Shared State

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

What is shared state?

Agentic Copilots maintain a shared state that connects your UI with the agent's execution. This shared state lets you:

  • 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
See this in Inspector

Open Inspector on localhost. Go to Inspect, then Agent. The Current State section shows the agent state as the run proceeds. With Intelligence on, you can also open a thread in Rich Threads and click State to see its saved state.

More detail: Inspector.

When should I use this?

Use shared state when you want the agent and the user to collaborate through the same application 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

Shared state in Strands is prompt-driven

A Strands agent knows only the state that your code copies into its request context. A state key you don't copy never reaches the model, and nothing reports it: the agent answers as if the UI had written nothing. Say in your system prompt what each copied value means.

Copy UI state into the request context

The UI writes state with agent.setState, and it arrives on the AG-UI run input as input_data.state. Copy the parts the model needs into the run's context. The adapter shows that context to the model during the run and restores the native history afterward, including on tool continuations:

src/agents/agent.py
from ag_ui.core.types import Context


def with_state_context(input_data):
    """Copy current UI state into transient AG-UI context, preserving user text.

    The adapter supplies context during model calls and restores native history
    afterward, including tool continuations. Never use state_context_builder to
    prepend application instructions to durable user messages.
    """
    context = list(input_data.context)
    state = input_data.state
    if isinstance(state, dict):
        preferences = _format_preferences_block(state.get("preferences") or {})
        if preferences:
            context.append(
                Context(description="Current user preferences", value=preferences)
            )
    return input_data.model_copy(update={"context": context})

_format_preferences_block turns the preferences object into a short text block for the prompt. Format your own keys the same way.

Apply it before every run

Wrap the StrandsAgent so every request, including tool continuations, passes through with_state_context:

src/agents/agent.py
from collections.abc import AsyncIterator
from contextlib import aclosing
from typing import Any

from ag_ui_strands import StrandsAgent


class _StateContextWrapper:
    """Add transient state context and preserve the adapter's event stream."""

    def __init__(self, delegate: StrandsAgent) -> None:
        self._delegate = delegate

    def __getattr__(self, name: str) -> Any:
        return getattr(self._delegate, name)

    async def run(self, input_data: Any) -> AsyncIterator[Any]:
        # The adapter owns snapshots, including unfinished parallel calls.
        async with aclosing(
            self._delegate.run(with_state_context(input_data))
        ) as events:
            async for event in events:
                yield event

Do not use StrandsAgentConfig(state_context_builder=...) to prepend the state to the user's message. Its output is saved as native message history, so every past message keeps the old state. Existing conversations created that way keep that text; start a new conversation for a clean history.

Send agent writes back to the UI

The agent writes state through a tool. Give the tool a ToolBehavior with state_from_args, and the adapter emits a state snapshot the moment the tool fires, so the UI re-renders without waiting for the text response:

src/agents/agent.py
from ag_ui_strands import StrandsAgent, StrandsAgentConfig, ToolBehavior
from strands import tool


@tool
def set_notes(notes: list[str]):
    """Replace the notes array in shared state with the full updated list.

    Use this whenever the user asks you to remember something, or when
    you have an observation about the user worth surfacing in the UI's
    notes panel. ALWAYS pass the FULL notes list (existing notes + any
    new ones), not a diff. Keep each note short (< 120 chars).

    Args:
        notes: The complete updated list of short note strings.

    Returns:
        Confirmation string for the LLM to summarise back to the user.
    """
    return f"Notes updated. Tracking {len(notes)} note(s)."


shared_state_config = StrandsAgentConfig(
    tool_behaviors={
        "set_notes": ToolBehavior(
            state_from_args=notes_state_from_args,
        ),
    },
)

notes_state_from_args reads the call's tool_input (a JSON string or a dict) and returns {"notes": [...]}, the snapshot the adapter publishes. Pass shared_state_config as config= to StrandsAgent, then wrap that agent in _StateContextWrapper.

