copilotkit-integrations

Connects external agent frameworks to CopilotKit applications via the AG-UI protocol.

Updated May 9, 2026
One-click install
npx skills add https://github.com/SebastienGt/LivingMargin-Google-Deepmind-Hackathon --skill copilotkit-integrations-sebastiengt
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: copilotkit-integrations
Source: https://github.com/SebastienGt/LivingMargin-Google-Deepmind-Hackathon/tree/main/.cursor/skills/copilotkit-integrations
Command: npx skills add https://github.com/SebastienGt/LivingMargin-Google-Deepmind-Hackathon --skill copilotkit-integrations-sebastiengt

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

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 pattern, and port configuration, which varies significantly across frameworks and is easy to get wrong. ## 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, MCP Apps). - Per-Framework Reference Guides: Detailed integration docs covering agent definition, FastAPI server setup, Next.js route configuration, and shared state management for each supported framework. - Common AG-UI Patterns: Ready-to-use frontend patterns for CopilotKitProvider, useAgent shared state, useFrontendTool, useRenderToolCall generative UI, and useHumanInTheLoop approval flows. - Use Case: You have a LangGraph Python agent and want to add a React chat UI with shared state. The skill directs you to the langgraph.md reference showing the CopilotKitState extension, LangGraphAGUIAgent FastAPI endpoint, and LangGraphHttpAgent route configuration. ## Quick Start Ask the agent to connect your LangGraph Python agent to a CopilotKit Next.js frontend using the AG-UI protocol.

Frequently Asked Questions about copilotkit-integrations

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I connect a LangGraph agent to CopilotKit?▼

Wrap your compiled LangGraph graph in LangGraphAGUIAgent and serve it with add_langgraph_fastapi_endpoint on FastAPI. In the Next.js route, use LangGraphHttpAgent from @copilotkit/runtime/langgraph pointing at the agent URL, defaulting to port 8123.

Which CopilotKit integration should I use for my agent framework?▼

Choose based on language and framework: TypeScript agents use Mastra or LangGraph JS integrations, while Python frameworks like CrewAI, PydanticAI, ADK, Agno, and Strands each have dedicated AG-UI adapters. The skill's decision tree maps each framework to its reference guide.

What is the AG-UI protocol in CopilotKit?▼

AG-UI is a streaming protocol enabling bidirectional communication between a CopilotKit frontend and a backend agent. Every integration follows the same pattern: an agent server, a framework-specific AG-UI adapter, a CopilotRuntime client in the Next.js route, and React hooks on the frontend.

Does CopilotKit support Microsoft Agent Framework in .NET?▼

Yes, .NET is supported via the Microsoft.Agents.AI.Hosting.AGUI.AspNetCore package. Register services with AddAGUI, map the endpoint with MapAGUI, and wrap your ChatClientAgent in SharedStateAgent for state management.

How do I share state between a CopilotKit frontend and a Python agent?▼

State sharing depends on the framework: LangGraph extends CopilotKitState, PydanticAI uses StateDeps with StateSnapshotEvent returns, and ADK uses ToolContext.state. Agents emit STATE_SNAPSHOT events that the frontend consumes via the useAgent hook.

Can I orchestrate multiple agents from different frameworks with CopilotKit?▼

Yes, the A2A Middleware pattern lets an orchestrator agent coordinate specialized agents built with different frameworks. A2AMiddlewareAgent from @ag-ui/a2a-middleware wraps the orchestrator and injects a send_message_to_a2a_agent tool for delegation.