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
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 freeReading agent state
Turn on get_shared_state and tell the model to read it
Antigravity sets an agent's instructions once, when the harness session
starts, and the adapter forwards only the user's messages. Shared state
therefore never reaches the prompt on its own. Instead, pass
experimental_app_state=True to AntigravityAgent. It gives the agent a
built-in get_shared_state() tool that returns the thread's shared state: what the UI sent with the current run (including edits made
with agent.setState), or what a server tool last stored, whichever is
newer. Say in the system instructions when to call it:
READ_WRITE_PROMPT = (
"You are a helpful, concise assistant. Call `get_shared_state` before "
"every answer. Its `preferences` object holds the user's name, preferred "
"tone, language and interests, which the user edits in the app: always "
"respect them, and address the user by name when you know it. Its "
"`notes` list holds what you have remembered so far. "
"When the user asks you to remember something, or when you observe "
"something worth surfacing in the UI, call `set_notes` with the FULL "
"updated list of short note strings (existing notes + new)."
)
def shared_state_read_write_agent():
return build(
system_instructions=READ_WRITE_PROMPT,
tools=[set_notes],
experimental_app_state=True,
)
The tool is silent: it emits no TOOL_CALL_* events, so no tool card
appears in the chat. A tool of your own with the same name replaces it.
Write state from a server tool
Server tools are plain Python functions passed as tools=[...]. Inside
one, the adapter's experimental_get_state() returns the thread's shared state and
experimental_set_state() replaces it. experimental_set_state() streams a STATE_SNAPSHOT to the
browser straight away, before the tool's own result, so any component
subscribed with useAgent re-renders while the agent is still running.
def set_notes(notes: list[str]) -> str:
"""Replace the notes array in shared state with the full updated list.
Use this tool 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).
"""
experimental_set_state({**experimental_get_state(), "notes": notes})
return "Notes updated."
Spread experimental_get_state() into the new value, as above: experimental_set_state() replaces
the whole object, so leaving it out drops the keys the UI owns, such as
preferences. Both helpers work only inside a server tool, where the
adapter knows which thread the call belongs to. Called anywhere else, they
raise.
The model sees state only when it asks
Other frameworks can fold the UI's state into the system prompt on every
run. With Antigravity the model has to call get_shared_state. If the
instructions do not tell it to, UI edits do not reach that answer.
Experimental
experimental_app_state, experimental_get_state() and
experimental_set_state() are experimental. Their names and behaviour may
change in a later release of the adapter.
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.
// 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.
// WRITE: every edit in the sidebar goes straight into agent state.
// On the agent's next turn, the model reads this back out of state
// through the adapter's built-in `get_shared_state` tool — 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.
// 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?