# MIOSA documentation reconstruction

- [Build on MIOSA](/docs/index.md): Understand the building blocks. Run code in a sandbox, inspect a preview, and publish a version you can return to.
- [Sandbox to deployment](/docs/quickstart.md): A complete first workflow: create an environment, write an application, inspect it, and publish a version with a clear rollback path.
- [Install the CLI or SDK](/docs/installation.md): Pick the interface that matches your workflow, configure credentials once, and verify the connection before making changes.
- [The product model](/docs/product-model.md): A small resource vocabulary makes the system easier to understand. Give every resource a clear owner, lifetime and purpose.
- [Learn MIOSA your way](/docs/learn.md): Read the words, try the labs, and understand what you build. Pick a path and make it your own.
- [Learn and earn](/docs/learn/earn.md): Learn how the building blocks fit together. Read, practice, and track your progress across three learning paths.
- [Learn the words](/docs/glossary.md): Plain-language explanations for the building blocks. Explore a category, practice the terms, then check what you know.
- [Learn with games](/docs/learn/games.md): Build your understanding by doing. Seven short, interactive labs take you from the vocabulary to your first product.
- [Learn with videos](/docs/learn/videos.md): Short lessons for the ideas behind the platform. This track opens when the lessons are ready.
- [Projects](/docs/projects.md): Group the resources for one application without hiding who owns them.
- [Services](/docs/services.md): Choose a web process, a worker or a scheduled job according to the work it does.
- [Deployments and rollback](/docs/deployments.md): Publish a specific version, verify that version, and retain a clear route to the last known good release.
- [Sandboxes](/docs/sandboxes.md): An isolated place for code and tools. Create it for a task, keep the state you need, and stop it when the task is finished.
- [Snapshots and persistence](/docs/snapshots.md): Save the state you intend to recover, understand what the snapshot includes, and verify the restored instance.
- [Computers](/docs/computers.md): Use a desktop when the task depends on visual applications, browser state or direct interaction.
- [Data and bindings](/docs/data.md): Choose storage by the shape and lifetime of the data, then connect it explicitly to the application.
- [Domains and previews](/docs/networking.md): Understand what a temporary preview exposes and what a stable domain promises to its users.
- [Models, harnesses and tools](/docs/agents.md): An agent is easier to understand when its reasoning, execution loop and machine are separate concepts.
- [CLI workflow](/docs/cli.md): Use explicit resources and structured output to make terminal workflows readable and repeatable.
- [Build your own dots](/docs/build/dots.md): Always-on agents that each get their own cloud computer and browser, working in the background.
- [Build your own Grok Bot](/docs/build/grok-bot.md): Named agents, each with its own cloud computer, teaming up to get work done around the clock.
- [Build your own Manus](/docs/build/manus.md): A general computer-use agent: full Linux desktops with browser, files, and human handoff.
- [Build your own Genspark](/docs/build/genspark.md): A super-agent product that plans, researches, and produces finished work for your users.
- [Run Claude Code](/docs/build/claude-code.md): Coding harnesses running in sandboxes, with streamed events and collected artifacts.
- [Build your own Lovable](/docs/build/lovable.md): A prompt-to-app builder: the agent writes the app in a sandbox and you publish it.
- [Build your own Devin](/docs/build/devin.md): An autonomous software engineer: dispatch long-running agent runs and stream their work.
- [Build your own OpenSwarm](/docs/build/openswarm.md): An AI desktop where every user gets a personal agent with a real computer behind it.
- [Build your own Replit Agent](/docs/build/replit.md): A cloud workspace where an agent builds, runs, and previews apps in isolated sandboxes.
- [Build your own An agent like ChatGPT agent](/docs/build/chatgpt-agent.md): Build an agent that browses, clicks and fills forms in a real browser session you can watch.
- [Build your own Perplexity Comet](/docs/build/comet.md): An agentic browser: navigate, extract, and act on the web with a live viewer.
- [Run OpenClaw](/docs/build/openclaw.md): A personal agent that lives on a persistent virtual device and works while you are away.
- [Run Hermes Agent](/docs/build/hermes-agent.md): An open agent that runs for businesses: many agents, each with tools and its own workspace.
- [Build your own An agent like Gemini agent](/docs/build/gemini-agent.md): Build an orchestrator that plans and delegates work to sub-agents.
- [Run Cursor agents](/docs/build/cursor.md): Fleets of coding agents working in parallel on isolated machines, coordinated from one place.
- [Build your own v0](/docs/build/v0.md): Generate a UI from a prompt and publish it to a stable URL in one step.
- [Build your own Bolt](/docs/build/bolt.md): Full-stack apps from a prompt, running on dynamic runtimes with real servers.
- [Build your own Windsurf](/docs/build/windsurf.md): An agentic IDE: run its agents against isolated sandboxes instead of a laptop.
- [Build your own GitHub Copilot agent](/docs/build/github-copilot.md): A coding agent that takes an issue, works in a sandbox, and opens a pull request.
- [Run OpenHands](/docs/build/openhands.md): An open-source software agent with a sandboxed workspace for every task.
- [Build your own Emergent](/docs/build/emergent.md): A full-stack app builder: prompts become running software with real infrastructure.
- [Build your own Base44](/docs/build/base44.md): Describe an app, get a working one: generated, previewed, and published for you.
- [SDKs](/docs/sdks.md): Use the same resource model from application code. Pick a language and keep identifiers and failures explicit.
- [MCP](/docs/mcp.md): Expose defined capabilities to an agent client without making the client guess how to call your service.
- [API fundamentals](/docs/api-reference.md): Read the resource contract, send an explicit request, and inspect the exact response before taking the next action.
- [Interactive API reference](/docs/api.md): Explore a working local sandbox API. Inspect its schema and try requests against this learning project.
- [Permissions and secrets](/docs/security.md): Make the ownership boundary visible, keep credentials out of browser bundles, and preserve useful failures.
- [Make this documentation your own](/docs/customization.md): Replace the content, adjust the tokens, and connect only the services you need. The reading experience works on its own.
- [Changelog](/docs/changelog.md): Changes to this local documentation reconstruction.