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
Declare the state with state_schema
Pass a state_schema to AgentFrameworkAgent. The adapter adds the
current shared state to the model's context on every turn, so values the
UI writes with agent.setState(...) reach the model. Without a
state_schema, the agent never sees those writes.
STATE_SCHEMA: dict[str, object] = {
"preferences": {
"type": "object",
"description": (
"User-supplied preferences. Adapt every response to match. "
"Address the user by name when appropriate."
),
"properties": {
"name": {"type": "string"},
"tone": {"type": "string"},
"language": {"type": "string"},
"interests": {"type": "array", "items": {"type": "string"}},
},
},
"notes": {
"type": "array",
"items": {"type": "string"},
"description": (
"Short notes the agent has chosen to remember about the "
"user. Updated by calling `set_notes` with the FULL list."
),
},
}Write state from a tool with predict_state_config
The agent writes state through a tool call. predict_state_config maps a
tool argument to a state key, and the adapter sends the new value to the
UI. The tool itself only returns a string for the model:
from typing import Annotated
from agent_framework import Agent, BaseChatClient, tool
from agent_framework_ag_ui import AgentFrameworkAgent
from pydantic import Field
PREDICT_STATE_CONFIG: dict[str, dict[str, str]] = {
"notes": {
"tool": "set_notes",
"tool_argument": "notes",
},
}
@tool(
name="set_notes",
description=(
"Replace the notes array in shared state with the full updated "
"list. Always pass the FULL list of short note strings "
"(existing notes + any new ones), not a diff. Keep each note "
"short (< 120 chars)."
),
)
def set_notes(
notes: Annotated[
list[str],
Field(
description=(
"The complete updated list of short note strings. "
"Must include every existing note you want to keep "
"plus any new ones."
)
),
],
) -> str:
"""Push the agent-authored notes into AG-UI shared state."""
return f"Notes updated. Tracking {len(notes)} note(s)."
def create_shared_state_read_write_agent(
chat_client: BaseChatClient,
) -> AgentFrameworkAgent:
base_agent = Agent(
client=chat_client,
name="shared_state_read_write_agent",
instructions=SYSTEM_PROMPT, # tells the model to call set_notes
tools=[set_notes],
)
return AgentFrameworkAgent(
agent=base_agent,
name="CopilotKitMSAgentSharedStateReadWriteAgent",
description=(
"Bidirectional shared-state demo. Reads UI-written "
"`preferences` from shared state every turn and writes "
"agent-authored `notes` back via the `set_notes` tool."
),
state_schema=STATE_SCHEMA,
predict_state_config=PREDICT_STATE_CONFIG,
require_confirmation=False,
)The mapped value replaces the state key, so have the tool take the
whole value (the full notes list), not a diff. Tell the model the same
thing in its instructions.
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, `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.
// 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.
# Tells the runtime to stream tool-argument deltas straight into
# `state.document` while `write_document` is still streaming — matches
# LGP's StateStreamingMiddleware setup.
PREDICT_STATE_CONFIG: dict[str, dict[str, str]] = {
"document": {
"tool": "write_document",
"tool_argument": "document",
}
}See State streaming for the full walkthrough,
including the corresponding useAgent subscription on the frontend.
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?