> ## Documentation Index
> Fetch the complete documentation index at: https://docs.openhome.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Vibe Coding

> Build OpenHome Abilities and companion dashboards with AI coding assistants — Claude, Cursor, and the Replit Agent.

Vibe coding is the fastest way to ship OpenHome. Let Claude (or any coding agent) drive the build while you describe what you want in plain English. With the right briefing, you can go from idea to live Ability in an afternoon.

There are two main surfaces:

<CardGroup cols={2}>
  <Card title="Build Abilities with Claude" icon="code" href="/guides/best-practices/vibe-coding-tips#vibe-coding-abilities-with-claude">
    Scaffold, deploy, and test Abilities from your terminal using the OpenHome CLI. Claude writes the Python; you review and ship.
  </Card>

  <Card title="Build dashboards with Replit" icon="chart-line" href="/guides/best-practices/vibe-coding-tips#vibe-coding-dashboards-with-the-replit-agent">
    Hand the Replit Agent a master prompt; get a working Flask + dashboard in one shot.
  </Card>
</CardGroup>

## The rule of two tabs

Whichever surface you're on, keep **two browser tabs open** side by side so you see both sides of the pipe at once:

| Building an Ability                 | Building a dashboard                |
| ----------------------------------- | ----------------------------------- |
| OpenHome Live Editor (Ability logs) | OpenHome Live Editor (Ability logs) |
| Your terminal with Claude + the CLI | Replit (server logs)                |

If a request fails, you see it in both within a second — the fastest feedback loop voice AI has ever had.

## What makes OpenHome good for vibe coding

* **Clear sandbox rules** — a tight list of allowed/blocked APIs means the LLM has unambiguous constraints to respect
* **Consistent SDK** — every method on `self.capability_worker` or `self.worker`; easy to brief a model on
* **Deep source material** — [SDK Reference](/api-sdk/sdk-reference) + [Simple Abilities Cookbook](/building-abilities/cookbook) fit in a single LLM context window
* **CLI + API** — the [OpenHome CLI](/guides/getting-started/cli) gives agents a tool surface to drive the entire build → deploy → test loop

## Next steps

* [Vibe Coding Tips](/guides/best-practices/vibe-coding-tips) — prompts, patterns, and guardrails for both surfaces
* [OpenHome CLI](/guides/getting-started/cli) — the Claude-friendly CLI
* [Companion Dashboards](/guides/getting-started/companion-dashboards) — the architecture path for dashboard-heavy builds