State Rendering

Render your agent's state with custom UI components in real-time.

What is this?

State rendering lets you build UI that reflects your agent's state in real-time. As your agent progresses through nodes and emits state updates, your frontend renders those changes, showing progress, drafts, or intermediate results.

When should I use this?

Use state rendering when you want to:

  • Show real-time progress (e.g. "Researching... 2/5 complete")
  • Display drafts that update as the agent works
  • Build dashboards that reflect agent state
  • Render structured output outside of the chat

How it works in code

On the frontend, subscribe to the agent's state. Each time the backend forwards a fresh value, your component re-renders with the latest partial output. useAgent returns an agent ref; read agent.value?.state in script or let templates unwrap the ref. Keep the provider in an ancestor SFC.

src/components/ResearchProgress.vue
<script setup lang="ts">
import { computed } from "vue";
import { useAgent, UseAgentUpdate } from "@copilotkit/vue/v2";

type ResearchState = { status?: string; draft?: string; completed?: number; total?: number };

const { agent } = useAgent({
  agentId: "researcher",
  updates: [UseAgentUpdate.OnStateChanged, UseAgentUpdate.OnRunStatusChanged],
});

const state = computed(() => (agent.value?.state ?? {}) as ResearchState);
</script>

<template>
  <section aria-live="polite">
    <p>{{ state.status ?? "Idle" }}</p>
    <progress :value="state.completed ?? 0" :max="state.total ?? 1" />
    <article v-if="state.draft">{{ state.draft }}</article>
  </section>
</template>
src/App.vue
<script setup lang="ts">
import { CopilotChat, CopilotKitProvider } from "@copilotkit/vue/v2";
import ResearchProgress from "./components/ResearchProgress.vue";
</script>

<template>
  <CopilotKitProvider runtime-url="/api/copilotkit">
    <ResearchProgress />
    <CopilotChat agent-id="researcher" />
  </CopilotKitProvider>
</template>

On the backend, a state-streaming mapping forwards a tool argument into a state key while the model writes it. Some frameworks provide that as middleware. Direct SDK adapters can emit STATE_SNAPSHOT events from their streaming loop. Either way, the UI can watch the answer assemble token-by-token rather than appearing in one burst between checkpoints.

Install the CrewAI AG-UI package

pip install ag-ui-crewai litellm

Declare the state key

src/agents/shared_state_streaming.py
from ag_ui_crewai import CopilotKitState


class SharedStateStreamingState(CopilotKitState):
    document: str = ""

Map the tool argument to the state key

Call copilotkit_predict_state with one StateItem before the model call. While the model streams write_document, CopilotKit copies the partial document argument into the document state key. Wrap the call in copilotkit_stream, or nothing streams until the turn ends.

src/agents/shared_state_streaming.py
from crewai.flow.flow import Flow, start
from litellm import acompletion

from ag_ui_crewai import StateItem, copilotkit_predict_state, copilotkit_stream


class SharedStateStreamingFlow(Flow[SharedStateStreamingState]):
    @start()
    async def write(self) -> None:
        await copilotkit_predict_state(
            [
                StateItem(
                    state_key="document",
                    tool="write_document",
                    tool_argument="document",
                )
            ]
        )
        tools = [*self.state.copilotkit.actions, WRITE_DOCUMENT_TOOL]
        response = await copilotkit_stream(
            await acompletion(
                reasoning_effort="none",
                allowed_openai_params=["reasoning_effort"],
                model="openai/gpt-6-luna",
                messages=[
                    {"role": "system", "content": SYSTEM_PROMPT},
                    *self.state.messages,
                ],
                tools=tools,
                parallel_tool_calls=False,
                stream=True,
            )
        )

WRITE_DOCUMENT_TOOL is a plain OpenAI-format tool schema with one required document string argument.

Persist the final value

When a Flow method finishes, its state becomes the single source of truth. The streamed predictions are not written to self.state, so assign the final value yourself. Otherwise it is overwritten when the method completes.

src/agents/shared_state_streaming.py
        # Still inside write(), after the model call (needs `import json`)
        message = response.choices[0].message
        self.state.messages.append(message)
        calls = message.get("tool_calls") or []
        write_call = next(
            (
                call
                for call in calls
                if call.get("function", {}).get("name") == "write_document"
            ),
            None,
        )
        if write_call is None:
            return

        arguments = json.loads(
            write_call.get("function", {}).get("arguments") or "{}"
        )
        document = arguments.get("document")
        self.state.document = document if isinstance(document, str) else ""

The showcase Flow then appends a role: "tool" message, calls copilotkit_emit_tool_result, and asks the model for a one-line confirmation. See src/agents/shared_state_streaming.py.

Emit progress without a tool argument

To show progress that is not a tool argument, assign the value and call copilotkit_emit_state after each sub-step:

agent.py
from ag_ui_crewai import copilotkit_emit_state

for step in steps:
    self.state.observed_steps = [*self.state.observed_steps, step]
    await copilotkit_emit_state(self.state)
    await asyncio.sleep(1)
shared_state_streaming.py
class SharedStateStreamingState(CopilotKitState):
    document: str = ""


class SharedStateStreamingFlow(Flow[SharedStateStreamingState]):
    """Predict write_document arguments into state, then persist the result."""

    @start()
    async def write(self) -> None:
        await copilotkit_predict_state(
            [
                StateItem(
                    state_key="document",
                    tool="write_document",
                    tool_argument="document",
                )
            ]
        )

Ask the researcher agent to write a report. The status line and the progress bar change while the agent runs, and the draft text grows as the tokens arrive.

Treat agent state as untrusted external data. Validate it before using it for privileged actions, and avoid putting secrets in state that is streamed to the browser.

How is this guide?