Reading agent state

This example demonstrates reading from shared state in the CopilotKit Feature Viewer.

What is this?#

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

Important

This guide assumes you are embedding your Mastra agent inside of Copilot Runtime, like so.

const runtime = new CopilotRuntime({
  agents: MastraAgent.getLocalAgents({ mastra }),
});

This feature will not work if you are using a remote Mastra agent.

When should I use this?#

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

Implementation#

Run and connect your agent#

You'll need to run your agent and connect it to CopilotKit before proceeding. If you haven't done so already, you can follow the instructions in the Getting Started guide.

If you don't already have an agent, you can use the coagent starter as a starting point as this guide uses it as a starting point.

Define the Agent State#

Mastra has advanced working memory concepts to provide statefulness to your agents. CopilotKit leverages Mastra's working memory concept to allow you to implement shared state between your agent and your application.

Providing working memory to your agent is as simple as providing a Zod schema to your agent.

mastra/agents/language-agent.ts

import { openai } from "@ai-sdk/openai";
import { Agent } from "@mastra/core/agent";
import { LibSQLStore } from "@mastra/libsql";
import { z } from "zod";
import { Memory } from "@mastra/memory";

// 1. Define the agent state schema
export const AgentStateSchema = z.object({
  language: z.enum(["english", "spanish"]),
});

// 2. Infer the agent state type from the schema
export const AgentState = z.infer<typeof AgentStateSchema>;

// 3. Create the agent
export const languageAgent = new Agent({
  name: "Language Agent",
  model: openai("gpt-5.4"),
  instructions: "Always communicate in the preferred language of the user as defined in your working memory. Do not communicate in any other language.",
  memory: new Memory({
    storage: new LibSQLStore({ id: "mastra-storage", url: ":memory:" }),
    options: {
      workingMemory: {
        enabled: true,
        schema: AgentStateSchema,
      },
    },
  }),
});

Use the `useAgent` Hook#

With your agent connected and running all that is left is to call the useAgent hook, pass the agent's name, and optionally provide an initial state.

ui/app/page.tsx

import { useAgent } from "@copilotkit/react-core/v2"; 
import { AgentState } from "@/mastra/agents/language-agent";

function YourMainContent() {
  const { agent } = useAgent({
    agentId: "your-mastra-agent-name",
    // optionally provide a type-safe initial state
    initialState: { language: "english" }
  });

  // ...

  return (
    // style excluded for brevity
    <div>
      <h1>Your main content</h1>
      <p>Language: {agent.state?.language}</p>
    </div>
  );
}

The agent.state in useAgent is reactive and will automatically update when the working memory changes.

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.

Rendering agent state in the chat#

You can also render the working memory in the chat UI. This is useful for informing the user about the working memory in a more in-context way. To do this, you can use the useAgent hook with a render function.