CopilotKit🪁

⭐️Introducing AG-UI; The Agent-User Interaction protocol 👾 Bring your AI agents into Frontend applications, and let them interact with users. Launching with day-0 integrations with LangGraph, CrewAI, Mastra, and AG2 - with more partnerships on the way 👀 github.com/ag-ui-protocol… How it works & demo 👇

@chronokaizen @PrimeIntellect How's it going? This looks really cool!

Prototyping for a shipping company (huge project deal) with @CopilotKit and training the model with @PrimeIntellect on shipping quotations based on real time data -- pilot run at the moment.

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 CopilotKit. You'll learn three approaches: Your agent can pick from custom components you build, like charts and forms. It can compose new layouts from a set of building blocks you provide, like rows, cards, and text. Or it can incorporate existing third-party apps, like a whiteboard or a calendar, right inside the conversation. Skills you’ll gain: - Build agents that render custom components like charts and forms on demand - Build an app where the agent and user collaborate on shared data, beyond just the chat window - Place third-party apps like maps, calendars, and whiteboards right in your interface Join and build agents that give users something to see and act on! deeplearning.ai/short-courses/…

Make your Agent speak your UI Many open source SDKs give you a simple chat UI But only @CopilotKit lets you bring fully-immersive Claude and Cursor-like agentic experiences into your own apps. Here's a thread on how to do, it in one sitting 🧵

Your AI stack just stopped being closed. 🔓 TanStack AI now speaks AG-UI client-to-server. - The same client hits any AG-UI server. - Any AG-UI client hits a TanStack server. Zero breaking changes. Migration guide in the tweet below 👇

One of my side quests this week was to build a product feedback agent that can listen in a Slack channel & distribute @linear tickets. As a good disciple of @HamelHusain and @sh_reya, I thought evals-first, so I actually designed the bot to categorize and score the posts, and then made this annotation tool where I could say whether it was good or bad & add a note. Super useful for fast iteration!

Most AI demos fail the same way: the agent lives on one side, the UI on the other. I rebuilt a film greenlighting agent to show what changes when the copilot becomes part of the workflow itself — shared state, generative UI, approval gates. Used @CopilotKit + React. Article 👇 @LakshmiNarayana_U/beyond-chat-building-an-agent-native-greenlight-room-with-copilotkit-and-react-97ed2c2aeb99" target="_blank" rel="nofollow noopener">medium.com/@LakshmiNaraya…

@sofiiiiiasz @ulidabess @WorkOS M C P

great start to @WorkOS’s #MCPNight! excited to see the lightning demos⚡️⚡️

Anthropic's most viral feature is now open-source! Until now, Anthropic's Generative UI capabilities only existed inside its own products. @CopilotKit just shipped Open Generative UI, an open-source implementation of Claude Artifacts that works in any app. The agent generates HTML/SVG at runtime, and CopilotKit streams it token-by-token into a sandboxed iframe inside the app's chat. So the user can watch the UI assemble itself in real time, not after the full response is ready. The sandbox is fully isolated with no access to the parent app, the DOM, or user data. So if the agent hallucinates broken markup or unexpected JavaScript, nothing leaks outside the iframe. Under the hood, the agent does not select from pre-built components. Instead, it generates arbitrary visuals from scratch every time. The output is unconstrained by default, but you can shape it by defining prompt-based skills that teach the agent specific visual formats or guidelines. For instance, a skill prompt can guide the agent toward producing a Chart.js dashboard with proper axis labels and responsive sizing, or an interactive 3D model with rotation controls. The video below shows this in action, and the output quality you see actually comes from the skills layer. Open Generative UI runs on AG-UI, so it works out of the box with LangGraph, CrewAI, Mastra, Google ADK, AWS Strands, and more. It also ships with a standalone MCP server that plugs into Claude Code, Cursor, or any MCP-compatible client. And the entire stack is built on top of CopilotKit, the open-source frontend framework for agents and generative UI. 30k+ GitHub stars, with SDKs for React, Next.js, Angular, and Vue. I have shared the GitHub repo and a live playground in the replies!

More of our customers and partners are asking for gen UI in non-browser surfaces. Think asking for agents to give you diagrams/visuals/other interactive elements in: - Slack - Teams - VS Code (and all its forks) Interesting signal & we are working to be the leader here.

Read more about this shift 👇

Generative UI and AG-UI at Google I/O 👀 It's a signal for where the ecosystem is heading: Agents are moving from text-only chat towards structured UI, app-native workflows, and interfaces that can adapt in real time. We make that practical: github.com/CopilotKit/Cop…

🎉 Generative UI, AG-UI and A2UI at Google I/O Google 'gets' this space, and we love collaborating with them on it. quick brain dump on where Generative Interfaces stand today: 1. All UI will be AI. This is CopilotKit's mantra. Every interaction between humans and technology will be mediated by agentic systems — from agentic SaaS, to Slack agents, to an agentic fridge. Agentic intelligence will be a part of every loop, and many loops will contain an interaction step with a user. 2. GenUI sits on a spectrum. On one end the developer controls the UI at build-time on the other the agent controls the UI at runtime. From tightly controlled, to declarative, to fully open-ended. CopilotKit is the only toolkit with primitives across that whole spectrum. 3. Agents break request-response. The contract that has defined the frontend-backend boundary for 30 years doesn't fit agents. They're long-running, they share control with users, they stream output. This was the original reason we built AG-UI — an event-based transport layer made for the agentic age. 4. Builders feel this pain constantly. Fragile glue code, unclear handoffs, terrible UX wiring agents into frontends. We hear it all the time, and folks are always relieved to learn someone has tackled it. we build this stuff because Generative Interfaces are one of the most meaningful shifts happening in software right now. if we can make starting on it less scary, that's a win github.com/CopilotKit/Cop…

This is all open-source, by the way.

One hook connects any Agent to your frontend Then layer on chat UI, threads, generative UI, voice transcription, tool calls, state sync, HITL, and any AI feature. We make it easy for devs to build fullstack agentic apps. Everything here is built with CopilotKit 👇

I’m happy to share that capturia got the first place on the hackathon of @AITinkerers . Built a tool to display elements in your video while you talk on real time. This used A2UI from @GoogleDeepMind and @CopilotKit and allows to have interactive elements generated on real time while you speak and it can update them too as requested The goal of this project is to allow a person to speak freely and get visual help without struggles or someone else moving elements with an assistant that deeply understands what you need Here is a demo, everything is on real time and recorded directly from capturia.vercel.app Thanks @Richardnotme for bringing the hackathon to Monterrey! It was amazing and pretty challenging

Great overview of what we allow you to build! If it wasn't super clear already 😉

Tools for Devs building with CopilotKit: 1. CopilotKit MCP Server gives coding agents (Cursor, Claude etc.) structured access to docs, code, and examples so that they can generate accurate code, give your AI agents a UI, and help you implement features correctly 2. Inspector built-in debugging tool that gives you full visibility into what's happening between your frontend and agents in real time 3. VS Code Extension Live preview your CopilotKit render hooks, A2UI catalog components, and AG-UI event stream — without leaving VS Code 3. Debug Mode single flag, structured logging across the full stack 4. AIMock mock your entire agentic stack (LLMs, MCP tools, A2A agents) from one config file for testing and more... docs.copilotkit.ai

Entirely open source. github.com/CopilotKit/Cop…

It found Google too 🤷‍♂️

We built an internal tool to find CI vulnerabilities Then @jpr5 made a bot that just scans all of GitHub and submits PRs to harden peoples' security. github.com/jpr5/sentinel