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
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.setStatearrives onRunAgentInput.stateand merges into the variables for the run. - At the start of the run,
AGUIStreamsends aSTATE_SNAPSHOTif the merged variables differ from the state the client sent. - At the end of the run, it sends another
STATE_SNAPSHOTif a tool changedcontext.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.
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:
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. 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 AG2 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?