--- title: "What you can build with MIOSA" description: "Concrete product patterns for MIOSA sandboxes, computers, agent runtimes, generated artifacts, previews, and deployments." last_updated: 2026-10-23 url: https://miosa.ai/docs/use-cases --- # What you can build with MIOSA MIOSA is the infrastructure underneath AI products. Your product, or your agent, gets real machines and real URLs: - **Sandboxes** for code, files, builds, and previews. - **Computers** for browsers and full desktops, with human handoff. - **Agents** you dispatch, stream, and collect artifacts from. - **Deployments and Docker Host** for immutable releases on stable URLs, with custom domains and rollback. - **Platform features** for white-label products: organizations, workspaces, scoped keys, domains, and usage metering. ```text User request -> agent plans work -> sandbox does code, files, builds, tests, artifacts -> computer does browser, desktop, screenshots, manual-style tasks -> MIOSA streams events and previews -> deployment ships the finished app ``` MIOSA is not just a remote shell. It is the execution layer for products that need AI agents to do real work safely. ## Browse the Build gallery Every product shape below has a step-by-step guide in the [Build gallery](https://miosa.ai/docs/build.md): the primitives you need, an architecture diagram, six steps from API key to custom domain, and a prompt you can hand to your coding agent. - [AI app builders](https://miosa.ai/docs/build.md#bg-app-builders): Lovable, Bolt, v0, Replit-style: prompt to a deployed app. - [Run coding agents](https://miosa.ai/docs/build.md#bg-run-coding-agents): Claude Code, Codex, Cursor in the cloud. - [Autonomous agents](https://miosa.ai/docs/build.md#bg-autonomous-agents): Agents with their own machine that finish work. - [Browser and computer-use agents](https://miosa.ai/docs/build.md#bg-browser-computer-agents): Agents that drive a real browser or desktop. - [AI chat and companions](https://miosa.ai/docs/build.md#bg-chat-companions): Assistants and always-on companions. - [Answer engines](https://miosa.ai/docs/build.md#bg-answer-engines): Research products that cite their sources. - [Multi-agent](https://miosa.ai/docs/build.md#bg-multi-agent): One request, many agents in parallel. - [Voice agents](https://miosa.ai/docs/build.md#bg-voice-agents): Agents that talk and act on calls. - [AI design tools](https://miosa.ai/docs/build.md#bg-design-tools): Prompt to a designed UI or asset. - [AI video and creative](https://miosa.ai/docs/build.md#bg-video-creative): Generate, edit, and produce media. - [Vertical AI apps](https://miosa.ai/docs/build.md#bg-vertical-ai): Agents for a specific industry workflow. - [Internal tools](https://miosa.ai/docs/build.md#bg-internal-tools): A company OS where agents, apps, and data live together. --- ## Builders and developers - **Prompt-to-app builders**: Lovable and v0-style products where an agent turns a prompt into a live app, then fixes and republishes it. `Sandbox` `Preview` `Deployment` [Start here: build a Lovable-style app](https://miosa.ai/docs/build/lovable.md) - **Coding agents in sandboxes**: Run Claude Code, Codex, or OSA inside a persistent sandbox with the files, packages, and shell a real repo needs. `Sandbox` `Agent runs` `Snapshots` [Start here: run coding agents](https://miosa.ai/docs/build/run-agents.md) - **Code execution products**: Run untrusted user code in an isolated microVM, stream stdout, and collect the artifacts it produces. `Sandbox` `Events` `Artifacts` [Start here: streaming code execution](https://miosa.ai/docs/cookbook/streaming-code-execution.md) - **Evaluation and benchmarking harnesses**: Run repeatable evals and benchmark bursts on real runtimes, with per-run evidence instead of mocks. `Sandbox` `Benchmarks` `Events` [Start here: evaluations](https://miosa.ai/docs/evaluations.md) and [benchmarks](https://miosa.ai/docs/benchmarks.md) ## Agent product teams - **Always-on agents with their own computer**: dots and Grok Bot-style agents that keep a device, files, a browser, and long-running jobs across sessions. `Sandbox` `Computer` `Agent devices` [Start here: agent devices](https://miosa.ai/docs/guides/agent-devices.md) - **Browser