Docs
Sign in Start building

Run OpenHands on MIOSA

~15 min TypeScript Python

What you’re building: Install the open-source software agent; the sandbox is its workspace.

Primitives you’ll use: Sandbox

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

OpenHands, by All Hands AI (https://all-hands.dev): an open-source software-engineering agent that works in a sandboxed workspace.

How it works: OpenHands runs an agent loop that edits files, runs commands and browses inside a sandboxed runtime, driven by a task description.

Key capabilities:

Open-source SWE agent

Sandboxed runtime for commands and files

Works on GitHub issues and tasks

Bring your own model

You will install and RUN the real OpenHands (open source (the Agent Canvas front end and agent server)). Read its docs first: https://github.com/OpenHands/OpenHands. 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 sandbox (an isolated Linux workspace)

State and files -> State lives under `~/.openhands`; a persistent sandbox keeps it across pauses. Keep project folders under /workspace.

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

Its web port 8000 -> a MIOSA preview URL (`miosa preview create`)

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

Goal

Install and run OpenHands on a MIOSA sandbox, 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

Sandbox: the agent's isolated Linux workspace

miosa create <product-name>-task-1 --wait

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 OpenHands

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

node --version # Node.js 24 or later is required

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

npm install -g @openhands/agent-canvas

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

Configure

Open the UI, add an LLM profile in Settings, and paste your own provider key. The MIOSA sandbox is already the isolation boundary, so use the "without a Docker sandbox" mode the README describes.

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-canvas

Check: the tool starts without errors and responds.

Persistence and access

State lives under `~/.openhands`; a persistent sandbox keeps it across pauses. Keep project folders under /workspace.

It listens on port 8000. Run it as a background process so it outlives your shell, then open a preview:

miosa preview create <product-name>-task-1 8000 --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

Run one OpenHands sandbox per customer workspace and put your own auth in front of the preview URL; never expose an unauthenticated agent server.

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

OpenHands 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.

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 open-source software-engineering agent that works in a sandboxed workspace Modelled on OpenHands, by All Hands AI.

OpenHands runs an agent loop that edits files, runs commands and browses inside a sandboxed runtime, driven by a task description.

Primitives you'll use: Sandbox

  • Open-source SWE agent
  • Sandboxed runtime for commands and files
  • Works on GitHub issues and tasks
  • Bring your own model

You install and run the real OpenHands on MIOSA. Read the official docs first: github.com/OpenHands/OpenHands. Every install command below comes from them; if the docs and this guide disagree, the docs win. OpenHands is open source (the Agent Canvas front end and agent server).

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. Sandbox The isolated Linux workspace the agent writes code and runs commands in. miosa create app-box --template nextjs --wait 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 sandbox (an isolated Linux workspace)

State and files -> State lives under `~/.openhands`; a persistent sandbox keeps it across pauses. Keep project folders under /workspace.

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

Its web port 8000 -> 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 openhands-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 OpenHands

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

node --version   # Node.js 24 or later is required
curl -LsSf https://astral.sh/uv/install.sh | sh
npm install -g @openhands/agent-canvas

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

Configure

Open the UI, add an LLM profile in Settings, and paste your own provider key. The MIOSA sandbox is already the isolation boundary, so use the "without a Docker sandbox" mode the README describes.

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-canvas

Check: the tool starts without errors and responds.

Persistence and access

State lives under `~/.openhands`; a persistent sandbox keeps it across pauses. Keep project folders under /workspace.

It listens on port 8000. Run it as a background process so it outlives your shell, then open a preview:

miosa preview create openhands-task-1 8000 --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

Run one OpenHands sandbox per customer workspace and put your own auth in front of the preview URL; never expose an unauthenticated agent server.

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

OpenHands 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

Was this page helpful?