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

# Using the Wherobots CLI with Agentic Terminals

> Use the Wherobots CLI from agentic coding tools like OpenCode, Claude Code, and other AI-powered terminals for natural language job management and automation.

<Badge color="purple">Public Preview</Badge>

The [**Wherobots CLI**](/develop/cli) works with agentic coding tools like **OpenCode**, **Claude Code**, and other AI-powered terminals out of the box.

Because these tools execute commands in your terminal, you can manage Wherobots jobs, stream logs, and access the full API using natural language.

## Before you start

The following requirements must be met to use the Wherobots CLI in an agentic terminal:

<AccordionGroup cols={2}>
  <Accordion title="Wherobots requirements" icon="cloud">
    * A **Wherobots Account** within a Community, Professional, or Enterprise Organization. See [Create a Wherobots Account](/get-started/wherobots-cloud/create-account).
      * While all Organization Editions can use the CLI, certain API features and job creation require a Professional or Enterprise Organization. See [Organization Editions](/get-started/organization-management/organization-editions) for details.
    * A Wherobots **API key**. See [API Keys](/get-started/wherobots-cloud/api-keys).
  </Accordion>

  <Accordion title="Local requirements" icon="laptop">
    * The **Wherobots CLI** installed and on your `PATH`. See [Install Wherobots CLI](/develop/cli).
    * Your `WHEROBOTS_API_KEY` environment variable set. See [Configure authentication](/develop/cli#configure-authentication).
    * An agentic terminal such as **OpenCode**, **Claude Code**, **Cursor**, or another AI-powered coding tool with terminal access.
      * Models such as **Claude Opus**, **GPT Codex**, or **Gemini Pro** for the best results when using natural language commands.
  </Accordion>
</AccordionGroup>

## Add agent skills

Agent skills give your agentic terminal domain-specific knowledge about Wherobots so it produces more accurate commands and better interprets results. Without skills, the agent relies only on CLI help text and its general training data. With skills installed, it has structured context about Wherobots workflows, APIs, and best practices — leading to fewer errors, less back-and-forth, and more reliable multi-step operations.

See [Agent Skills](/develop/agent-skills) for installation instructions and the full list of available skills.

## Benefits

<AccordionGroup>
  <Accordion title="No syntax to memorize" icon="brain">
    Describe what you want in plain language. The agentic terminal resolves the correct commands, subcommands, and flags for you.
  </Accordion>

  <Accordion title="Multi-step workflows in a single request" icon="layer-group">
    Chain together operations like submitting a job, waiting for completion, and retrieving logs without writing a script.
  </Accordion>

  <Accordion title="Built-in error guidance" icon="triangle-exclamation">
    When a command fails, the agent reads the error, suggests a fix, and can retry automatically.
  </Accordion>
</AccordionGroup>

## Example tasks

Once the CLI is installed and your API key is set, just ask. Your agentic terminal translates natural language into the right `wherobots` commands, picks the appropriate flags, and interprets the results.

<Tip>
  Wherobots recommends using the latest high-performing AI model available in your agentic terminal for the best results such as Claude Opus, GPT Codex, or Gemini Pro.
</Tip>

### Explore the API

| Terminal Prompt                    | What you can expect                                                   |
| ---------------------------------- | --------------------------------------------------------------------- |
| *List available CLI commands*      | Prints the full command tree so you can see every available endpoint. |
| *Preview a job submission request* | Previews the exact API request without executing it.                  |

### Submit and monitor jobs

| Terminal Prompt                                | What you can expect                                                       |
| ---------------------------------------------- | ------------------------------------------------------------------------- |
| *Submit a script as a job and stream the logs* | Uploads the script, creates a run, and tails the output until completion. |
| *Check the status of a recent job*             | Fetches the most recent run and reports its state.                        |
| *Get resource metrics for a running job*       | Pulls live CPU and memory metrics for the specified run.                  |

### Debug and triage

| Terminal Prompt                                | What you can expect                                                                      |
| ---------------------------------------------- | ---------------------------------------------------------------------------------------- |
| *List recent failed jobs and summarize errors* | Fetches recent failures, parses the structured output, and gives you a readable summary. |
| *Retrieve logs from a failed run*              | Tails the logs for the most recent failure so you can jump straight to the error.        |

### Automate

| Terminal Prompt                                | What you can expect                                       |
| ---------------------------------------------- | --------------------------------------------------------- |
| *List running jobs as JSON*                    | Returns the running jobs in JSON format.                  |
| *Cancel all running jobs in a specific region* | Filters runs by region and status, then cancels each one. |

## Next steps

<CardGroup cols={2}>
  <Card title="Install Wherobots CLI" icon="terminal" href="/develop/cli">
    Install and configure the CLI for terminal-based Wherobots access.
  </Card>

  <Card title="MCP Server" icon="microchip" href="/develop/mcp/mcp-server-setup">
    Configure the Wherobots MCP Server for catalog exploration and spatial query generation.
  </Card>
</CardGroup>