Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

🎉 Introducing 𝙾𝚙𝚎𝚗 𝙱𝚘𝚝 An open source Grok Bot that works with ANY agent harness, designed for real companies. It includes: - AI Coworkers - Generative UI - Computer use (remote/local) - Agent-human handoffs - Full data recording, owned by you Repo → We're using this internally at CopilotKit🪁... show more

Atai Barkai

9,363 subscribers

858,321 views • 1 month ago •via X (Twitter)

Science & Technology Education News & Politics

Anya Rossi• Live Now

Private livecam show

55 Comments

Atai Barkai1 month ago

See more: Note: 𝙾𝚙𝚎𝚗 𝙱𝚘𝚝 is in alpha and we’re actively building this out.

Atai Barkai1 month ago

🧵 Bring any AG-UI agent OpenBot doesn't care what your agent is built with. If it speaks AG-UI, it's a Bot. Powered by the newly released Channels SDK. Includes: Google ADK, AWS Strands, MS Agent Framework, LangChain, CrewAI, Mastra, Pydantic AI, Claude Agent SDK and more.

Atai Barkai1 month ago

🧵 Enterprise Security Every Bot gets its own computer with separate browser, logins and files. One Bot can't read another's files or reuse its sessions.

Atai Barkai1 month ago

🧵 Governance Open Bot logs everything such that you can find out not just what happened, but who made the decision and why it was made. Instead of just the what, it logs the who, what and when.

Atai Barkai1 month ago

🧵 Threads, memory, and learning 1/ Threads persist, which are powered by CopilotKit Intelligence, and tied to the person, not the browser. Close the tab, come back tomorrow, pick up right where you left off. 2/ Memory stays updated. New facts replace old ones instead of piling up next to them. It's recall, not a transcript. 3/ A learning agent reads your Bot's threads, notices patterns, and drafts new skills for it. It proposes and you can approve. 4/ You can see what your Bots are up to: active users, event volume, tool usage, error rate, p95 latency, tokens, duration, memory velocity.

tobi lutke1 month ago

Congrats. Needs bash and package manager though. Gvisor is a good pick.

Atai Barkai1 month ago

It's coming

Ravi Ojha1 month ago

damn people are shipping at crazy speed.. saw a couple opensource versions of grok bot already and they're all quite complete

Atai Barkai1 month ago

Our team ships like crazy, but several things are unique here, as mentioned in each thread. There's a lot under the hood.

Ian1 month ago

What you built looks cool, but Claude just did a deep dive analysis for me and verified that it cannot be used without a commercial CoPilotKit account, so not truly free 100% open source given this test fixture comment ("there is no runtime without Intelligence") and a throw in config.ts, both invisible from the README, the LICENSE and the product page.

Atai Barkai1 month ago

Dave put it well

Uli Barkai🪁1 month ago

Nice leveraging of AG-UI for one more important form factor Team ships fast 💨

Ujjal Bhattacharjee1 month ago

Nice work - we need a lot of oss

Atai Barkai1 month ago

Thanks, I'm with you 100%.

kitze 🛠️ tinkerer.club1 month ago

oh man give it a cool lobster logo that would be fire

Sam Julien1 month ago

Really interested for folks' feedback on this one. Having an open platform for context-rich agentic coworkers feels like a phase shift to me.

Dan1 month ago

Nice! I thought of calling sub8 🐙 "OpenBot" at first but changed my mind. Project looks great Atai 👏

Atai Barkai1 month ago

Thank you!

Dan1 month ago

keep building! let me know if you have any issues clicking the VMs. I got them working to perfection with Claude, Grok Build and local models.

Atai Barkai1 month ago

Thanks for sharing.

Nathan Tarbert1 month ago

Amazing work! It's impressive how fast the team ships!

parsa1 month ago

copilotkit cookin

Atai Barkai1 month ago

True

Ziwen1 month ago

Love this! I was about to create one if no one does

Contextable1 month ago

Amazing stuff again from CopilotKit!

Aymane1 month ago

Congrats on the launch!!

Atai Barkai1 month ago

Thanks, really appreciate the support!

MultiAgent Max1 month ago

Something new to try.

Atai Barkai1 month ago

Yes, and we would love your feedback!

Funkpopo1 month ago

Amazing work and amazing speed.

Yishai Cohen1 month ago

Nice work!

