Reading agent state - Copilotkit

<Callout type="info"> This example demonstrates reading from shared state in the [CopilotKit Feature Viewer](https://feature-viewer.copilotkit.ai/langgraph/feature/shared_state). </Callout>

What is this?

You can easily use the realtime agent state not only in the chat UI, but also in the native application UX.

When should I use this?

You can use this when you want to provide the user with feedback about your agent's state. As your agent's state updates, you can reflect these updates natively in your application.

Implementation

<Steps> <Step> ### Run and connect your agent <RunAndConnect /> </Step> <Step> ### Define the Agent State LangGraph is stateful. As you transition between nodes, that state is updated and passed to the next node. For this example, let's assume that our agent state looks something like this.

<Tabs groupId="agent_language" items={["Python", "TypeScript"]} persist>
  <Tab value="Python">
    ```python title="agent.py"
    from copilotkit import CopilotKitState
    from typing import Literal

    class AgentState(CopilotKitState):
        language: Literal["english", "spanish"] = "english"

    # The agent reads `state["language"]` from tools or middleware hooks
    # as it runs — no custom node required.
    ```
  </Tab>
  <Tab value="TypeScript">
    ```ts title="agent.ts"
    import { createMiddleware } from "langchain";
    import { copilotkitMiddleware } from "@copilotkit/sdk-js/langgraph"; // [!code highlight]
    import { z } from "zod";

    // Define the state as a middleware. The default flows through automatically.
    export const languageStateMiddleware = createMiddleware({
        name: "AgentState",
        stateSchema: z.object({
            language: z.enum(["english", "spanish"]).default("english"),
        }),
    });

    // Compose with copilotkitMiddleware when constructing the agent:
    // createDeepAgent({ middleware: [languageStateMiddleware, copilotkitMiddleware], ... })
    ```
  </Tab>
</Tabs>

</Step> <Step> ### Use the `useAgent` Hook With your agent connected and running all that is left is to call the `useAgent` hook, pass the agent's ID, and read the state.

```tsx title="ui/app/page.tsx"
import { useAgent } from "@copilotkit/react-core/v2"; // [!code highlight]

function YourMainContent() {
  // [!code highlight:3]
  const { agent } = useAgent({
    agentId: "sample_agent",
  });

  const language = (agent.state.language as string) ?? "english";

  // ...

  return (
    // style excluded for brevity
    <div>
      <h1>Your main content</h1>
      <p>Language: {language}</p>
    </div>
  );
}
```
<Callout type="info">
  The `agent.state` is reactive and will automatically update when the agent's state changes.
</Callout>

</Step> <Step> ### Give it a try! As the agent state updates, your `state` variable will automatically update with it! In this case, you'll see the language set to "english" as that's the initial state we set.

<Frame>
  <ImageZoom src="https://cdn.copilotkit.ai/docs/copilotkit/images/coagents/read-agent-state.png" alt="read agent state" width={1000} height={1000} className="my-0"/>
</Frame>

<Callout type="info">
  Pictured above is the [coagent starter](https://github.com/copilotkit/copilotkit/tree/main/examples/coagents-starter) with
  the [implementation](#implementation) section applied!
</Callout>

</Step> </Steps>

Rendering agent state in the chat

You can also render the agent's state in the chat UI using useRenderTool or by accessing agent.state from useAgent. The state is reactive and updates automatically.

tsx

import { useAgent } from "@copilotkit/react-core/v2"; // [!code highlight]

function YourMainContent() {
  // [!code highlight:3]
  const { agent } = useAgent({
    agentId: "sample_agent",
  });

  const language = (agent.state.language as string) ?? "english";

  return (
    <div>
      <p>Language: {language}</p>
    </div>
  );
}

Intermediately Stream and Render Agent State

By default, the Deep Agents agent state will only update between LangGraph node transitions -- which means state updates will be discontinuous and delayed.

You likely want to render the agent state as it updates continuously.

See emit intermediate state.