Run Cursor agents on MIOSA

What you're building

an AI code editor whose agents can also run in the background in the cloud Modelled on Cursor, by Anysphere.

Cursor is an editor with an agent that edits across a codebase; background agents work on tasks in a remote environment and report back.

Primitives you'll use: Sandbox

• Agent edits across a codebase
• Background agents on remote machines
• Review the result as a diff
• Run several agents at once

You install and run the real Cursor on MIOSA. Read the official docs first: cursor.com/docs/cli/overview. Every install command below comes from them; if the docs and this guide disagree, the docs win. Cursor is Cursor's command-line agent; installs with an official install script.

What you need on MIOSA

Each row is one thing to create before you start. The number matches the step that uses it.

1. 1 Organization and API key Scopes every call; a workspace key is all a worker needs. miosa api-key create app-key --preset agent Docs
2. 2 Sandbox The isolated Linux workspace the agent writes code and runs commands in. miosa create app-box --template nextjs --wait Docs
3. 2 A workspace per customer Isolates each customer’s machines, deployments, and data as they onboard. miosa workspace create customer-1 Docs
4. 2 Branding and white-label Your name and slug on previews, deployments, and the desktop; customers never see MIOSA. miosa org Docs
5. 2 Usage metering and bill-to Usage per customer, and which account pays for new machines. miosa org bill Docs

Architecture

How it runs on MIOSA

Where it runs -> a MIOSA sandbox (an isolated Linux workspace)

State and files -> Keep the repo in /workspace; a persistent sandbox keeps it across pauses. Without `--force`, print mode only proposes changes.

Model -> your own provider key, never a MIOSA platform key

Your customers -> one workspace each, isolated from each other

Auth and tenancy

Your organization is the platform; customers never get a MIOSA account, they sign into YOUR product. One workspace per customer, created as they onboard, isolates their machines, runs and data.

miosa workspace create cursor-customer-1

Tag every machine and run with the customer id in `metadata`, and never query across customers. Meter usage per customer with GET /api/v1/usage and set who pays with PUT /api/v1/bill-to (/docs/platform/usage-and-billing).

Install Cursor

Run these inside the sandbox (for example `miosa exec cursor-task-1 -- bash -lc '<command>'`), in order. The commands are from the official docs.

curl https://cursor.com/install -fsS | bash

Check: the install finishes without errors; the next sections configure and start it.

Configure

Authenticate for scripts with your own key: export CURSOR_API_KEY="..." (see the Cursor CLI authentication docs).

Model: Anthropic (Claude). Calls use my own provider key (entered in the tool's own setup); MIOSA platform keys are never used.

Run it

Start it and prove it works.

agent --version

Scripted, non-interactive use (what a product or a queue would call):

agent -p --force "add JSDoc comments to src/index.js"

agent -p --output-format stream-json "review the changes on this branch"

Check: a headless task completes and prints a result.

Persistence and access

Keep the repo in /workspace; a persistent sandbox keeps it across pauses. Without `--force`, print mode only proposes changes.

Check: after the machine pauses and resumes, the tool starts again with its state intact.

Make it a product

Run it per customer task in the customer's workspace as a worker behind your own task queue. It is not a built-in MIOSA harness, so install it in the machine and call it with `miosa exec`.

Limits and costs

Pin the version you tested and update deliberately; these tools change quickly.

Give the tool only the credentials it needs, as secrets, not baked into files.

Prototype: keep it to one machine at the default size, skip replicas and custom hostnames you do not need, and delete everything when you are done.

Acceptance checks

Cursor runs on a MIOSA sandbox and answers a real task.

State survives a pause and resume.

Each customer has its own workspace and its own instance; nothing is shared between them.

Everything it created can be deleted with nothing left running.

Next steps

• Agent prompt builder Pick a product shape and hand the brief to your agent.
• Run coding agents Run Claude Code, Codex or Cursor in the cloud, or build a product on them.
• Compare MIOSA How MIOSA compares to other sandbox and agent platforms.
• What you can build Every product pattern MIOSA supports.