What problem does it solve? Integrating AI agents into a React application requires wiring up runtimes, chat components, frontend tools, and interrupt handling across multiple CopilotKit v2 packages, and this Skill provides the exact API patterns and code templates to do it correctly. ## Core Features & Use Cases - Runtime Setup: Create CopilotRuntime endpoints with Hono or Express, register LangGraph agents, and configure middleware, CORS, and transcription. - Chat UI & Tools: Add CopilotChat, CopilotPopup, or CopilotSidebar components, register frontend tools with useFrontendTool, and share app state via useAgentContext. - Interrupts & Rendering: Handle agent interrupts with useInterrupt, build human-in-the-loop approvals with useHumanInTheLoop, and render tool calls with useRenderTool. - Use Case: Add a sidebar chat to a Next.js app that lets an agent highlight spreadsheet cells in the browser and ask the user for approval before executing destructive actions. ## Quick Start Add a CopilotKit sidebar chat connected to my LangGraph agent and register a frontend tool the agent can call in the browser.