Run Skyvern on MIOSA

What you're building

open-source browser automation that uses vision and a model to drive websites and complete workflows without brittle selectors Modelled on Skyvern, by Skyvern AI.

Skyvern reads a page with vision and a model, then acts on it (click, type, extract) to complete a multi-step workflow; the same workflow can be applied to a different site.

Primitives you'll use: Sandbox · Postgres

• Vision plus model control of a page
• Reusable multi-step workflows
• Structured extraction with schemas
• Handles 2FA and password managers
• Open source

You install and run the real Skyvern on MIOSA. Read the official docs first: github.com/Skyvern-AI/skyvern. Every install command below comes from them; if the docs and this guide disagree, the docs win. Skyvern is open source (AGPL-3.0).

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 Postgres Managed relational data, injected as DATABASE_URL in the machine and in production. miosa api POST /databases -d '{"name":"app-db","engine":"postgresql"}' Docs
4. 2 A workspace per customer Isolates each customer’s machines, deployments, and data as they onboard. miosa workspace create customer-1 Docs
5. 2 Branding and white-label Your name and slug on previews, deployments, and the desktop; customers never see MIOSA. miosa org Docs
6. 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 -> Workflows, runs and screenshots live in the database; keep the SQLite file or your managed Postgres reachable and the work survives a pause.

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

Its web port 8080 -> a MIOSA preview URL (`miosa preview create`)

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 skyvern-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 Skyvern

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

python3 --version   # Python 3.11 or later is recommended

pip install "skyvern[all]"

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

Configure

Add your own model key (OPENAI_API_KEY, ANTHROPIC_API_KEY or GEMINI_API_KEY) so Skyvern can reason about the page.

The pip path defaults to SQLite; point it at a managed Postgres with `skyvern quickstart --database-string=postgresql+psycopg://<user>:<pass>@<host>:5432/<db>` when you need one.

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.

skyvern quickstart

skyvern status

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

skyvern run server   # the API without the UI, for your own task queue

Check: a headless task completes and prints a result.

Persistence and access

Workflows, runs and screenshots live in the database; keep the SQLite file or your managed Postgres reachable and the work survives a pause.

It listens on port 8080. Run it as a background process so it outlives your shell, then open a preview:

miosa preview create skyvern-box 8080 --name web

Check: the preview URL answers, and still answers after the machine pauses and resumes (previews wake it on request).

Make it a product

One Skyvern instance per customer workspace (or a pool with a task queue) behind your own API keys; never expose the raw UI publicly.

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

Skyvern 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.