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

# RemoteGraph

> Call LangGraph RemoteGraph deployed on LangSmith from emma

## Overview

RemoteGraph allows you to call LangGraph graphs deployed on LangSmith directly from emma. This enables you to leverage your custom AI workflows and agents within emma's automation capabilities.

## What is RemoteGraph?

RemoteGraph is a LangGraph feature that allows you to interact with graphs deployed on LangSmith as if they were running locally. By integrating RemoteGraph with emma, you can:

* **Execute custom AI workflows** - Run your LangGraph agents from emma
* **Leverage LangSmith deployments** - Use graphs deployed on LangSmith infrastructure
* **Combine with Automations** - Schedule and automate your LangGraph workflows

## Getting Started

<Steps>
  <Step title="Deploy your graph to LangSmith">
    First, deploy your LangGraph graph to LangSmith. Refer to the [LangSmith documentation](https://docs.smith.langchain.com/) for deployment instructions.
  </Step>

  <Step title="Get your deployment URL">
    After deployment, obtain your LangSmith deployment URL and API key.
  </Step>

  <Step title="Configure in emma">
    Add your RemoteGraph configuration in emma's settings.
  </Step>

  <Step title="Start using">
    Call your RemoteGraph from emma tasks or automations.
  </Step>
</Steps>

## Configuration

To connect your LangSmith deployment to emma, you'll need:

| Parameter          | Description                          |
| ------------------ | ------------------------------------ |
| **Deployment URL** | Your LangSmith deployment endpoint   |
| **API Key**        | LangSmith API key for authentication |
| **Graph Name**     | Name of the deployed graph           |

## Use Cases

<CardGroup cols={2}>
  <Card title="Custom AI Agents" icon="robot">
    Run your custom LangGraph agents through emma
  </Card>

  <Card title="Complex Workflows" icon="diagram-project">
    Execute multi-step AI workflows with state management
  </Card>

  <Card title="Scheduled Execution" icon="clock">
    Combine with Automations for scheduled graph execution
  </Card>

  <Card title="Team Collaboration" icon="users">
    Share deployed graphs across your team via emma
  </Card>
</CardGroup>

## Best Practices

<AccordionGroup>
  <Accordion title="Monitor your deployments">
    Use LangSmith's monitoring features to track graph execution and performance.
  </Accordion>

  <Accordion title="Handle errors gracefully">
    Implement proper error handling in your graphs for reliable automation.
  </Accordion>

  <Accordion title="Optimize for latency">
    Consider response times when using RemoteGraph in time-sensitive automations.
  </Accordion>
</AccordionGroup>