Shared State

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

What is shared state?

Shared state connects your app's 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 app
Shared State Demo

When should I use this?

Use shared state when you want the agent and the user to work on the same app state. The UI shows what the agent writes. The agent reads what the user changes in the UI.

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

Reading agent state

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.

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.

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.

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:

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"

Subscribe a component to the agent's state with useAgent. Each time the agent changes its state, for example from a tool call, the hook re-renders your component with the new values.

src/NotesCard.tsx
import { Text, View } from "react-native";
import { useAgent, UseAgentUpdate } from "@copilotkit/react-native/headless";

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

export function NotesCard() {
  const { agent } = useAgent({
    agentId: "default",
    updates: [UseAgentUpdate.OnStateChanged],
  });
  const state = (agent.state ?? {}) as NotesState;

  return (
    <View style={{ padding: 16, gap: 4 }}>
      {(state.notes ?? []).map((note) => (
        <Text key={note}>• {note}</Text>
      ))}
    </View>
  );
}

agent.state is a plain object. Read it like any other React data and render the parts you care about: notes the agent wrote, structured output, progress, or anything else the agent put there.

Writing agent state

The same agent has a setState method. Call it from a UI event, and the agent reads the new value on its next turn. The UI's writes steer the model.

import { Button } from "react-native";

// In NotesCard, below the list:
<Button
  title="Prefer short answers"
  onPress={() =>
    agent.setState({
      ...state,
      preferences: { ...state.preferences, tone: "concise" },
    })
  }
/>

This makes shared state two-way. The UI can send the agent new inputs, such as preferences, selections, or partial work, without the chat.

The agent reads the new state on its next run. To run it right away, call copilotkit.runAgent({ agent }) (from useCopilotKit) after setState. Running through copilotkit also sends your frontend tools and context with the run. To tell the model what changed, add a message first:

const { copilotkit } = useCopilotKit();

agent.setState({ ...state, language: newLanguage });
agent.addMessage({
  id: `user-${Date.now()}`,
  role: "user",
  content: `The language has been updated to ${newLanguage}.`,
});
await copilotkit.runAgent({ agent });

See Programmatic Control for more ways to run the agent from code.

Rendering shared state in the UI

Because agent.state is plain React data, the UI layer is whatever you'd normally build. Nothing about it is chat-specific: useAgent works in any component under CopilotKitProvider, so you can render the state on your main screen, not just next to the chat. See Render agent state in your app for the full pattern.

Streaming partial state updates

By default, agent state only updates between backend checkpoints, so a long tool call shows up as one burst at the end. State streaming copies one tool argument into a state key while the model writes it, so the UI shows the answer token by token.

State streaming isn't available on this framework yet. The UI gets the agent's state between checkpoints.

Read-only context

When a value is UI-owned, and the agent should read it but never write it back, use useAgentContext instead of shared state. Examples are the current user, the selected record, or the open screen. It sends values one way, from the UI to the agent, and removes them when the component unmounts.

See Agent Read-Only Context for the full pattern.

How is this guide?