# 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 keys on your Flow state

    A Flow keeps its state in `self.state`. Type the Flow on a subclass of
    `CopilotKitState` and declare every key the UI reads or writes, with a
    default. `CopilotKitState` brings the CopilotKit messages and actions.

    ```python title="src/agents/shared_state_read_write.py"
    from typing import List, Optional

    from ag_ui_crewai import CopilotKitState
    from pydantic import BaseModel, Field


    class Preferences(BaseModel):
        name: str = ""
        tone: str = "casual"
        language: str = "English"
        interests: List[str] = Field(default_factory=list)


    class AgentState(CopilotKitState):
        # Written by the UI with agent.setState
        preferences: Optional[Preferences] = None
        # Written by the agent, read by the UI with useAgent
        notes: List[str] = Field(default_factory=list)
    ```

    Import `CopilotKitState` from `ag_ui_crewai`. If you promoted the Flow to a
    Conversational Flow, keep inheriting
    from `ag_ui_crewai.CopilotKitState`: it also carries the conversation
    fields CrewAI needs.

  </Step>
  <Step>
    ### Read what the UI wrote

    Values the UI writes with `agent.setState` are on `self.state` when the
    next run starts. A nested model can arrive as a plain dict, so convert it
    before you use it:

    ```python title="src/agents/shared_state_read_write.py"
    from crewai.flow.flow import Flow, start


    class SharedStateReadWriteFlow(Flow[AgentState]):
        @start()
        async def chat(self) -> None:
            prefs = self.state.preferences
            if isinstance(prefs, dict):
                prefs = Preferences(**prefs)
                self.state.preferences = prefs
    ```

  </Step>
  <Step>
    ### Write state and emit it

    By default the UI receives the Flow's state only when a method finishes.
    To update the UI mid-run, assign the value and call
    `copilotkit_emit_state`:

    ```python title="agent.py"
    import asyncio
    from typing import TypedDict

    from crewai.flow.flow import Flow, start
    from ag_ui_crewai import CopilotKitState, copilotkit_emit_state


    class Searches(TypedDict):
        query: str
        done: bool


    class AgentState(CopilotKitState):
        searches: list[Searches] = []


    class SearchFlow(Flow[AgentState]):
        @start()
        async def chat(self):
            self.state.searches = [
                {"query": "Initial research", "done": False},
                {"query": "Retrieving sources", "done": False},
                {"query": "Forming an answer", "done": False},
            ]
            await copilotkit_emit_state(self.state)

            for search in self.state.searches:
                await asyncio.sleep(1)
                search["done"] = True
                await copilotkit_emit_state(self.state)
    ```

    The showcase's `src/agents/shared_state_read_write.py` does the same after
    the model calls its `set_notes` tool: it assigns `self.state.notes` and
    emits the state, so the notes card updates before the turn ends.

  </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.

```python title="src/agents/shared_state_streaming.py"
class SharedStateStreamingState(CopilotKitState):
    document: str = ""


class SharedStateStreamingFlow(Flow[SharedStateStreamingState]):
    """Predict write_document arguments into state, then persist the result."""

    @start()
    async def write(self) -> None:
        await copilotkit_predict_state(
            [
                StateItem(
                    state_key="document",
                    tool="write_document",
                    tool_argument="document",
                )
            ]
        )
```

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"]} />
