CopilotKit

Introduction

Bring your Deep Agents to your users with CopilotKit via AG-UI.


Deep Agents

Bring your Deep Agents to your users

Give your Deep Agents real user-interactivity using CopilotKit and AG-UI. Build rich, interactive, agent-powered applications with LangChain's Deep Agents framework.

Start the quickstart
What you can build

Build with Deep Agents

The user-facing primitives every Deep Agents integration ships with — pick the one that fits your product and drop the code in.

Generative UI

Render your agent's state, progress, outputs, and tool calls with custom UI components in real-time. Bridges the gap between AI agents and user interfaces.

Human in the Loop

Empower users to guide agents at key checkpoints. Combine the best of AI and human judgment for more reliable and controllable agent behavior.

Shared State

Keep your agent and your app in sync. Your agent can see everything in your app, and your app can react to your agent in real-time.

How it fits together

Architecture

The shape of a CopilotKit + Deep Agents application — from your UI down to the agent runtime.

CopilotKit Deep Agents architecture diagram
Live example

Run Deep Agents in your browser

Two patterns we see most often — drive a SaaS workflow, or collaborate on a canvas with your agent.

A traditional SaaS application enhanced with AI agents. These copilots integrate seamlessly into existing workflows, providing intelligent assistance for specific business processes. Perfect for customer service, sales automation, project management, and domain-specific tasks where users need guided, step-by-step AI assistance.