# 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>
    ### Keep the state in conversation variables

    On AG2, shared state is the agent's **conversation variables**
    (`context.variables`). `AGUIStream` syncs them in both directions, so you
    do not build state events yourself:

    - State that the UI writes with `agent.setState` arrives on
      `RunAgentInput.state` and merges into the variables for the run.
    - At the start of the run, `AGUIStream` sends a `STATE_SNAPSHOT` if the
      merged variables differ from the state the client sent.
    - At the end of the run, it sends another `STATE_SNAPSHOT` if a tool
      changed `context.variables`.

    A snapshot replaces the client's state as a whole, so each one carries the
    client's keys and the server's variables together.

    ```python title="agent.py"
    from typing import Annotated

    from fastapi import FastAPI, Header
    from fastapi.responses import StreamingResponse
    from pydantic import Field

    from ag2 import Agent, Context, tool
    from ag2.ag_ui import AGUIStream, RunAgentInput
    from ag2.config import OpenAIResponsesConfig

    @tool
    def set_language(
        language: Annotated[str, Field(description="language such as english or spanish")],
        context: Context,
    ) -> str:
        """Update the language in shared state."""
        context.variables["language"] = language.lower()
        return f"Language set to {language}"

    agent = Agent(
        name="assistant",
        prompt=(
            "You are a helpful assistant for tracking language. "
            "Always respond in the current language."
        ),
        config=OpenAIResponsesConfig(model="gpt-6-luna"),
        tools=[set_language],
    )

    stream = AGUIStream(agent)
    app = FastAPI()

    @app.post("/chat")
    async def run_agent(
        message: RunAgentInput,
        accept: str | None = Header(None),
    ) -> StreamingResponse:
        return StreamingResponse(
            stream.dispatch(message, accept=accept),
            media_type=accept or "text/event-stream",
        )
    ```

    Everything in the variables is sent to the browser. Do not put secrets
    there. Pass them with `dispatch(dependencies=...)`, which never leaves the
    server.

  </Step>
  <Step>
    ### Do not seed state with `Agent(variables=...)`

    Agent variables take precedence over the incoming `RunAgentInput.state` on
    every run. A default set with `Agent(variables={"language": "english"})`
    overwrites whatever the UI wrote with `agent.setState`, and resets a value
    the agent changed on the previous turn. Nothing reports an error. Provide
    defaults in the UI instead, or with `context.variables.setdefault` inside a
    tool.

  </Step>
  <Step>
    ### Send intermediate snapshots from long tools

    The automatic snapshots only arrive at the start and the end of a run. To
    update the UI while a long tool runs, send a snapshot from an async tool
    with `context.send`:

    ```python title="agent.py"
    from ag_ui.core import StateSnapshotEvent

    from ag2 import Context, tool
    from ag2.ag_ui import AGUIEvent

    @tool
    async def long_running_task(context: Context) -> str:
        """A long task that streams state updates as it progresses."""
        for step in range(3):
            context.variables["progress"] = step
            await context.send(
                AGUIEvent(StateSnapshotEvent(snapshot=dict(context.variables)))
            )
        return "Done"
    ```

  </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 AG2 yet.** The Shared State: Streaming demo for AG2 can't run yet, so its code isn't shown here.

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"]} />
