What problem does it solve? Wiring a backend agent framework like LangGraph, CrewAI, or PydanticAI into a CopilotKit frontend requires matching the correct AG-UI adapter, client class, server endpoint, and port for each framework, and getting any of these wrong breaks the streaming connection between agent and UI. ## Core Features & Use Cases - Framework Decision Tree: Routes you to the correct integration guide based on language (Python, TypeScript, .NET) and framework (LangGraph, CrewAI, PydanticAI, Mastra, ADK, LlamaIndex, Agno, Strands, Microsoft Agent Framework, A2A). - Per-Framework Reference Guides: Detailed integration docs covering agent definition, FastAPI server setup, Next.js route configuration, and shared state patterns for each supported framework. - Common AG-UI Patterns: Ready-to-use snippets for CopilotKitProvider, useAgent shared state, useFrontendTool, useRenderToolCall generative UI, and useHumanInTheLoop approval flows. - Use Case: You have a LangGraph Python agent and need it to drive a React canvas. The skill directs you to the langgraph.md reference, where you wrap the graph with LangGraphAGUIAgent, serve it via add_langgraph_fastapi_endpoint on port 8123, and connect it in route.ts with LangGraphHttpAgent. ## Quick Start Ask the agent to connect your LangGraph Python agent to a CopilotKit Next.js frontend using the AG-UI protocol.
