud Agents are the path for deliveries that don't need an engineer at the keyboard: a PM clicking Deliver on a Brief, Routines running scheduled work, or parallel deliveries across the Team.
To set up a Cloud Agent, give it a name, add one or more repositories, and click Set up environment:
Name it and attach repositories — Click New, name the environment, and add the repositories offered by the picker. To deliver a Brief from a connected GitLab or Cursor Origin repository, choose Hamster Cloud in Delivering Briefs.
Set up environment — Hamster works out the Install, Build, Test, and Run commands itself, then checks them in a fresh sandbox. Progress shows as Preparing your environment, Setting things up, Checking everything works, and Saving your environment.
Provide credentials if asked — If setup needs a value from outside your workspace, it pauses with Setup needs a credential. Values are stored encrypted and never shown again.
Review or edit later — Open Advanced setup to see or change the saved commands. Deliveries boot from the saved environment instead of repeating setup.
After setup completes, the Cloud Agent shows Active and is ready to deliver. You can configure multiple repositories and multiple Cloud Agents for different parts of your codebase.
Open an active Agent at any time to review its environment variables and saved Install, Build, Test, and Run commands in one place.
Each Cloud Agent shows its current status:
If a build fails, the row shows the error summary. Open the Agent to inspect it.
The list updates live, so you can save a config and watch the pill change without refreshing.
Env vars are encrypted at rest and never exposed in the UI after they're saved. You can paste:
.env blob — comments, blank lines, and export prefixes are tolerated..env overrides the prior value cleanly.Vars are scoped to the Cloud Agent and made available to the sandbox at Delivery time.
You can run as many Cloud Agents as your team needs. Common patterns:
Two Briefs targeting different Agents deliver in parallel without contention. Two Briefs targeting the same Agent each get their own sandbox, also in parallel, booted from the shared snapshot.
Hamster Cloud works from:
Put your requirements and constraints in the Brief and Plan so the agent can use them while implementing the change.
Hamster Cloud can run deliveries with Cursor CLI using Grok 4.7 High Fast.
This is separate from Cursor Cloud and OpenAI Agents delivery. Cursor Cloud Agents run in Cursor's hosted environment, OpenAI Agents run in OpenAI's hosted sandbox, and Cursor CLI runs inside the Hamster Cloud sandbox. The Cursor Cloud repository list only includes GitHub repositories the connected Cursor account can reach. Cursor Cloud and OpenAI Agents deliver only to GitHub repositories. Use Hamster Cloud to open a merge request on GitLab or a pull request on Cursor Origin.
Each Delivery moves through a set of states Hamster tracks and displays:
Only one Delivery can be active for a given Brief at a time. Wait until the current run finishes, or stop it, before starting a separate delivery.
If a Cloud Agent you set up manually stops booting cleanly — bad commit, broken dependency, stale snapshot — right-click the Agent in the list and click Reset environment. Hamster boots a fresh sandbox and sets the Agent back to Pending. When it shows Active again, it has a fresh snapshot. Agents Hamster set up itself don't offer Reset environment; change their commands in Advanced setup instead.
Reset is the right move when:
When a Cloud Agent opens a pull request, it creates commits with the following properties:
Commit verification depends on the code host and environment. Check the verification status on your code host before merging. Commit verification is not configurable per workspace.
Configuring Cloud Agents requires permission to manage environments, while delivering a Brief requires permission to manage documents. Owner, Admin, and Creator roles can deliver; Reviewers cannot. For sensitive environments, limit access to the roles that should configure or launch work.
Cloud Agents are available on Team and Enterprise plans. If your workspace is on the free plan, choosing Hamster Cloud from Deliver, or creating or opening a Cloud Agent, shows an option to upgrade. Cursor Cloud and OpenAI Agents deliver only to GitHub, so delivering to GitLab from the cloud needs one of these plans.
The Team plan now starts at a single seat — there's no creator minimum. See the pricing page for current rates.
Cloud Agents and the IDE flow (the Hamster plugin) are two paths to the same destination — a PR in your repo from a Brief. Use whichever fits the situation:
Most teams use both. The Hamster plugin for individual engineers; Cloud Agents for everything else.
.env source of truth somewhere stable (1Password, a secrets manager). Re-paste into the Cloud Agent any time the source changes; the parser handles re-paste cleanly.