automation agents**: Browser use runs inside every sandbox: an agent drives a real browser over CDP while a human can watch. `Sandbox` `Browser use` `Live viewer` [Start here: browser use](https://miosa.ai/docs/browser-use.md) - **Desktop and computer-use agents**: Agents that screenshot, click, and type on a durable Linux desktop, with human takeover when they get stuck. `Computer` `Computer use` `Embedding` [Start here: computer use](https://miosa.ai/docs/computer-use.md) ## Platform and agency teams - **White-label agent platforms**: Lumen-style platforms with your brand, your domains, and your end users, while MIOSA runs behind them. `Org and workspaces` `Branding` `Attribution` [Start here: Platform builder guide](https://miosa.ai/docs/platform/overview.md) - **Agency client platforms**: Northwind-style agencies that give each client an isolated workspace, build their apps, and hand over domains. `Multi-tenant` `Quotas` `Custom domains` [Start here: Platform builder guide](https://miosa.ai/docs/platform/overview.md#northwind-agency-client-work) - **Internal Business OS for teams**: An Acme Corp-style internal platform where your team agents, apps, and data live together on MIOSA. `Sandbox` `Connectors` `Data` [Start here: internal Business OS](https://miosa.ai/docs/build/business-os.md) ## Infrastructure and enterprise - **Bring-your-own machines**: OpenComputers enrolls machines you own so agents can run commands and files on your own hardware. `OpenComputers` `Hosts` `Meshes` [Start here: OpenComputers](https://miosa.ai/docs/opencomputers.md) - **Enterprise data with Fractal**: Fractal gives enterprise data a governed home, so agents work against your systems with the right controls. `Fractal` `Data` `Governance` [Start here: Fractal enterprise data](https://miosa.ai/docs/data/fractal.md) > **Note: Capability labels matter** > > MIOSA can host the application, data, workflow, customer boundary, and deployment for these products today. > Specialized model and media execution may use connected providers. > Managed GPU execution and customer-cloud placement remain gated until the availability page marks them shipped. > See [Availability and roadmap](https://miosa.ai/docs/availability.md). --- ## Product primitives | Primitive | Use it for | Not for | |---|---|---| | **Sandbox** | Code, files, commands, package installs, builds, tests, generated artifacts, preview servers | GUI/browser interaction | | **Computer** | Browser automation, screenshots, mouse/keyboard, desktop apps, visual QA, user handoff | Headless code builds that do not need a desktop | | **Deployment** | Stable public app/site/API URLs, versions, releases, rollback | Active development iteration | | **Docker Host** | Many customer apps running as isolated containers on one workspace Docker Host host | Generic sandbox development | | **Artifacts** | Files created by agents: PDFs, docs, images, reports, exports, screenshots | Hidden temporary state | | **Events** | Real-time UI updates: tool calls, stdout, file writes, preview readiness, deployment status | Long-term storage | ## Build an agent-company product Several modern AI products package the same high-level pattern: an agent, a persistent workspace, connected apps, a browser or cloud device, jobs, files, and generated deliverables. MIOSA exposes those primitives directly, so you can build your own version inside your product. ```text Your product UI -> agent configuration -> device policy -> sandbox/computer/local device -> connected accounts and managed connectors -> streamed tool calls and events -> files, artifacts, previews, jobs, and deployments ``` | Product shape | MIOSA primitives | |---|---| | Always-on virtual device | Persistent sandbox or computer, primary device policy, snapshots, jobs | | Agent team | Orchestrator, child sandboxes, child computers, shared artifacts, event stream | | Mini-app builder | Next.js sandbox, preview URL, artifact panel, publish flow | | Operator agent | Browser computer, connected apps, schedules, approvals, memory | | Design/research agent | Web research, a managed research connector, files, browser screenshots | | 24/7 monitoring