MCP Apps: Bring MCP Apps to your users!

AG-UI Is Redefining the Agent–User Interaction Layer
By Nathan Tarbert
October 30, 2025

The AG-UI Protocol continues to surge - and with it, a new standard is forming across the agentic landscape.

AG-UI isn’t just another SDK or framework that has emerged. It’s an open protocol for agent <> user communication, enabling real-time collaboration between humans and agents across any app, platform, or framework.

In the simplest form, it’s the bridge between the agent and the user.

A little bit of a backstory - what started as an internal solution inside the CopilotKit ecosystem, has grown into an open-source movement - now being adopted, extended, and accelerated by large scale teams across the industry.

“The future of agents isn’t one company or one platform - it’s an agentic ecosystem connected by protocols.”

CopilotKit Team

The Protocol Triangle: MCP + A2A + AG-UI

__wf_reserved_inherit

Agent Stack Triangle
Together, MCP, A2A, and AG-UI form what we call the Protocol Triangle that equals the new foundation of the agentic ecosystem.

Each protocol plays a unique but connected role:

  1. MCP → defines how agents communicate with tools and APIs
  2. A2A → defines how agents communicate with other agents
  3. AG-UI → defines how agents communicate with users

This triad enables a new generation of collaborative systems, where humans, agents, and applications share context, take actions, and learn together in real time.

Highlights from the Past Month

The AG-UI and CopilotKit ecosystem has been growing at an unprecedented pace. A few key milestones:

  • Google’s ADK officially joined the AG-UI ecosystem - releasing their integration and enabling ADK agents to collaborate with users via the AG-UI protocol.
__wf_reserved_inherit
  • The “Fullstack Agents” Hackathon SF brought developers together to build with MCP, A2A, and AG-UI - showing the power of multi-agent collaboration.
__wf_reserved_inherit
  • CopilotKit surpassed 2 million agent-user interactions per week, doubling in just two weeks.
__wf_reserved_inherit
  • AG-UI crossed 9,000 GitHub stars ⭐️, one of the fastest-growing open-source protocol projects in the space.
  • AG-UI + CopilotKit hit 120,000 weekly installs - an explosive milestone that shows how fast developers are adopting this new protocol layer.
__wf_reserved_inherit

Weekly installs (Oct 2024 → Sep 2025)

The Handshake 🤝 Heard Around the Ecosystem

__wf_reserved_inherit

This month also marked the official handshake between A2A and AG-UI - connecting agent-to-agent and agent-to-user communication layers for the first time.

And two other giants 🧐 - (you’ll have to guess who they are 😁) - are now actively building their own integrations. More on that soon.

The Bigger Picture

This isn’t just about numbers. It’s about interoperability becoming inevitable.

Developers are no longer constrained by silos — they can now connect agents, apps, and humans under one shared language of interaction.

AG-UI’s rapid adoption signals something bigger:

The agentic web is becoming standardized.

What’s Next

The CopilotKit team and AG-UI community are already working on what’s next:

  • Expanding SDK support - now including TypeScript, Python, Kotlin, Java, and Golang
    • Rust (coming soon)
  • Deepening integrations across MCP and ADK
  • Designing new collaboration features that make agent-user experiences more intuitive, shared, and human

If you’re building agents, or platforms where humans and agents collaborate - AG-UI is the protocol to watch.

Explore More:

Follow CopilotKit on Twitter and say hi, and if you'd like to build something cool, join our active Discord community of agentic builders.

Happy Building!

Top posts

See All
The Developer's Guide to Generative UI in 2026
Anmol Baranwal and Nathan TarbertJanuary 29, 2026
The Developer's Guide to Generative UI in 2026AI agents have become much better at reasoning and planning. The UI layer has mostly stayed the same, and it is holding back the experience. Most agent experiences still rely on chat, even when the task clearly needs forms, previews, controls, or step-by-step feedback. Generative UI is the idea that allows agents to influence the interface at runtime, so the UI can change as context changes. This is usually done through UI specs like A2UI, Open-JSON-UI, or MCP Apps. We'll break down Generative UI, the three practical patterns, and how CopilotKit supports them (using AG-UI protocol under the hood).
Bring MCP Apps into your OWN app with CopilotKit & AG-UI
Anmol Baranwal and Nathan TarbertJanuary 22, 2026
Bring MCP Apps into your OWN app with CopilotKit & AG-UIToday, we are excited to announce CopilotKit’s support for MCP Apps. Now, MCP servers can finally ship an interactive UI that works out of the box in real agent applications.
How to build a Frontend for LangChain Deep Agents with CopilotKit!
Anmol Baranwal and Nathan TarbertJanuary 20, 2026
How to build a Frontend for LangChain Deep Agents with CopilotKit!LangChain recently introduced Deep Agents: a new way to build structured, multi-agent systems that can plan, delegate, and reason across multiple steps. It comes with built-in planning, a filesystem for context, and subagent spawning. But connecting that agent to a real frontend is still surprisingly hard. Today, we will build a Deep Agents powered job search assistant and connect it to a live Next.js UI with CopilotKit, so the frontend stays in sync with the agent in real time.
Are you ready?

Stay in the know

Subscribe to our blog and get updates on CopilotKit in your inbox.