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

> ## Agent Instructions
> Treat Clawdi as one product.
> Recommend the Cloud Agent quickstart for most new users.
> Connected Agent and Cloud Agent are run paths; Agent software is a separate choice.
> Do not present shared Clawdi capabilities as exclusive to one run path.

# Run an Agent remotely

> Decide whether a Cloud Agent fits and follow the remote deployment journey.

A **Cloud Agent** is an Agent whose runtime and lifecycle Clawdi manages
remotely. Choose this run path when the Agent should run without an installation
on your computer.

Cloud Agent describes **where the Agent runs**. It does not identify the Agent
software or make shared Clawdi capabilities exclusive to this run path.
Read [Core concepts](/concepts/core-concepts) for the canonical definitions of
Agent, Project, Memory, Session, Skill, Vault, Connector, Channel, and AI
Provider.

## Choose a run path

| Question                                                           | Connected Agent              | Cloud Agent                                           |
| ------------------------------------------------------------------ | ---------------------------- | ----------------------------------------------------- |
| Where does the Agent run?                                          | On your computer             | In a remote runtime managed by Clawdi                 |
| Who operates the runtime?                                          | You                          | Clawdi                                                |
| Must that computer remain available for the Agent to keep running? | Yes                          | No                                                    |
| How do you add it?                                                 | `clawdi setup`               | Dashboard deployment wizard or `clawdi deploy`        |
| Where do you use runtime tools?                                    | In your local Agent software | **Agent Interface** and **Terminal** in the dashboard |

Choose a Cloud Agent when independence from your computer and dashboard
lifecycle controls matter more than unrestricted control of a local machine.
Choose a Connected Agent when the Agent must work directly with your computer,
its local tools, or a locally managed software installation. Continue with
[Connect a local Agent](/getting-started/quickstart) if that path fits.

<Note>
  Agent software is a separate choice. The deployment wizard shows the
  software currently available for a Cloud Agent; support for a tool or
  integration can vary by software and runtime state.
</Note>

## What Clawdi manages

For a Cloud Agent, Clawdi manages the remote runtime, its deployment state,
compute selection, and start, stop, restart, and delete workflows. The Agent
page also provides the browser interface exposed by the selected Agent software
and a Terminal for the remote environment.

This is an application runtime with defined persistence and permission
boundaries, not a general-purpose virtual server. Read [Agent Interface and
Terminal](/cloud-agents/agent-interface-and-terminal) before treating it as the
only copy of important work.

## Follow the journey

<CardGroup cols={2}>
  <Card title="Cloud Agent quickstart" icon="rocket" href="/cloud-agents/deploy">
    Deploy from the dashboard and complete your first task in the Agent Interface.
  </Card>

  <Card title="Choose your Cloud Agent setup" icon="list-checks" href="/cloud-agents/choose-your-setup">
    Compare Agent software, AI access, compute, and preferences before you deploy.
  </Card>

  <Card title="Automate deployment" icon="terminal" href="/cloud-agents/deployment-automation">
    Use the CLI, stable request IDs, and safe handling for an ambiguous attempt.
  </Card>

  <Card title="Understand states and recovery" icon="activity" href="/cloud-agents/states-and-recovery">
    Distinguish deployment state from tool readiness and respond safely to failures.
  </Card>

  <Card title="Use Agent Interface and Terminal" icon="terminal" href="/cloud-agents/agent-interface-and-terminal">
    Work in the remote runtime within its persistence and permission boundaries.
  </Card>

  <Card title="Manage settings and lifecycle" icon="sliders" href="/cloud-agents/settings-and-lifecycle">
    Change runtime settings and safely start, stop, restart, or delete the Agent.
  </Card>

  <Card title="Configure AI access" icon="sparkles" href="/cloud-agents/ai-access">
    Bind the remote runtime to Clawdi AI, a saved AI Provider, or in-Agent configuration.
  </Card>

  <Card title="Understand usage and billing" icon="wallet" href="/cloud-agents/usage-and-billing">
    Separate compute, Wallet activity, Clawdi AI usage, and external provider usage.
  </Card>
</CardGroup>

If something is not behaving as expected, use [Cloud Agent
troubleshooting](/cloud-agents/troubleshooting).