Eli Berman🪁1 month ago

AI Coworkers are truly the next form-factor for agents. Awesome release 👏

Sebastian Heyneman1 month ago

Can I use my chatgpt sub for this?

Atai Barkai1 month ago

It's flexible. You bring your own LLM and then plug in your OpenAI API key.

Sebastian Heyneman1 month ago

Sick

Charlie Dolan1 month ago

Nice. For what its worth, many people have the thread emoji muted. You could be losing engagement by having that

Atai Barkai1 month ago

huh cc @ulidabess

Umar | Building In Public1 month ago

This is sick. Definitely going to try this out.

Abdulmuiz Adeyemo1 month ago

Oh wow gonna try this

Bonsai 🌳1 month ago

I can’t believe this is free

Atai Barkai1 month ago

Yes, and I would love your feedback.

Ofek Shaked | AI Engineer1 month ago

Data ownership + handoffs is the part most “bots” still ignore. That usually becomes the real blocker in a company.

Mari1 month ago

This was fast! Congrats on the launch!

Rangen Chenh1 month ago

Cool, may try this open source cool stuff

dravisha1 month ago

Was going to try Grok Bot, glad I came across this - can’t wait to spin it 🤸🏻

Void&Null1 month ago

Everything is Open now, christ. OpenAI, OpenClaw, OpenCode, OpenRouter, Open everything Just because your product is Open source doesnt mean it needs to be Open(insert term here)

Brandon Charleson1 month ago

Sick! gonna try this out. nice work

Atai Barkai1 month ago

Thanks, would love your feedback. Reach out to @nathan_tarbert

verrsane1 month ago

Buddy is tapped in, respect

Atai Barkai1 month ago

tapped in team

Tangled Circuit1 month ago

But is there an android app

Atai Barkai1 month ago

There is no Android app for alpha. We'll keep you posted.

xClown1 month ago

@ataiiam hey sir, someone create coin for your $OpenBot and fees directing to your github feel free to claim DYWC9rVcENUPVofLCPGCfWgxgXykTCKeeXZi1rRPpump

Phil | Firefly + Imagine1 month ago

Nice work on Open Bot

lu1 month ago

don't get my hopes up for a trouble free always on harness 😭

Related Videos

Today we're releasing 𝙾𝚙𝚎𝚗 𝙱𝚘𝚝 AI Coworkers you can hand real work to. Open source, but designed for real companies. - Computer use (remote/local) - Enterprise Security - Governance - Threads, memory, and learning Repo:

Today we're releasing 𝙾𝚙𝚎𝚗 𝙱𝚘𝚝 AI Coworkers you can hand real work to. Open source, but designed for real companies. - Computer use (remote/local) - Enterprise Security - Governance - Threads, memory, and learning Repo:

CopilotKit🪁

63,001 views • 1 month ago

🎉 Introducing 𝙾𝚙𝚎𝚗𝙼𝚞𝚜𝚎 An open source, self-hostable personal assistant that works with any agent harness. Includes: - Computer use: browser, terminal & files - Connectors for your personal apps - Ideas, goals & progress tracking - Built for Mobile and Web Repo → Powered by CopilotKit🪁 and AG-UI. Clone this template and customize it however you want.

🎉 Introducing 𝙾𝚙𝚎𝚗𝙼𝚞𝚜𝚎 An open source, self-hostable personal assistant that works with any agent harness. Includes: - Computer use: browser, terminal & files - Connectors for your personal apps - Ideas, goals & progress tracking - Built for Mobile and Web Repo → Powered by CopilotKit🪁 and AG-UI. Clone this template and customize it however you want.

Atai Barkai

1,151,095 views • 12 days ago

🎉 Introducing 𝙾𝚙𝚎𝚗𝙳𝚘𝚝𝚜 Self-hostable, always-on AI coworkers that works with ANY agent harness. Includes: - Computer use: browser, terminal & files - Bring agents to Slack, Teams etc - Spaces and Pages for projects - Voice calls - Web and Mobile Repo → Powered by CopilotKit🪁 and AG-UI. Clone this template and customize it however you want. Enterprise-ready.