Subscribe a component to the agent's state with useAgent. Any time the agent mutates its state, for example via a tool call, the hook fires and your UI re-renders with the new values.

page.tsx
  // Subscribe the component to agent state changes. Any time the agent
  // mutates its state (e.g. via its `set_notes` tool) this hook fires,
  // we re-render, and the sidebar panels reflect the new values.
  const { agent } = useAgent({
    agentId: "shared-state-read-write",
    updates: [UseAgentUpdate.OnStateChanged],
  });

The returned agent.state is just a plain object. Read it like any other piece of React state and render the parts you care about: agent-written notes, structured outputs, progress indicators, anything the agent has put there.

Writing agent state

The same agent object exposes a setState setter. 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.

page.tsx
  // WRITE: every edit in the sidebar goes straight into agent state.
  // On the agent's next turn, `PreferencesInjectorMiddleware` reads this
  // back out of state and adds it to the system prompt — so the UI's
  // writes visibly steer the model.
  const handlePreferencesChange = (next: Preferences) => {
    agent.setState({
      preferences: next,
      notes, // preserve what the agent has written
    } as RWAgentState);
  };

This makes shared state two-way. The UI can also send the agent new inputs, such as preferences, selections, or partial work. These inputs do not go through 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 hint message first:

const { copilotkit } = useCopilotKit();

agent.setState({ language: newLanguage });
agent.addMessage({
  id: crypto.randomUUID(),
  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. The demo on this page wires the agent's outputs into a small card component and feeds user edits back through setState.

notes-card.tsx
// Read-side render: this card reflects the agent-authored `notes` slice
// of shared state. The parent page passes `state.notes` in; we never
// touch agent state ourselves — we just render it. The Clear button is
// a small write-back, exposed as an `onClear` prop.
export function NotesCard({ notes, onClear }: NotesCardProps) {
  return (
    <Card data-testid="notes-card" className="w-full">
      <CardHeader>
        <div className="flex items-start justify-between gap-3">
          <div className="space-y-1.5">
            <CardTitle>Agent Scratch pad</CardTitle>
            <CardDescription>
              The agent writes here via its{" "}
              <code className="font-mono text-[11px] text-[#010507] dark:text-foreground">
                set_notes
              </code>{" "}
              tool. The UI re-renders from shared state.
            </CardDescription>
          </div>
          {notes.length > 0 && (
            <Button
              type="button"
              onClick={onClear}
              data-testid="notes-clear-button"
              variant="destructive"
              size="sm"
              className="uppercase tracking-[0.14em] text-[10px]"
            >
              Clear
            </Button>
          )}
        </div>
      </CardHeader>

      <CardContent>
        {notes.length === 0 ? (
          <div
            data-testid="notes-empty"
            className="text-sm text-[#838389] italic min-h-[160px] flex items-center justify-center text-center px-4 border border-dashed border-[#E9E9EF] rounded-xl bg-[#FAFAFC] dark:text-muted-foreground dark:border-border dark:bg-muted"
          >
            the agent will make observations about you and note them here!
          </div>
        ) : (
          <ul
            data-testid="notes-list"
            className="space-y-2 text-sm text-[#010507] dark:text-foreground"
          >
            {notes.map((note, i) => (
              <li
                key={i}
                data-testid="note-item"
                className="flex gap-2 rounded-lg border border-[#E9E9EF] bg-[#FAFAFC] px-3 py-2 dark:border-border dark:bg-muted"
              >
                <span className="text-[#838389] font-mono text-xs leading-5 select-none dark:text-muted-foreground">
                  {String(i + 1).padStart(2, "0")}
                </span>
                <span className="flex-1">{note}</span>
              </li>
            ))}
          </ul>
        )}
      </CardContent>
    </Card>
  );
}

Nothing about this is chat-specific: useAgent works in any component under <CopilotKit>, so you can render agent.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.

Streaming partial state updates

By default, agent state only updates between backend checkpoints, so a long-running tool call appears as one big burst at the end. State streaming copies one tool argument into a state key while the model writes it. 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 the 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.

See Agent read-only context for the full pattern.

How is this guide?