Shared State

Create a two-way connection between your UI and agent 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
Shared State Demo

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.

Building stateful agents?Persistent threads ship with CopilotKit Intelligence on the free Developer tier.Get CopilotKit Intelligence free

Reading agent state

Type the agent's deps with StateDeps

Declare the shared state as a Pydantic model and set deps_type=StateDeps[YourState]. The AG-UI adapter writes the state the UI sent into ctx.deps.state at the start of every run.

src/agents/shared_state_read_write.py
from pydantic import BaseModel, Field
from pydantic_ai import Agent, RunContext
from pydantic_ai.ui import StateDeps
from pydantic_ai.models.openai import OpenAIResponsesModel


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


class SharedStateRWState(BaseModel):
    preferences: Preferences = Field(default_factory=Preferences)
    notes: list[str] = Field(default_factory=list)


agent = Agent(
    model=OpenAIResponsesModel("gpt-6-luna"),
    deps_type=StateDeps[SharedStateRWState],
    system_prompt=_BASE_SYSTEM_PROMPT,
)

Read what the UI wrote

A dynamic system prompt reads ctx.deps.state on every turn, so values the UI writes with agent.setState steer the model:

src/agents/shared_state_read_write.py
@agent.system_prompt
def _inject_preferences(
    ctx: RunContext[StateDeps[SharedStateRWState]],
) -> str:
    block = _build_prefs_block(ctx.deps.state.preferences)
    return block or ""

Write state from a tool

Change ctx.deps.state, then return a StateSnapshotEvent so the UI receives the new state as soon as the tool returns. Serialize the model with model_dump():

src/agents/shared_state_read_write.py
from ag_ui.core import EventType, StateSnapshotEvent


@agent.tool
async def set_notes(
    ctx: RunContext[StateDeps[SharedStateRWState]],
    notes: list[str],
) -> StateSnapshotEvent:
    """Replace the notes array in shared state with the full updated list."""
    ctx.deps.state.notes = list(notes)
    return StateSnapshotEvent(
        type=EventType.STATE_SNAPSHOT,
        snapshot=ctx.deps.state.model_dump(),
    )

Build the deps fresh on every request

The adapter writes the client's state into deps.state, so a shared StateDeps instance leaks state between concurrent requests and users:

agent.py
from pydantic_ai.ui.ag_ui import AGUIAdapter
from starlette.applications import Starlette
from starlette.requests import Request
from starlette.responses import Response
from starlette.routing import Route


async def run_agent(request: Request) -> Response:
    return await AGUIAdapter.dispatch_request(
        request, agent=agent, deps=StateDeps(SharedStateRWState())
    )


app = Starlette(routes=[Route("/", run_agent, methods=["POST"])])

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.

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

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.

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

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 for the full main-view pattern.

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

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 PydanticAI yet

The Shared State: Streaming demo for PydanticAI can't run yet, so its code isn't shown here. See the framework grid for the frameworks where it runs.

See State streaming for the full walkthrough, including the corresponding useAgent subscription on the frontend.

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 for the full pattern.

How is this guide?