🎉 Introducing 𝙾𝚙𝚎𝚗𝙳𝚘𝚝𝚜 Self-hostable, always-on AI coworkers that works with ANY agent harness. Includes: - Computer use: browser, terminal & files - Bring agents to Slack, Teams etc - Spaces and Pages for projects - Voice calls - Web and Mobile Repo → Powered by CopilotKit🪁 and AG-UI. Clone this template and customize it however you want. Enterprise-ready.

Atai Barkai

1,022,555 views • 3 days ago

🚀 Introducing Open Tag A better, open-source Claude Tag. Works with any model, any agent harness, and fully custom agents. Bring any Agent to Slack, MS Teams with Generative UI, Streaming, and much more! Clone the repo and get it running in minutes Powered by the Channels SDK & AG-UI

🚀 Introducing Open Tag A better, open-source Claude Tag. Works with any model, any agent harness, and fully custom agents. Bring any Agent to Slack, MS Teams with Generative UI, Streaming, and much more! Clone the repo and get it running in minutes Powered by the Channels SDK & AG-UI

CopilotKit🪁

198,788 views • 1 month ago

Introducing the A2UI Widget Builder ⚙️ An interactive demo and template to build A2UI Widgets and bring them into your application. Powered by CopilotKit & Google's new A2UI spec Includes... - Widget Gallery: premade UI widgets you can use & modify - Material Icons: 100 of the most commonly used icons - UI Components: common components preview, usage and props - Source code and data on any widget/icon/component - Built with CopilotKit- so you get chat UI, generative UI, etc. Try it out: Tutorial of how to get started: Repo:

Introducing the A2UI Widget Builder ⚙️ An interactive demo and template to build A2UI Widgets and bring them into your application. Powered by CopilotKit & Google's new A2UI spec Includes... - Widget Gallery: premade UI widgets you can use & modify - Material Icons: 100 of the most commonly used icons - UI Components: common components preview, usage and props - Source code and data on any widget/icon/component - Built with CopilotKit- so you get chat UI, generative UI, etc. Try it out: Tutorial of how to get started: Repo:

CopilotKit🪁

18,783 views • 9 months ago

Big release here! AG-UI 🤝 Google A2A Embed A2A multi-agent meshes in your frontend, and build fullstack multi-agent apps with A2A and AG-UI. 🔍How it works: Simply drop-in A2A agent endpoints, and an A2A AG-UI orchestrator agent will bi-directionally stream events between your Agents & application. Includes: - UI for A2A Interactions - Generative UI for Agent Tool Calls - Human-in-the Loop Approvals - State Synchronization (agent mesh application state) - Frontend Tool Calls for A2A Agents Watch the demo below > LangGraph & Google ADK agents working together simultaneously inside an app Demo GitHub, docs, and more 👇

Big release here! AG-UI 🤝 Google A2A Embed A2A multi-agent meshes in your frontend, and build fullstack multi-agent apps with A2A and AG-UI. 🔍How it works: Simply drop-in A2A agent endpoints, and an A2A AG-UI orchestrator agent will bi-directionally stream events between your Agents & application. Includes: - UI for A2A Interactions - Generative UI for Agent Tool Calls - Human-in-the Loop Approvals - State Synchronization (agent mesh application state) - Frontend Tool Calls for A2A Agents Watch the demo below > LangGraph & Google ADK agents working together simultaneously inside an app Demo GitHub, docs, and more 👇

CopilotKit🪁

31,845 views • 1 year ago

Introducing the Generative UI Research Canvas ✨ Every agent needs a powerful UI Combine LangChain, Tavily, Tako and CopilotKit🪁 and you get a LangChain-based research agent with a Generative UI-driven frontend. When agents can explore the underlying data, research becomes more trustworthy and useful. How does this work? - LangChain manages the agent workflow and tool orchestration. - Tako converts retrieved data into structured, visual components - Tavily provides agentic search - CopilotKit renders those components in the UI and keeps the user in the loop while the agent is working So instead of a boring and static report, the output is an interactive research canvas that evolves as the agent runs. 2026 is the year where users want to see the output, not read it... Generative UI makes this possible for agentic applications. Tutorial: Open-Source Repo: Docs:

