Reading agent state
Read the realtime agent state in your native application.
This video shows the result of npx copilotkit@latest init with the
implementation section applied to it.
What is this?#
You can easily use the realtime agent state not only in the chat UI, but also in the native application UX.
CopilotKit consumes AG-UI protocol events streamed by AG2 over
/chat. See the
AG2 AG-UI integration docs
.
When should I use this?#
You can use this when you want to provide the user with feedback about your agent's state. As your agent's state updates, you can reflect these updates natively in your application.
Implementation#
Run and connect your agent#
Start your AG2 backend and connect your CopilotKit frontend to the AG-UI /chat endpoint.
Define the Agent State#
Create your AG2 backend with ContextVariables and emit StateSnapshotEvent whenever the state changes:
from typing import Annotated
from ag_ui.core import EventType, StateSnapshotEvent
from fastapi import FastAPI, Header
from fastapi.responses import StreamingResponse
from autogen import ContextVariables, ConversableAgent, LLMConfig
from autogen.ag_ui import AGUIStream, RunAgentInput
def read_state(context: ContextVariables) -> dict:
return context.get("agent_state", {"language": "english"})
def write_state(context: ContextVariables, state: dict) -> StateSnapshotEvent:
context["agent_state"] = state
return StateSnapshotEvent(type=EventType.STATE_SNAPSHOT, snapshot=state)
agent = ConversableAgent(
name="assistant",
system_message=(
"You are a helpful assistant for tracking language. "
"Always respond in the current language."
),
llm_config=LLMConfig({"model": "gpt-5.4-mini"}),
)
@agent.register_for_llm(description="Update the language in shared state.")
def set_language(
context: ContextVariables,
language: Annotated[str, "language such as english or spanish"],
) -> StateSnapshotEvent:
return write_state(context, {"language": language.lower()})
agent.register_for_execution(name="set_language")(set_language)
stream = AGUIStream(agent)
app = FastAPI()
@app.post("/chat")
async def run_agent(
message: RunAgentInput,
accept: str | None = Header(None),
):
return StreamingResponse(
stream.dispatch(message, accept=accept),
media_type=accept or "text/event-stream",
)
Use the useAgent Hook#
With your agent connected and running all that is left is to call the useAgent hook, pass the agent's ID, and optionally provide an initial state.
// Define the agent state type, should match the actual state of your agent
type AgentState = {
language: "english" | "spanish";
}
function YourMainContent() {
// [!code highlight:4]
const { agent } = useAgent({
agentId: "my_agent", // MUST match the agent name in CopilotRuntime
initialState: { language: "english" } // optionally provide an initial state
});
// ...
return (
// style excluded for brevity
<div>
<h1>Your main content</h1>
{/* [!code highlight:1] */}
<p>Language: {agent.state.language}</p>
</div>
);
}
The agentId parameter must exactly match the agent name you defined in your CopilotRuntime configuration (e.g., my_agent from the quickstart).
The agent.state in useAgent is reactive and will automatically update when the agent's state changes.
Give it a try#
As the agent state updates, your state variable will automatically update with it. In this case, you'll see the
language set to "english" as that's the initial state we set.
Rendering agent state in the chat#
You can also render the agent's state in the chat UI. This is useful for informing the user about the agent's state in a
more in-context way. To do this, you can use the useAgent hook with a render function.
// Define the agent state type, should match the actual state of your agent
type AgentState = {
language: "english" | "spanish";
};
function YourMainContent() {
// ...
// [!code highlight:7]
useAgent({
agentId: "my_agent",
render: ({ state }) => {
if (!state.language) return null;
return <div>Language: {state.language}</div>;
},
});
// ...
}
The name parameter must exactly match the agent name you defined in your
CopilotRuntime configuration (e.g., my_agent from the quickstart).
The agent.state in useAgent is reactive and will automatically update when
the agent's state changes.
Intermediately Stream and Render Agent State#
By default, AG2 state updates are visible to CopilotKit whenever your backend emits StateSnapshotEvent.
For smoother long-running workflows, emit additional intermediate snapshots from your backend tools.