On this page

Agent devices

Devices are the machines agents use to do real work. MIOSA has three active device classes and one hosting target:

TypeProduct meaning
Sandbox WorkerIsolated code/file/build/preview/artifact workspace
ComputerPersistent cloud desktop/browser with screenshot and input APIs
Local Device / BYOC / OpenComputerPaired user-owned host for local files, apps, private network access, or customer-owned capacity
App EngineDurable app-container host after development is finished

App Engine is not where an agent edits code. It is where a verified sandbox-built app runs as a durable container.


Device selection

JobPick
Generate code, run tests, install packagesSandbox Worker
Build a Next.js previewSandbox Worker
Generate PDFs, DOCX, images, diagrams, chartsSandbox Worker
Browse a website, fill forms, login, click UIComputer
Screenshot visual QAComputer
Use a private VPN, local IDE, local files, customer desktop appLocal Device / BYOC / OpenComputer
Host many customer apps under one workspaceApp Engine

Sandbox vs computer vs BYOC/OpenComputer

Use this rule before adding complexity:

NeedRuntimeReason
The agent must create or edit code, run package managers, produce files, or serve a previewSandbox WorkerIt is a headless Linux workspace with stable /workspace state
The agent must see pixels, click UI, handle browser sessions, upload files, or collect screenshotsComputerIt exposes desktop/browser control and visual state
The agent must run near private data, private network services, local GPUs, desktop apps, or customer-owned hardwareBYOC / OpenComputerWork stays on the customer’s registered host and connects outbound to MIOSA
The output is ready for stable customer trafficDeployment or App EngineHosting is separate from the agent editing surface

A single run can use more than one runtime. For example, a sandbox can build an app, a computer can test the preview, and an OpenComputer can call a private internal service before the final artifact is exported.


How devices relate

The agent can switch devices during a run. For example, a sandbox writes a web app, a computer opens the preview and checks it visually, then the sandbox publishes the verified result.


Sandbox Worker

A sandbox is the normal runtime for coding agents.

Sandbox capabilities

  • persistent /workspace
  • file read/write/list/delete
  • Bash, Python, Node, package managers
  • long-running dev servers
  • public preview URLs
  • snapshots and forks
  • generated artifacts
  • deploy and App Engine publish prep
  • scoped environment variables and connectors

Use a sandbox to build products like app builders, artifact factories, research workspaces, evaluation runners, and code agents.


Computer

A computer is a full desktop/browser runtime.

Computer capabilities

  • screenshot
  • click, type, scroll, drag
  • clipboard
  • window control
  • browser sessions
  • visual QA
  • terminal and shell
  • persistent storage
  • embeddable desktop stream

Use a computer when the job requires a visible browser, GUI automation, manual handoff, or desktop-only software.


Local Device / BYOC / OpenComputer

A local device is a paired machine owned by the user or tenant. In MIOSA docs you will also see this path called BYOC or OpenComputers.

Use it when an agent needs:

  • local files that cannot be uploaded
  • private network access
  • installed desktop apps
  • local credentials that should not leave the machine
  • customer-controlled hardware
  • local GPUs or other host-specific capacity

Local devices are powerful but should be opt-in. The user should see exactly which workspace and agent can reach the device.


Primary device

Each workspace should have a primary device policy. Agents use it by default when a task does not specify a runtime.

Recommended primary-device policies:

Workspace typePrimary policy
App builderSandbox Worker
Browser automation workspaceComputer
Enterprise RPAComputer, with BYOC/OpenComputer fallback
Customer-owned coding workspacePersistent sandbox
Artifact factorySandbox Worker

The primary device can change over time, but historical runs should still record which device actually executed each action.


Persistence

Agent work should survive normal stops.

RuntimeExpected behavior
Persistent sandboxTimeout stops compute and preserves state for resume
Non-persistent sandboxTimeout destroys state
ComputerStop/start preserves filesystem and desktop state
BYOC/OpenComputerState stays on the customer-owned host unless the task exports it
App EngineApp keeps running as a deployment until stopped or replaced

For agent-building workflows, persistent sandbox should be the default. Use non-persistent only for one-off untrusted jobs where the filesystem should be discarded.


Activity and timeout

Active agent work should reset the idle clock:

  • exec calls
  • file writes
  • terminal input
  • preview traffic
  • browser/computer actions
  • artifact generation
  • deployment publish
  • explicit extend calls

The UI and CLI should warn before a device is paused or destroyed. Long-running workflows should create snapshots at stable checkpoints.


Device permissions

Device access should be explicit:

PermissionExample
devices:useRun commands or browser actions on an assigned device
devices:createCreate child sandboxes or computers
devices:destroyPermanently delete a device and saved state
devices:connect-localPair or use a local device
devices:set-primaryChange workspace default device policy
deployments:publishPromote workspace output to durable hosting

High-risk permissions should be gated by owner/admin roles or human approval.


Building virtual-device products

With these primitives, you can build products that look like an always-on agent workspace:

Workspace
  -> primary sandbox for code and files
  -> optional computer for browser/desktop
  -> connected accounts and managed connectors
  -> jobs and schedules
  -> artifacts and previews
  -> deployment targets

This supports products like:

  • 24/7 research agents
  • browser automation workers
  • AI app builders
  • cofounder-style task operators
  • artifact generation studios
  • agent teams with shared files
  • customer-owned coding workspaces

For Lovable/Replit/Genspark-style app builders, make the sandbox the primary device and attach a computer only for browser QA or login-heavy checks. For a Nebula-style virtual device, make the primary device visible in the UI so users understand whether the current work is happening in a sandbox, a computer, or a customer-owned OpenComputer.


Was this helpful?