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

Seed the state on the router

Pass initial_state to get_ag_ui_workflow_router. The router keeps the run's state under the state key of the workflow store and syncs that key with the UI. It also adds the current state to the latest user message in a <state>...</state> block, so the model reads what the UI wrote with agent.setState on its next turn.

src/agents/shared_state_read_write_agent.py
from llama_index.llms.openai import OpenAI
from llama_index.protocols.ag_ui.router import get_ag_ui_workflow_router

shared_state_read_write_router = get_ag_ui_workflow_router(
    llm=OpenAI(model="gpt-6-luna"),
    frontend_tools=[],
    backend_tools=[set_notes],
    system_prompt=SYSTEM_PROMPT,
    initial_state={
        "preferences": {
            "name": "",
            "tone": "casual",
            "language": "English",
            "interests": [],
        },
        "notes": [],
    },
)

Write state from a backend tool

A backend tool reads the state key from ctx.store, changes it, and stores it again. The router sends a state snapshot to the UI after every tool call, so the UI updates without any custom event.

shared_state_read_write_agent.py
async def set_notes(
    ctx: Context,
    notes: Annotated[
        list[str],
        "The COMPLETE updated list of notes (existing notes + new notes). "
        "Always pass the full list, never a diff. Each note < 120 chars.",
    ],
) -> str:
    """Replace the agent-authored notes array in shared state.

    Use this whenever the user asks you to "remember" something, or when
    you have an observation worth surfacing in the UI's notes panel.
    """
    state: dict[str, Any] = await ctx.store.get("state", default={})
    # Mutate in place so the router's post-tool StateSnapshotWorkflowEvent
    # carries the new value to the UI.
    state["notes"] = list(notes)
    await ctx.store.set("state", state)
    return f"Notes updated. {len(notes)} note(s) saved."

Register the tool in backend_tools, as in the previous step.

Only the state key reaches the UI. Keep private data in other ctx.store keys; see Workflow Execution.

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 LlamaIndex yet

The Shared State: Streaming demo for LlamaIndex 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?