Introducing the Generative UI Research Canvas ✨ Every agent needs a powerful UI Combine LangChain, Tavily, Tako and CopilotKit🪁 and you get a LangChain-based research agent with a Generative UI-driven frontend. When agents can explore the underlying data, research becomes more trustworthy and useful. How does this work? - LangChain manages the agent workflow and tool orchestration. - Tako converts retrieved data into structured, visual components - Tavily provides agentic search - CopilotKit renders those components in the UI and keeps the user in the loop while the agent is working So instead of a boring and static report, the output is an interactive research canvas that evolves as the agent runs. 2026 is the year where users want to see the output, not read it... Generative UI makes this possible for agentic applications. Tutorial: Open-Source Repo: Docs:

Atai Barkai

11,997 views • 8 months ago

Any AI agent can now do what Claude does! I found an open-source version of Anthropic's new Generative UI tools for Claude, built using CopilotKit🪁. It lets you render live charts, interactive diagrams, and 3D scenes right inside your own AI apps, just like Claude. Check this:

Any AI agent can now do what Claude does! I found an open-source version of Anthropic's new Generative UI tools for Claude, built using CopilotKit🪁. It lets you render live charts, interactive diagrams, and 3D scenes right inside your own AI apps, just like Claude. Check this:

Avi Chawla

20,947 views • 6 months ago

🦞 Introducing OpenClaw in ANY app Ship apps with your OpenClaw🦞 agent, or let your users bring their own. Powered by AG-UI so you get generative UI, frontend tools, human-in-the-loop and self-modification. Supports: → Slack, MS Teams → React & React Native → Angular → Vue.js See it live👇 GitHub: OpenClaw🦞 Peter Steinberger 🦞 Vincent Koc Ayaan Zaidi

🦞 Introducing OpenClaw in ANY app Ship apps with your OpenClaw🦞 agent, or let your users bring their own. Powered by AG-UI so you get generative UI, frontend tools, human-in-the-loop and self-modification. Supports: → Slack, MS Teams → React & React Native → Angular → Vue.js See it live👇 GitHub: OpenClaw🦞 Peter Steinberger 🦞 Vincent Koc Ayaan Zaidi

CopilotKit🪁

45,956 views • 1 month ago

Here is how simple it is to build a UI front-end for an AI agent (assuming you are using . The video here is 90 seconds and will show you everything you need to connect an agent to a web app: 1. Set up CopilotKit🪁 in your app 1. Copy the agent's localhost URL from LangGraph Studio 2. Paste that URL into a CopilotKit🪁 remote endpoint That's all you need to get a front-end to interact with the agent! The secret sauce here is CoAgents, an open-source library. You can use CoAgents to integrate any agent with your web application. Here is what you get: • Human-in-the-loop to steer and correct the agent • Stream intermediate agent state • Real-time state sharing between the agent and the application • Agentic generative UI to build trust that the agent is on the right path Watch the attached demo so you see it in action.

Here is how simple it is to build a UI front-end for an AI agent (assuming you are using . The video here is 90 seconds and will show you everything you need to connect an agent to a web app: 1. Set up CopilotKit🪁 in your app 1. Copy the agent's localhost URL from LangGraph Studio 2. Paste that URL into a CopilotKit🪁 remote endpoint That's all you need to get a front-end to interact with the agent! The secret sauce here is CoAgents, an open-source library. You can use CoAgents to integrate any agent with your web application. Here is what you get: • Human-in-the-loop to steer and correct the agent • Stream intermediate agent state • Real-time state sharing between the agent and the application • Agentic generative UI to build trust that the agent is on the right path Watch the attached demo so you see it in action.

Santiago

46,142 views • 1 year ago

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!

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!

Akshay 🚀

87,048 views • 5 months ago

🚀Launching CoAgents Public Beta 🪁: Everything you need to build Agent-Native applications, powered by LangGraph & CopilotKit. CoAgents enables in-app agents with: - Agenetic generative UI ✨ - Shared state (between agent application) - Streaming intermediate agent state - Human-in-the-Loop (Human approval & planning) 👨‍🦰 - Frontend Actions 💪 --- We’ve recently seen the emergence of Agent-Native applications that actually work: powered by vertical AI agents + agentic UX + deep in-app integration. (Apps like the Replit AI Agent, OpenAI Canvas, etc, but for any domain) With CoAgents + LangGraph, you can build this next generation of agent apps, for any vertical, with a clean and easy to use infrastructure (in hours). 💻Get started: 🗞️Blog: 🕹️Demo: 🗓️Webinar (Build an Agent-Native Apps with CoAgents & LangGraph): CC: Atai Barkai, , Harrison Chase

