# Shared State

> Create a two-way connection between your UI and agent state.

## What is shared state? [#what-is-shared-state]

Shared state connects your UI with the agent's run. With shared state you can:

- Display the agent's current progress and intermediate results
- Update the agent's state through UI interactions
- React to state changes in real-time across your application

<ImageZoom
  src="https://cdn.copilotkit.ai/docs/copilotkit/images/coagents/SharedStateCoAgents.gif"
  alt="Shared State Demo"
  width={1000}
  height={1000}
  className="rounded-lg shadow-lg border mt-0"
/>

## When should I use this? [#when-should-i-use-this]

Use shared state when you want the agent and the user to collaborate through the same application state. The agent's outputs are reflected in the UI, and user updates in the UI are reflected in the agent's execution.

<OpsPlatformCTA
  variant="inline"
  title="Building stateful agents?"
  body="Persistent threads ship with CopilotKit Intelligence on the free Developer tier."
  surface="docs_shared_state"
/>

## Reading agent state [#reading-agent-state]

<Steps>
  <Step>
    ### Declare the shared state on your Deep Agent

    A Deep Agent declares its state through middleware. Add your field to a
    state schema, and pass that middleware to the agent together with the
    CopilotKit middleware. This example shares a `language` value.

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

        from copilotkit import CopilotKitMiddleware, CopilotKitState
        from deepagents import create_deep_agent
        from langchain_openai import ChatOpenAI
        from langchain.agents.middleware import AgentMiddleware

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

        class LanguageStateMiddleware(AgentMiddleware[AgentState, Any]):
            state_schema = AgentState

        agent = create_deep_agent(
            model=ChatOpenAI(model="gpt-6-luna", reasoning_effort="none"),
            middleware=[
                LanguageStateMiddleware(),
                CopilotKitMiddleware(expose_state=["language"]),
            ],
            system_prompt=(
                "You are a helpful assistant. Current agent state contains "
                "language. Always answer in that language."
            ),
        )
        ```
      </Tab>
      <Tab value="TypeScript">
        ```ts title="agent.ts"
        import { createMiddleware } from "langchain";
        import {
          createCopilotkitMiddleware,
          zodState,
        } from "@copilotkit/sdk-js/langgraph";
        import { createDeepAgent } from "deepagents";
        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: zodState(z.enum(["english", "spanish"]).default("english")),
          }),
        });

        export const agent = createDeepAgent({
          model: "openai:gpt-6-luna",
          middleware: [
            languageStateMiddleware,
            createCopilotkitMiddleware({ exposeState: ["language"] }),
          ],
          systemPrompt:
            "You are a helpful assistant. Current agent state contains " +
            "language. Always answer in that language.",
        });
        ```
      </Tab>
    </Tabs>

    In TypeScript, `zodState` keeps the field in the AG-UI state snapshots
    that reach the frontend.

  </Step>
  <Step>
    ### Expose the field to the model

    A value the UI writes with `agent.setState` reaches the agent's state, but
    the CopilotKit middleware does not show state to the model by default.
    List the fields the model should see in `expose_state` (`exposeState`),
    and say in the system prompt what they mean. Without the allowlist, the
    run succeeds and the model answers as if the UI had written nothing. Keep
    the allowlist narrow.

  </Step>
  <Step>
    ### Read and write the state in your UI

    Deep Agents has no live demo on this page yet, so the demo code below does
    not show for it. `useAgent` returns the agent, its reactive `state`, and
    `setState`:

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

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

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

      const toggleLanguage = () => {
        agent.setState({ language: language === "english" ? "spanish" : "english" });
      };

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

  </Step>
</Steps>

Subscribe a component to the agent's state with `useAgent`. Any time the agent mutates its state, for example via a tool call, the composable updates its reactive `agent` ref and your UI re-renders with the new values.

```vue title="src/components/SharedWorkspace.vue"
<script setup lang="ts">
import { computed } from "vue";
import { useAgent, UseAgentUpdate } from "@copilotkit/vue/v2";

type WorkspaceState = {
  notes?: string[];
  preferences?: { tone?: string };
};

const { agent } = useAgent({
  agentId: "workspace",
  updates: [UseAgentUpdate.OnStateChanged],
});
const state = computed(
  () => (agent.value?.state ?? {}) as WorkspaceState,
);
</script>

<template>
  <ul>
    <li v-for="note in state.notes ?? []" :key="note">{{ note }}</li>
  </ul>
</template>
```

The returned `agent.value.state` is a plain object. Read it like any other reactive application data and render the parts you care about: agent-written notes, structured outputs, progress indicators, or anything else the agent has put there.

## Writing agent state [#writing-agent-state]

The same agent object exposes `setState`. Calling it from a UI event handler pushes the new value into shared state, and the agent reads it back on its next turn. The UI's writes visibly steer the model.

```vue title="src/components/SharedWorkspace.vue"
<script setup lang="ts">
function setTone(tone: string) {
  const current = agent.value;
  if (!current) return;

  const previous = (current.state ?? {}) as WorkspaceState;
  current.setState({
    ...previous,
    preferences: { ...previous.preferences, tone },
  });
}
</script>

<template>
  <button @click="setTone('concise')">Prefer concise answers</button>
</template>
```

The UI can also send the agent new inputs, such as preferences, selections, or partial work, without the chat.

## Rendering shared state in the UI [#rendering-shared-state-in-the-ui]

Because `agent.state` is plain data exposed through a Vue ref, the UI layer is ordinary Vue. The example above wires the agent's outputs into a list and feeds user edits back through `setState`.

Nothing about this is chat-specific: `useAgent` works in any component under `CopilotKitProvider`, so you can render shared state in your main view or canvas, not just inside the chat panel. See **[Render agent state in your app](/vue/shared-state/rendering-in-app)** for the full main-view pattern.

```vue title="src/App.vue"
<script setup lang="ts">
import { CopilotChat, CopilotKitProvider } from "@copilotkit/vue/v2";
import SharedWorkspace from "./components/SharedWorkspace.vue";
</script>

<template>
  <CopilotKitProvider runtime-url="/api/copilotkit">
    <SharedWorkspace />
    <CopilotChat agent-id="workspace" />
  </CopilotKitProvider>
</template>
```

## Streaming partial state updates [#streaming-partial-state-updates]

By default, shared state only updates *between* backend checkpoints, so a long-running tool call appears as one big burst at the end. State streaming copies a tool argument into a state key while the model writes it, so the UI can watch the answer assemble token-by-token. The sample below is the LangGraph (Python) version.

> **Not available for Langchain DeepAgents yet.** This sample comes from the showcase's `shared-state-streaming` demo, and Langchain DeepAgents doesn't have it yet.

See **[State streaming](/vue/shared-state/streaming)** for the full walkthrough, including the corresponding `useAgent` subscription on the frontend.

## Read-only context [#read-only-context]

When a value is **UI-owned** and the agent should read it but never write it back, such as current user, selected record, or scroll position, reach for `useAgentContext` instead of full shared state. It publishes values as a one-way UI-to-agent channel that auto-unregisters on unmount.

`useAgentContext` is a separate read-only capability; it does not replace the bidirectional `agent.state` / `agent.setState(...)` contract above.

See **[Agent read-only context](/vue/shared-state/agent-readonly)** for the full pattern.

<IntegrationGrid path="shared-state" exclude={["agno", "agent-spec", "spring-ai", "langroid"]} />
