A frontend SDK for building full-stack agentic applications with generative UI, shared state, and human-in-the-loop workflows.
CopilotKit is a frontend SDK for building agent-native applications with generative UI, shared state, and human-in-the-loop workflows. It provides the tools to connect AI agents directly to user interfaces, enabling dynamic, interactive applications where agents can render UI, manage state, and request user input. The project is also the creator of the AG-UI Protocol, adopted by major companies like Google, LangChain, and AWS.
Frontend and full-stack developers building interactive AI-powered applications, chat interfaces, or agentic workflows that require tight integration between AI logic and dynamic user interfaces.
Developers choose CopilotKit for its comprehensive, integrated approach to building agentic applications, offering features like generative UI, shared state, and human-in-the-loop workflows out of the box. Its backing by the widely adopted AG-UI Protocol ensures compatibility and deep integrations with popular agent frameworks.
The Frontend Stack for Agents & Generative UI. React + Angular. Makers of the AG-UI Protocol
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.
Provides a React-based chat interface with built-in message streaming and tool call support, eliminating the need for custom chat implementation from scratch.
Enables AI agents to generate and update UI components at runtime based on user intent, allowing for highly interactive and adaptive applications.
Offers a shared state layer that both agents and UI components can read and write to in real time, ensuring data consistency across the application.
Allows agents to pause execution to request user input or confirmation, facilitating collaborative and controlled agentic processes.
Built on the AG-UI Protocol adopted by Google and AWS, ensuring deep integrations with popular agent frameworks like LangGraph and CrewAI.
Primarily designed for React, making it unsuitable for projects using other frontend frameworks without significant adaptation or polyfills.
While quick start tools exist, integrating with complex existing agent workflows or custom backends requires understanding the AG-UI Protocol and additional configuration.
Real-time state synchronization and dynamic UI generation can increase bundle size and introduce latency, potentially impacting performance in resource-constrained environments.
As a newer project with rapid development, APIs and documentation may change, posing maintenance challenges for production applications.