🚀Launching CoAgents Public Beta 🪁: Everything you need to build Agent-Native applications, powered by LangGraph & CopilotKit. CoAgents enables in-app agents with: - Agenetic generative UI ✨ - Shared state (between agent application) - Streaming intermediate agent state - Human-in-the-Loop (Human approval & planning) 👨‍🦰 - Frontend Actions 💪 --- We’ve recently seen the emergence of Agent-Native applications that actually work: powered by vertical AI agents + agentic UX + deep in-app integration. (Apps like the Replit AI Agent, OpenAI Canvas, etc, but for any domain) With CoAgents + LangGraph, you can build this next generation of agent apps, for any vertical, with a clean and easy to use infrastructure (in hours). 💻Get started: 🗞️Blog: 🕹️Demo: 🗓️Webinar (Build an Agent-Native Apps with CoAgents & LangGraph): CC: Atai Barkai, , Harrison Chase

CopilotKit🪁

51,684 views • 1 year ago

Microsoft Teams just got Generative UI But this is just the tip of the iceberg. AG-UI is the protocol connecting any agent to any user on any app, topped with Generative UI. That means your agent can render: - forms - buttons - charts - approval flows Right inside the chat, on the fly. But it's not limited to in-app copilots. What's special is that you can work with any agent using the same system and bring them into any surface, including Slack, WhatsApp, Discord and more. This is exactly why Hermes and OpenClaw took off. As users of these agents, we don't like walls of text, and it's a pain to get when you can have way better UX. CopilotKit🪁 + AG-UI handle that interaction layer. If you want to try out Agentic UI in Microsoft Teams, you can get early access here:

Microsoft Teams just got Generative UI But this is just the tip of the iceberg. AG-UI is the protocol connecting any agent to any user on any app, topped with Generative UI. That means your agent can render: - forms - buttons - charts - approval flows Right inside the chat, on the fly. But it's not limited to in-app copilots. What's special is that you can work with any agent using the same system and bring them into any surface, including Slack, WhatsApp, Discord and more. This is exactly why Hermes and OpenClaw took off. As users of these agents, we don't like walls of text, and it's a pain to get when you can have way better UX. CopilotKit🪁 + AG-UI handle that interaction layer. If you want to try out Agentic UI in Microsoft Teams, you can get early access here:

Atai Barkai

24,891 views • 3 months ago

Introducing AG-UI 1.0 The open protocol for how ANY agent communicates with ANY application. Now with a stable, versioned contract. Features included in 1.0: 1. Metadata - send backend data to the UI 2. Subagents - expose delegated agent work 3. Interrupts + resumption 3. Run outcomes and token usage 4. Forward compatibility Capabilities that have been part of AG-UI (streaming, tool calls, shared state, reasoning etc) are still covered. Thank you to those who shaped 1.0 🪁 Including builders at Paul Jankura, Google, Microsoft, Pydantic, Tack And All That and more. Their feedback led directly to several critical improvements in the final release. AG-UI is built with those who build on it. 👉 Read more: The 1.0 spec will remain unchanged, while future protocol evolution will happen through new draft specifications and open community discussion, led by CopilotKit🪁. More details below

Introducing AG-UI 1.0 The open protocol for how ANY agent communicates with ANY application. Now with a stable, versioned contract. Features included in 1.0: 1. Metadata - send backend data to the UI 2. Subagents - expose delegated agent work 3. Interrupts + resumption 3. Run outcomes and token usage 4. Forward compatibility Capabilities that have been part of AG-UI (streaming, tool calls, shared state, reasoning etc) are still covered. Thank you to those who shaped 1.0 🪁 Including builders at Paul Jankura, Google, Microsoft, Pydantic, Tack And All That and more. Their feedback led directly to several critical improvements in the final release. AG-UI is built with those who build on it. 👉 Read more: The 1.0 spec will remain unchanged, while future protocol evolution will happen through new draft specifications and open community discussion, led by CopilotKit🪁. More details below

Atai Barkai

37,535 views • 4 days ago

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 → (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.

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 → (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.