job | Scheduled trigger, persistent device, app connector, notifications | The important architecture point is that the agent should work in a MIOSA device. The local CLI, MCP client, or your backend orchestrates, but files, commands, browser actions, previews, and artifacts live in the assigned runtime. See [Build an agent-company platform](https://miosa.ai/docs/guides/build-agent-company.md), [What MIOSA agents can do](https://miosa.ai/docs/guides/agent-capabilities.md), [Agent devices](https://miosa.ai/docs/guides/agent-devices.md), and [Agent orchestration](https://miosa.ai/docs/guides/agent-orchestration.md) for the full model. > **Tip: Default agent loop** > > For AI coding products, the default loop should be sandbox-first: create or > resume a sandbox, write files inside `/workspace`, run commands inside the > sandbox, show the preview, snapshot progress, then publish. --- ## Example: generated app builder ```mermaid sequenceDiagram participant User participant Product as Your product participant Agent participant S as MIOSA Sandbox participant D as MIOSA Deploy User->>Product: Build a landing page for my customer Product->>Agent: Start build task Agent->>S: get_or_create(name, template_id=nextjs) Agent->>S: write /workspace/app/page.tsx Agent->>S: exec npm install && npm run build S-->>Product: stream stdout, stderr, file events Agent->>S: start preview on port 3000 S-->>Product: preview_url User->>Product: Make the hero more premium Agent->>S: patch files and rerun checks User->>Product: Ship it Agent->>D: publish /workspace D-->>Product: public_url ``` Your frontend can show the same work stream users expect from modern AI builders: tool calls, command output, generated files, preview links, screenshots, and final deployment URLs. --- ## Example: artifact workspace Use a sandbox when the output is a file, not a deployed app. ```text User asks for a proposal -> agent writes Python or Node generator -> sandbox creates proposal.html -> sandbox renders proposal.pdf -> sandbox creates proposal.docx -> product shows artifacts in a side panel -> user downloads or asks for edits ``` Good artifact outputs: - client proposals - pitch decks - data reports - PDF invoices - SVG diagrams - PNG charts - HTML previews - ZIP bundles - code archives --- ## Two sandbox choices, and both cover the jobs | Choice | Intended job | |---|---| | The default sandbox (`miosa-sandbox`) | Everything in one place: Python and Node execution, generated web apps, reports and artifacts, browser testing, and database-backed apps. | | The desktop (`miosa-desktop`) | GUI work and human takeover, when a person needs to see and drive the screen. | The product shape stays the same: start the default sandbox, let the agent work inside it. --- ## What to show users in your product Users should not have to understand VM internals. Show them useful work: - current task and plan - tool calls - command output - files created or edited - artifacts generated - preview URL - screenshots from browser checks - deployment URL - rollback/version history - credits and runtime usage The message should be: "Your agent is working in a real cloud workspace. You can watch it, inspect the files, preview the result, and ship when ready." --- ## See also - [See apps you can build](https://miosa.ai/docs/build.md): Step-by-step guides for 20+ product shapes, from Lovable and Bolt to Devin and an internal Business OS. - [Build an agent-company platform](https://miosa.ai/docs/guides/build-agent-company.md): Map always-on devices and operator agents onto MIOSA primitives. - [Backend orchestration](https://miosa.ai/docs/integrations/backend-orchestration.md): Build the API layer that dispatches prompts into sandboxes, computers, and local devices. - [Agent orchestration](https://miosa.ai/docs/guides/agent-orchestration.md): Coordinate sandbox agents, computer agents, artifacts, events, and deployments. - [Sandboxes](https://miosa.ai/docs/develop/sandboxes.md): Persistent code workspaces for files, commands, previews, snapshots, and publishing. - [Computers](https://miosa.ai/docs/computers/overview.md): Desktop/browser runtimes for screenshots, clicks, uploads, visual QA, and handoff.