> ## Documentation Index
> Fetch the complete documentation index at: https://langchain-5e9cc07a-preview-lginte-1765488813-6406a61.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# LangGraph integrations

LangGraph integrates with a growing ecosystem of tools and protocols that help you connect your agents to user interfaces, standardize agent definitions, and build production-ready applications. LangGraph integrations span two categories:

* [Front-end integrations](#front-end-integrations) — Connect LangGraph agents to user interfaces
* [Standards and interoperability](#standards-and-interoperability) — Portable agent definitions across runtimes

## Front-end integrations

Front-end integrations provide a lightweight bridge between LangGraph and user interfaces, allowing you to connect your agents to user interfaces with streaming state updates and human-in-the-loop support.

<CardGroup cols={2}>
  <Card title="AG-UI Python" icon="file-code" href="https://docs.ag-ui.com/getting-started/quickstart-langgraph-python">
    Open event-based protocol that standardizes how AI agents connect to user-facing applications. Provides a lightweight bridge between LangGraph and any front end with streaming state updates and human-in-the-loop support.
  </Card>

  <Card title="CopilotKit" icon="file-code" href="https://docs.copilotkit.ai/coagents/quickstart/langgraph-python">
    Open-source React framework for building AI copilots. Built on AG-UI, it provides pre-built UI components and deep LangGraph integration for embedding agents directly into React and Next.js applications.
  </Card>
</CardGroup>

## Standards and interoperability

Integrations for standards and interoperability provide a portable way to define agentic systems across different runtimes.

<CardGroup cols={1}>
  <Card title="Open Agent Spec (PyAgentSpec)" icon="file-code" href="https://oracle.github.io/agent-spec/index.html">
    Framework-agnostic declarative language by Oracle for defining agentic systems. Define agents and workflows in a portable JSON/YAML format that can be executed across different runtimes.
  </Card>
</CardGroup>

***

<Callout icon="pen-to-square" iconType="regular">
  [Edit the source of this page on GitHub.](https://github.com/langchain-ai/docs/edit/main/src/oss/langgraph/integrations.mdx)
</Callout>

<Tip icon="terminal" iconType="regular">
  [Connect these docs programmatically](/use-these-docs) to Claude, VSCode, and more via MCP for real-time answers.
</Tip>