in-app-agent-write.mdx

title	Writing agent state
icon	lucide/ArrowRight
description	Write to agent's state from your application.

This example demonstrates writing to shared state in the [CopilotKit Feature Viewer](https://feature-viewer.copilotkit.ai/langgraph/feature/shared_state).

What is this?

This guide shows you how to write to your agent's state from your application.

When should I use this?

You can use this when you want to provide the user with feedback about what your agent is doing, specifically when your agent is calling tools. CopilotKit allows you to fully customize how these tools are rendered in the chat.

Implementation

### Run and connect your agent ### 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="language_langgraph_agent" 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"
    ```
  </Tab>
  <Tab value="TypeScript">
    ```ts title="agent-js/src/agent.ts"
    import { StateSchema } from "@langchain/langgraph";
    import { CopilotKitStateSchema } from "@copilotkit/sdk-js/langgraph";
    import { z } from "zod";

    export const AgentStateSchema = new StateSchema({
        language: z.enum(["english", "spanish"]).default("english"),
        ...CopilotKitStateSchema.fields,
    });
    export type AgentState = typeof AgentStateSchema.State;
    ```
  </Tab>
</Tabs>

### Use the `useAgent` hook to read and write state `useAgent` gives you access to the agent, including its state. You can update state by calling `agent.setState`.

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

// Example usage in a pseudo React component
function YourMainContent() {
  // [!code highlight:3]
  const { agent } = useAgent({
    agentId: "sample_agent",
  });

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

  // ...

  const toggleLanguage = () => {
    agent.setState({ language: language === "english" ? "spanish" : "english" }); // [!code highlight]
  };

  // ...

  return (
    // style excluded for brevity
    <div>
      <h1>Your main content</h1>
      {/* [!code highlight:1] */}
      <p>Language: {language}</p>
      <button onClick={toggleLanguage}>Toggle Language</button>
    </div>
  );
}
```

### Give it a try! You can now use the `setState` function to update the agent state and `state` to read it. Try toggling the language button and talking to your agent. You'll see the language change to match the agent's state.

<video src="https://cdn.copilotkit.ai/docs/copilotkit/images/coagents/write-agent-state.mp4" className="rounded-lg shadow-xl" loop playsInline controls autoPlay muted />
<Callout>
  This video shows the result of `npx copilotkit@latest init` with the [implementation](#implementation) section applied to it!
</Callout>

Advanced Usage

Re-run the agent with updated state

The new agent state will be used next time the agent runs. If you want to re-run it manually, use agent.runAgent after updating state.

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

// ...

function YourMainContent() {
  const { agent } = useAgent({
    agentId: "sample_agent",
  });

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

  // setup to be called when some event in the app occurs
  const toggleLanguage = () => {
    const newLanguage = language === "english" ? "spanish" : "english";
    agent.setState({ language: newLanguage });

    // [!code highlight:2]
    // re-run the agent with updated state
    agent.runAgent();
  };

  return (
    // ...
  );
}

Intermediately Stream and Render Agent State

By default, the LangGraph 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 predictive state updates.