For years, AI inside software meant a chat widget bolted onto the corner of an application. You typed, the model responded with text, and you manually translated that output into actions. It was functional, but fundamentally passive. CopilotKit, a Seattle-based startup co-founded by Atai Barkai and Uli Barkai, has argued for years that this model is broken—and in 2026, the developer community is agreeing loudly.
The company’s approach is straightforward: the way forward is to enable agents to live inside applications, understand user context, take actions, and render useful interfaces instead of just returning text blocks. This approach has produced a sharp 2026 shipping cycle covering three distinct infrastructure gaps: knowledge retrieval, testing reliability, and runtime persistence. Each release targets the unglamorous architecture that separates agent demos from production-grade systems.
Before the new tooling makes sense, the protocol layer underneath it needs to. The agentic ecosystem has quietly assembled a three-layer stack. MCP standardizes how agents access external tools and databases. A2A handles coordination between agents. AG-UI, created by CopilotKit, handles the third and previously unaddressed problem: the interaction layer between agents and human users inside software applications.
While MCP and A2A handle context and agent coordination, AG-UI defines the interaction layer between the user, the application, and the agent. It provides transparency, safety, and control at the critical boundary where users interact with agents. Concretely, it enables real-time streaming responses, dynamic UI component generation, bidirectional state synchronization, and human-in-the-loop pauses where agents wait for user confirmation before proceeding.
The protocol is today supported by major AI infrastructure providers like Google, Microsoft, Amazon, and Oracle, as well as popular frameworks including LangChain, Mastra, PydanticAI, and Agno. First-party SDKs cover LangGraph, CrewAI, and others. On the community side, fully supported implementations exist for languages including Kotlin, Go, Rust, and Java. AWS has integrated AG-UI into its FAST examples and Bedrock AgentCore, cementing its role as production infrastructure. The ecosystem expansion into education via DeepLearning.AI signals that the protocol has matured into a standard for full-stack agentic development.
