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
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 freeReading 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:
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:
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 eventDo 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:
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 composable updates its reactive agent ref and your UI re-renders with the new values.
<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.
<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.
<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 AWS Strands (Python) yet
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?