7acadae
CopilotKitDocs
  • Docs
  • Integrations
  • Reference
Get Started
QuickstartCoding Agents
Concepts
ArchitectureGenerative UI OverviewOSS vs Enterprise
Agentic Protocols
OverviewAG-UIAG-UI MiddlewareMCPA2A
Build Chat UIs
Prebuilt Components
CopilotChatCopilotSidebarCopilotPopup
Custom Look and Feel
CSS CustomizationSlots (Subcomponents)Fully Headless UIReasoning Messages
Multimodal AttachmentsVoice
Build Generative UI
Controlled
Tool-based Generative UITool RenderingState RenderingReasoning
Your Components
Display ComponentsInteractive Components
Declarative
A2UIDynamic Schema A2UIFixed Schema A2UI
Open-Ended
MCP Apps
Adding Agent Powers
Frontend ToolsShared State
Human-in-the-Loop
HITL OverviewPausing the Agent for InputHeadless Interrupts
Sub-AgentsAgent ConfigProgrammatic Control
Agents & Backends
Built-in Agent
Backend
Copilot RuntimeFactory ModeAG-UI
Runtime Server AdapterAuthentication
LangGraph (Python)
Your Components
Display-onlyInteractiveInterrupt-based
Shared state
Reading agent stateWriting agent stateInput/Output SchemasState streaming
ReadablesInterruptsConfigurableSubgraphsDeep Agents
Advanced
Disabling state streamingManually emitting messagesExiting the agent loop
Persistence
Loading Agent StateThreadsMessage Persistence
Videos
Video: Research Canvas
Error Debugging & ObservabilityCommon LangGraph issues
Troubleshooting Copilots
Migrate to AG-UI
Observe & Operate
InspectorVS Code Extension
Troubleshooting
Common Copilot IssuesError Debugging & ObservabilityDebug ModeAG-UI Event InspectorHook ExplorerError Observability Connectors
Enterprise
CopilotKit PremiumHow the Enterprise Intelligence Platform WorksHow Threads & Persistence WorkObservabilitySelf-Hosting IntelligenceThreads
Deploy
AWS AgentCore
What's New
Full MCP Apps SupportLangGraph Deep Agents in CopilotKitA2UI Launches with full AG-UI SupportCopilotKit v1.50Generative UI Spec SupportA2A and MCP Handshake
Migrate
Migrate to V2Migrate to 1.8.2
Other
Contributing
Code ContributionsDocumentation Contributions
Anonymous Telemetry
LangGraph (Python)Shared StateIn App Agent Write

Writing agent state

Write to agent's state from your application.

Info

This example demonstrates writing to shared state in the CopilotKit Feature Viewer.

What is this?#

This guide shows you how to write to your agent's state from your application.

When should I use this?#

You can use this when you want to provide the user with feedback about what your agent is doing, specifically when your agent is calling tools. CopilotKit allows you to fully customize how these tools are rendered in the chat.

Implementation#

Run and connect your agent#

You'll need to run your agent and connect it to CopilotKit before proceeding. If you haven't done so already, you can follow the instructions in the Getting Started guide.

If you don't already have an agent, you can use the coagent starter as a starting point as this guide uses it as a starting point.

Define the Agent State#

LangGraph is stateful. As you transition between nodes, that state is updated and passed to the next node. For this example, let's assume that our agent state looks something like this.

agent.py
python
from copilotkit import CopilotKitState
from typing import Literal

class AgentState(CopilotKitState):
    language: Literal["english", "spanish"] = "english"

Use the useAgent hook to read and write state#

useAgent gives you access to the agent, including its state. You can update state by calling agent.setState.

ui/app/page.tsx
tsx
import { useAgent } from "@copilotkit/react-core/v2"; // [!code highlight]

// Example usage in a pseudo React component
function YourMainContent() {
  // [!code highlight:3]
  const { agent } = useAgent({
    agentId: "sample_agent",
  });

  const language = (agent.state.language as string) ?? "english";

  // ...

  const toggleLanguage = () => {
    agent.setState({ language: language === "english" ? "spanish" : "english" }); // [!code highlight]
  };

  // ...

  return (
    // style excluded for brevity
    <div>
      <h1>Your main content</h1>
      {/* [!code highlight:1] */}
      <p>Language: {language}</p>
      <button onClick={toggleLanguage}>Toggle Language</button>
    </div>
  );
}

Give it a try!#

You can now use the setState function to update the agent state and state to read it. Try toggling the language button and talking to your agent. You'll see the language change to match the agent's state.

Info

This video shows the result of npx copilotkit@latest init with the implementation section applied to it!

Advanced Usage#

Re-run the agent with updated state#

The new agent state will be used next time the agent runs. If you want to re-run it manually, use agent.runAgent after updating state.

ui/app/page.tsx
tsx
import { useAgent } from "@copilotkit/react-core/v2"; // [!code highlight]

// ...

function YourMainContent() {
  const { agent } = useAgent({
    agentId: "sample_agent",
  });

  const language = (agent.state.language as string) ?? "english";

  // setup to be called when some event in the app occurs
  const toggleLanguage = () => {
    const newLanguage = language === "english" ? "spanish" : "english";
    agent.setState({ language: newLanguage });

    // [!code highlight:2]
    // re-run the agent with updated state
    agent.runAgent();
  };

  return (
    // ...
  );
}

Intermediately Stream and Render Agent State#

By default, the LangGraph agent state will only update between LangGraph node transitions -- which means state updates will be discontinuous and delayed.

You likely want to render the agent state as it updates continuously.

See predictive state updates.

On this page
What is this?When should I use this?ImplementationAdvanced UsageRe-run the agent with updated stateIntermediately Stream and Render Agent State