State Rendering

What is this?#

AWS Strands agents maintain state as they process tasks. CopilotKit allows you to render this state in your application with custom UI components, which we call Agentic Generative UI.

When should I use this?#

Rendering the state of your agent in the UI is useful when you want to provide the user with feedback about the overall state of a session. A great example of this is a situation where a user and an agent are working together to solve a problem. The agent can store a draft in its state which is then rendered in the UI.

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.

Setup your AWS Strands agent with state#

Configure your Strands agent to maintain state. Here's an example that tracks searches:

agent/main.py

import os
import json
from ag_ui_strands import StrandsAgent, StrandsAgentConfig, ToolBehavior, create_strands_app
from strands import Agent, tool
from strands.models.openai import OpenAIModel

# Create tool that updates state
@tool
def add_search(query: str):
    """Add a search to the agent's list of searches.

    Args:
        query: The search query to add

    Returns:
        Success status and query
    """
    return json.dumps({"success": True, "query": query})

# Extract state from tool arguments
async def searches_state_from_args(context):
    try:
        tool_input = context.tool_input
        if isinstance(tool_input, str):
            tool_input = json.loads(tool_input)
        query = tool_input.get("query", "")
        return {"searches": [{"query": query, "done": True}]}
    except Exception:
        return None

config = StrandsAgentConfig(
    tool_behaviors={
        "add_search": ToolBehavior(
            state_from_args=searches_state_from_args,
        ),
    },
)

model = OpenAIModel(
    client_args={"api_key": os.getenv("OPENAI_API_KEY", "")},
    model_id="gpt-4o",
)

strands_agent = Agent(
    model=model,
    system_prompt="You are a helpful assistant for storing searches. Use the add_search tool to add searches.",
    tools=[add_search],
)

agui_agent = StrandsAgent(
    agent=strands_agent,
    name="strands_agent",
    description="A helpful assistant for storing searches",
    config=config,
)

app = create_strands_app(agui_agent)

Render state of the agent in the chat#

Now we can utilize useAgent with a render function to render the state of our agent in the chat.

app/page.tsx

// ...
import { useAgent } from "@copilotkit/react-core/v2";
// ...

// Define the state of the agent, should match the state schema of your Strands Agent.
type AgentState = {
  searches: {
    query: string;
    done: boolean;
  }[];
};

function YourMainContent() {
  // ...

  // styles omitted for brevity
  useAgent({
    agentId: "strands_agent",
    render: ({ state }) => (
      <div>
        {state.searches?.map((search, index) => (
          <div key={index}>
            {search.done ? "✅" : "❌"} {search.query}{search.done ? "" : "..."}
          </div>
        ))}
      </div>
    ),
  });

  // ...

  return <div>...</div>;
}

Important

The name parameter must exactly match the agent name you defined in your Strands configuration (e.g., searchAgent from above).

Render state outside of the chat#

You can also render the state of your agent outside of the chat. This is useful when you want to render the state of your agent anywhere other than the chat.