Sep 10One Agent, Three Surfaces
Copilot Kit Logo

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
aimock: Deterministic Mock Infra for AI Apps
Eli Berman August 14, 2026
aimock: Deterministic Mock Infra for AI Appsaimock is open-source mock infrastructure for every AI service your app talks to — LLMs, MCP tools, vector DBs, image models, TTS, and more. Write a JSON fixture, run npx aimock, point your API URL at localhost. Tests run offline in milliseconds and are completely deterministic, so zero tokens burned. Now at 1M+ weekly installs and 700+ stars, quietly powering CI at OpenClaw, TanStack, Mastra and the AG-UI protocol. From the team at CopilotKit.
Building a Production-Ready Slack Agent with Channels SDK
Nathan Tarbert and Anmol BaranwalAugust 13, 2026
Building a Production-Ready Slack Agent with Channels SDKWatch Mike Ryan (CopilotKit Engineer) build a production-ready Slack agent, using Mastra, end to end with the Channels SDK. It's the open-source library that brings any AG-UI agent into Slack, Teams, Discord, WhatsApp, and more chat platforms. Learn how an agent goes from a message in a channel to a real response, with tools, rich native messages, and durable memory across a thread.
Claude Managed Agents are now AG-UI compatible
Eli Berman August 12, 2026
Claude Managed Agents are now AG-UI compatibleAnthropic just shipped a full AG-UI integration for Claude Managed Agents (CMA), so you can drop a Managed Agent into any AG-UI-compatible frontend without gluing together your own transport, state sync, and UI primitives. That means React, React Native, Next.js, and Angular on the web, plus Slack, Teams, and other messaging surfaces via the Channels SDK — all with generative UI, streaming, tool calls, and stateful sessions. Everything is open source. Here's where to start and how to ship.
Are you ready?

Stay in the know

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