Run Browser Use on MIOSA

~15 min TypeScript Python

What you’re building: Install the open-source library and let an agent drive a real browser.

Primitives you’ll use: Computer, Sandbox

Agent prompt

Start with your coding agent

A few quick questions, then copy a prompt for any coding agent.

Who is it for?

Pick one to start. The rest adapts to it.

For my company Internal. One organization, a workspace per team, SSO. No billing. Build a product For customers. A workspace per customer, isolation, metering and billing.

What you're building

an open-source library that lets an AI agent drive a real browser Modelled on Browser Use, by Browser Use.

You give the library a task and a model; it controls a Chromium browser (pages, clicks, forms, extraction) in a loop until the task is done.

Primitives you'll use: Computer · Sandbox

An agent that drives a real browser
Extracts structured data from pages
Works with your choice of model
Open source and embeddable

You install and run the real Browser Use on MIOSA. Read the official docs first: docs.browser-use.com. Every install command below comes from them; if the docs and this guide disagree, the docs win. Browser Use is open source Python library.

What you need on MIOSA

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

Organization and API key Scopes every call; a workspace key is all a worker needs. miosa api-key create app-key --preset agent Docs
Computer A persistent Linux desktop for browser, mouse, and screenshot work. miosa computer create app-desktop Docs
Sandbox The isolated Linux workspace the agent writes code and runs commands in. miosa create app-box --template nextjs --wait Docs
A workspace per customer Isolates each customer’s machines, deployments, and data as they onboard. miosa workspace create customer-1 Docs
Branding and white-label Your name and slug on previews, deployments, and the desktop; customers never see MIOSA. miosa org Docs
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 and outputs live in /workspace on the computer; browser profiles persist with 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 browser-use-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 Browser Use

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

curl -LsSf https://astral.sh/uv/install.sh | sh

python3 --version   # Python >= 3.11 is required

uv init --python 3.12

uv add browser-use

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

Configure

Put your own model key in `.env` (the README example uses OPENAI_API_KEY). A MIOSA computer already has a desktop and Chrome for the agent to drive; use Browser Use's cloud browser only if you choose to.

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.

uv run agent.py   # the README's agent.py with your task

Check: the tool starts without errors and responds.

Persistence and access

Scripts and outputs live in /workspace on the computer; browser profiles persist with the computer.

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

Make it a product

One computer per customer workspace; a queue in front; results and screenshots stored per customer.

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

Browser Use 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.