Docs
Sign in Start building

Run Stagehand on MIOSA

~15 min TypeScript Python

What you’re building: Install the framework and run reliable browser automations on a computer.

Primitives you’ll use: Computer

Agent prompt

Start with your coding agent

Choose how you will use it. The brief installs and runs the real tool on MIOSA, then shapes it for your team or your customers. Copy it into OSA, Claude Code, Codex, or Cursor.

Template coming soon

1 What are you building?

Leave it empty and your agent will propose 3 names, pick one, and use it for resources, the domain and branding.

3 Configure

Model
Scale
Extras

4 Your prompt

Reference tool

Stagehand, by Browserbase (https://www.browserbase.com/stagehand): an AI browser-automation framework with act, extract and observe primitives.

How it works: Stagehand mixes code with natural-language steps: you call act/extract/observe against a page and it uses a model to find elements and perform actions reliably.

Key capabilities:

Natural-language act, extract and observe

Mixes with normal automation code

Reliable, repeatable browser flows

Works against cloud or local browsers

You will install and RUN the real Stagehand (open source (Browserbase)). Read its docs first: https://docs.stagehand.dev/v4/first-steps/quickstart. Every install command below comes from them; if the docs and this brief disagree, the docs win.

How it runs on MIOSA

Where it runs -> a MIOSA computer (a persistent desktop with a browser)

State and files -> Scripts live in /workspace on the computer.

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

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

Goal

Install and run Stagehand on a MIOSA computer, so it can serve my customers. Each customer is isolated in its own workspace; I meter usage and bill them.

Product name: propose 3 product names, pick one, and use it for resource names, the domain and branding. Until you pick, <product-name> stands for it in the commands below.

Scale: a prototype.

Set up

npm i -g @miosa/cli

miosa login && miosa whoami

miosa api-key create <product-name>-key --preset agent

export MIOSA_API_KEY="msk_u_..."

miosa org

Resources

Computer: a persistent Linux desktop with a browser

miosa computer create <product-name>-desktop

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 <product-name>-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 Stagehand

Run these inside the computer (its terminal), in order. The commands are from the official docs.

pnpm add @browserbasehq/stagehand 'zod@~4.4.3' # Python: pip install stagehand

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

Configure

Local runs need Chrome, which a MIOSA computer has. Export your own model key as the quickstart describes.

Model: Anthropic (Claude). Calls use my own provider key (ANTHROPIC_API_KEY); MIOSA platform keys are never used.

export ANTHROPIC_API_KEY="..." # set it in the process environment, or the Secrets API; never write it into files you commit

Run it

Start it and prove it works.

pnpm tsx automation.ts # your script using act, extract and observe

Check: the tool starts without errors and responds.

Persistence and access

Scripts live in /workspace on the computer.

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

Make it a product

Run each customer's automation on its own computer in the customer's workspace.

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

Stagehand runs on a MIOSA computer 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.

What your choices added

  • Build a product. a workspace per customer, per-customer metering and bill-to
  • Agent suggests a name. proposes 3 product names and picks one; commands use <product-name>
  • Model: Anthropic. your own provider key
  • Prototype. one small machine, no extras, easy to delete

What you're building

an AI browser-automation framework with act, extract and observe primitives Modelled on Stagehand, by Browserbase.

Stagehand mixes code with natural-language steps: you call act/extract/observe against a page and it uses a model to find elements and perform actions reliably.

Primitives you'll use: Computer

  • Natural-language act, extract and observe
  • Mixes with normal automation code
  • Reliable, repeatable browser flows
  • Works against cloud or local browsers

You install and run the real Stagehand on MIOSA. Read the official docs first: docs.stagehand.dev/v4/first-steps/quickstart. Every install command below comes from them; if the docs and this guide disagree, the docs win. Stagehand is open source (Browserbase).

What you need on MIOSA

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

  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. Computer A persistent Linux desktop for browser, mouse, and screenshot work. miosa computer create app-desktop Docs
  3. A workspace per customer Isolates each customer’s machines, deployments, and data as they onboard. miosa workspace create customer-1 Docs
  4. Branding and white-label Your name and slug on previews, deployments, and the desktop; customers never see MIOSA. miosa org Docs
  5. 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 computer (a persistent desktop with a browser)

State and files -> Scripts live in /workspace on the computer.

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 stagehand-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 Stagehand

Run these inside the computer (its terminal), in order. The commands are from the official docs.

pnpm add @browserbasehq/stagehand 'zod@~4.4.3'   # Python: pip install stagehand

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

Configure

Local runs need Chrome, which a MIOSA computer has. Export your own model key as the quickstart describes.

Model: Anthropic (Claude). Calls use my own provider key (ANTHROPIC_API_KEY); MIOSA platform keys are never used.

export ANTHROPIC_API_KEY="..."   # set it in the process environment, or the Secrets API; never write it into files you commit

Run it

Start it and prove it works.

pnpm tsx automation.ts   # your script using act, extract and observe

Check: the tool starts without errors and responds.

Persistence and access

Scripts live in /workspace on the computer.

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

Make it a product

Run each customer's automation on its own computer in the customer's workspace.

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

Stagehand runs on a MIOSA computer 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

Was this page helpful?