CopilotKit🪁 @CopilotKit

All UI will be AI. AI Agents need generative UI to EXPRESS not another paragraph of text.

Shubham Saboo @Saboo_Shubham_

a day ago

x.com/i/article/2057…

38 133 1K 894K 3K

One hook connects any agent to your frontend From there the possibilities are endless. Headless UI, threads, frontend tool calls, shared state, human in the loop, and generative UI. Docs ↓ docs.copilotkit.ai/reference/v2/h…

Quickstart: docs.copilotkit.ai/strands/quicks… Start in minutes, either from a starter template or by wiring CopilotKit into your existing Strands agent.

AWS Strands 🤝 AG-UI @AWS Strands TypeScript Agents are now AG-UI compatible 🧬 Thanks to a contribution by Jack Stevenson from AWS' PACE team 🔥 Bring your Strands Agents into rich fullstack agentic applications with Generative UI, including: - Chat UI: pre-built or fully headless UI - Generative UI (controlled, declarative, open) - State sync between agent <> app - Human-in-the-loop - Frontend tool calls - Threads ...and more! All the building blocks you need to take your agents from the backend and into a fullstack agentic application. Try it live: dojo.ag-ui.com/aws-strands-ty…

The Future of AG-UI - Any Frontend (Slack, MS Teams, Discord etc.) x.com/i/broadcasts/1…

Watch the 1 hour course by @ataiiam and @AndrewYNg: deeplearning.ai/courses/build-…

Generative UI is changing EVERY app. Here's how you can start building agents that respond to users with custom UIs like charts, forms, and whiteboards, generated on demand 👇 1. Watch @DeepLearningAI's course 2. Read @Saboo_Shubham_'s article You'll learn three approaches that turn your agents into interactive fullstack apps. Save this for later.

Shubham Saboo @Saboo_Shubham_

a day ago

x.com/i/article/2057…

38 133 1K 894K 3K

This is what I'm talking about 👇 Back in the day enterprise custom dashboards took months to build, now agents can build it on demand.

Shubham Saboo @Saboo_Shubham_

a day ago

x.com/i/article/2057…

38 133 1K 894K 3K

Generative UI isn't a feature, it's a dial. One end: the agent picks from your components. Other end: it builds UI you never wrote. AG-UI standardizes how the agent talks to your frontend - CopilotKit renders the actual UI

Shubham Saboo @Saboo_Shubham_

a day ago

x.com/i/article/2057…

38 133 1K 894K 3K

Build with AG-UI and Microsoft Agent Framework: learn.microsoft.com/en-us/agent-fr…

CopilotKit at Microsoft Build 2026! Had a great time joining the Microsoft Agent Framework team to show builders AG-UI, Microsoft Agent Harness and CopilotKit All UI will be AI - and we are determined to keep bringing the best Frontend + Generative UI experiences to the Microsoft Agent Ecosystem. Catch CopilotKit on stage at the Agents in AI Foundry Session: build.microsoft.com/en-US/sessions…

keyboard_arrow_left Previous keyboard_arrow_right Next

Entirely open source on GitHub: github.com/CopilotKit/Cop…

Microsoft just mentioned AG-UI at Build 2026 TL;DR - Agent UX is moving into all UI CopilotKit helps teams ship that layer with chat, generative UI, human approvals, shared state, and production-ready React components. Article below breaks down how 👇

Shubham Saboo @Saboo_Shubham_

a day ago

x.com/i/article/2057…

38 133 1K 894K 3K

Anthropic's in trouble, again! They spent years building what's now fully open-source. What made Claude feel different from a normal app is that the agent could act inside the interface instead of only talking in a chat box. For instance, Claude Artifacts let an agent render real UI, charts, dashboards, and interactive components that assemble live inside the response. Every major AI product tried to replicate it. But the problem was that unlike reasoning, planning, tool-calling, etc., none of it shipped natively with LangGraph, CrewAI, or Google ADK. So teams started building an owned version that required engineering the entire interface layer from scratch. Most teams, however, just settled for shipping the agent as a backend API in a chat box since rendering the UI is only one piece of it. To actually make it work, the interface layer also needed real-time streaming, state kept in sync between agent and UI, conversations that persist across sessions, and reconnection when a user refreshes mid-run. @CopilotKit is now the only open-source framework that actually lets you build your own full-stack Claude-like apps. It decouples the agent from the interface, talking over AG-UI (an open protocol for agent-to-user communication). Being a standard protocol, the frontend never needs to know whether it is talking to a LangGraph or a CrewAI agent. You can change the backend anytime and the UI will never notice. In practice, CopilotKit's interface layer gives several pre-implemented React building blocks that wire the agent directly into the app, like: - generative UI, so the agent renders real components instead of text - chat windows, sidebars, and popups, or a fully headless setup - shared state, so the agent and app stay in sync - human-in-the-loop approvals, where the agent waits before acting - persistent threads that store the whole session, including the agent-user interactions and generated UI, not just text And because that full history is captured, those interactions can feed a self-learning layer that also improves the agent from real usage over time. The interface layer that Anthropic spent years engineering in-house is now literally available to any developer/team. CopilotKit is open-source with 30k+ GitHub stars, and AG-UI, the protocol underneath, is already supported across every major agent framework: LangGraph, CrewAI, Mastra, Google ADK, and more. CopilotKit GitHub repo → github.com/CopilotKit/Cop… (don't forget to star it ⭐ ) If you want to go deeper, I found a detailed breakdown by Shubham Saboo recently on the three Generative UI patterns, with implementation. Read it below.

Shubham Saboo @Saboo_Shubham_

a day ago

x.com/i/article/2057…

38 133 1K 894K 3K

Interesting new course from @AndrewYNg on building agents with generative UI. deeplearning.ai/courses/build-… Built in partnership with @CopilotKit and taught by @ataiiam, co-founder of CopilotKit. @CopilotKit

Andrew Ng @AndrewYNg

4 weeks ago

New course: Build agents that respond to users with not only plaintext, but custom UIs like charts, forms, and whiteboards, generated on demand and displayed right in the chat. This short course is built in partnership with @CopilotKit and taught by @ataiiam, co-founder of

104 232 1K 204K 1K

seeing AG-UI & CopilotKit featured onstage at Build was🔥🔥 your agent deserves a better frontend than the TUI

@sofiiiiiasz @swyx @aiDotEngineer Wow at these artisanal bullet point icons 🤩

#MicrosoftBuild day 2 highlights: ✤ meeting @swyx & getting excited for @aiDotEngineer world’s fair in july ✻ seeing the @CopilotKit x MSFT Agent Harness on stage ✸ the beautiful weather at fort mason today!

Fantastic writeup on Generative UI by @Saboo_Shubham_ Quite a few mentions of CopilotKit 🎉

Shubham Saboo @Saboo_Shubham_

a day ago

x.com/i/article/2057…

38 133 1K 894K 3K

Generative UI has just gone beyond traditional web. ✨ We got it working in Slack, Teams, Google Chat, Discord, and beyond. Going live tomorrow to walk through our challenges and how we got around them. If this is something you need, we'd love to hear from you. We are opening early access today. Early access form 👉 go.copilotkit.ai/beyond-the-web… Register for the event 👉 luma.com/copilo-61s7