MCP Apps: Bring MCP Apps to your users!

CopilotKit Expands Capabilities with CrewAI Integration for CoAgents

By Graham McBain
March 27, 2025
CopilotKit Expands Capabilities with CrewAI Integration for CoAgents

The CopilotKit team has been heads down over the last few weeks building out support for CrewAI. We’re excited to share that you can now build an agentic UI for all your Crews using CopilotKit!

CrewAI is one of the fastest growing agent frameworks that is being adopted by enterprises of all shapes and sizes. With this release, teams building with Crew will now be able to integrate Crews into their applications faster and with a better user experience.

More about CrewAI

CrewAI is The Leading Multi-Agent Platform that lets you streamline workflows across industries with powerful AI agents. CrewAI lets you build and deploy automated workflows using any LLM and cloud platform. Crew is more than an agent framework though, they are an entire platform dedicated to making every step of the process of building agents seamless and straightforward.

Your same Crews, but with more functionality!

CrewAI is already one of the most powerful platforms for building enterprise grade multi agent systems. Now with Copilot, CrewAI Crews new features that will improve the user experience. The most powerful part about this new integration is that your frontend developers don't have to learn anything new. If they know how to build with React, they know how to build with CopilotKit.

  • Human in the loop: Complicated user<>agent interactions often require a ping-pong style back and forth. Most often it takes the shape of checklist style interactions like this:
Demo GIF
  • Agentic Generative UI: With Agentic Generative UI, your Crews now have the ability to call on rich components that you've created so your agent's integration into your application feels natural.
Demo GIF
  • Tool Based Generative UI: Tool-based generative UI allows you to render components in the chat and the front end based on the output of tools that your agent calls in the back end.
Demo GIF
  • Shared State: Shared state gives your agent the ability to see what the user sees inside the application. This is really powerful for human agent collaboration.
Demo GIF
  • Predictive State Updates: Sometimes your agent can take up to a few minutes to resolve something that it's searching for. Predictive state updates allow you to predict what the end state of the agent will be and render it in the front end so the user can feel like the application is more responsive and has more trust in what the agent's doing.
Demo GIF

Why is this important?

CrewAI is already one of the most powerful platforms for building an agent on the market today period with support for CrewAI agents. CoPilotKit is now an even more powerful platform for building human agent interactions. Agents are incredibly powerful tools for building enterprise value and they're even more powerful when they can work alongside users to build business value.

We're excited about this partnership and have already seen some incredibly powerful applications built using CrewAI and CoPilotKit.

How to get started?

We've worked really hard to make this as seamless as possible. So if you're already building with CrewAI, you'll be able to put a CopilotKit interface on top of that very quickly.

And if you're new to both CrewAI and CopilotKit, we have some demos that should make it really easy for you to get up and running building a CopilotKit CrewAI agent quickly. We're looking forward to seeing what you build and can't wait to help out if you have any questions.

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.