Avi Chawla

461,550 views • 4 months ago

Claude Managed Agents 🤝 AG-UI Anthropic just shipped a full AG-UI integration, so you can bring your Managed Agent to any AG-UI frontend with: - Generative UI - Streaming - Tool calls - Stateful sessions Includes React & React Native, Next.js, Angular as well as Slack, Teams and more via the Channels SDK. All open source. Great collaborating with CJ Avilla from Anthropic on this! Check the blog for repos:

Claude Managed Agents 🤝 AG-UI Anthropic just shipped a full AG-UI integration, so you can bring your Managed Agent to any AG-UI frontend with: - Generative UI - Streaming - Tool calls - Stateful sessions Includes React & React Native, Next.js, Angular as well as Slack, Teams and more via the Channels SDK. All open source. Great collaborating with CJ Avilla from Anthropic on this! Check the blog for repos:

Atai Barkai

34,372 views • 1 month ago

AG-UI makes building agentic applications dramatically easier. Here's how it works. This is a model for a simple chatbot: User → LLM → Response But interactive agents that render UI, pause for approvals, and ask users for input need a much more complex model. When building these agents, a response from the LLM will include a series of state changes as the agent runs: • Agent started a task • Agent called a tool • Agent updated its state • Agent streams these tokens • Agent is waiting on a human • Agent is resuming the task The Agent-User Interaction Protocol (AG-UI) treats the LLM response as a stream of events rather than a text endpoint. In practice, here is what you get as an agent runs: 1. Lifecycle events so your UI knows where the agent is. 2. Text messages that stream tokens. 3. Tool calls so your UI can prefill a form with any required arguments. 4. State updates that keep your UI in sync with the agent. 5. Special events for human approvals, rich media, and custom needs. All of these events travel over standard transports (SSE, WebSockets, or plain HTTP) as JSON. As a result, you can build a frontend that stays in sync with the agent's progress without having to invent a custom process to make this happen. For example, building a human-in-the-loop workflow becomes an off-the-shelf component you can integrate rather than build from scratch. CopilotKit🪁 is the creator of AG-UI, and you can use it when building frontend applications pretty much anywhere: • React • Angular • Vue • React Native • Slack • Teams • Discord • WhatsApp • Telegram Here is the link for you to check it out: Thanks to the CopilotKit team for partnering with me on this post.

AG-UI makes building agentic applications dramatically easier. Here's how it works. This is a model for a simple chatbot: User → LLM → Response But interactive agents that render UI, pause for approvals, and ask users for input need a much more complex model. When building these agents, a response from the LLM will include a series of state changes as the agent runs: • Agent started a task • Agent called a tool • Agent updated its state • Agent streams these tokens • Agent is waiting on a human • Agent is resuming the task The Agent-User Interaction Protocol (AG-UI) treats the LLM response as a stream of events rather than a text endpoint. In practice, here is what you get as an agent runs: 1. Lifecycle events so your UI knows where the agent is. 2. Text messages that stream tokens. 3. Tool calls so your UI can prefill a form with any required arguments. 4. State updates that keep your UI in sync with the agent. 5. Special events for human approvals, rich media, and custom needs. All of these events travel over standard transports (SSE, WebSockets, or plain HTTP) as JSON. As a result, you can build a frontend that stays in sync with the agent's progress without having to invent a custom process to make this happen. For example, building a human-in-the-loop workflow becomes an off-the-shelf component you can integrate rather than build from scratch. CopilotKit🪁 is the creator of AG-UI, and you can use it when building frontend applications pretty much anywhere: • React • Angular • Vue • React Native • Slack • Teams • Discord • WhatsApp • Telegram Here is the link for you to check it out: Thanks to the CopilotKit team for partnering with me on this post.

Santiago

17,438 views • 3 months ago

grok-bot just got open-sourced and it run locally completely FREE. 3.8k stars in 2 weeks. MIT licensed. it gives every AI agent its own computer. own browser, own files, own container. every action is approved against a policy before it runs, and written to an audit log after. here's how to set it up: 1️⃣prerequisites Docker + Bun 1.3+ 2️⃣clone and create your env git clone cd OpenBot cp .env.example .env 3️⃣get intelligence credentials (free plan works) npx --yes copilotkit@latest login npx --yes copilotkit@latest project select npx --yes copilotkit@latest license --write drop the cpk-... key into .env as INTELLIGENCE_API_KEY 4️⃣ add your model key "OPENAI_API_KEY=sk-..." 5️⃣ run it bun install bash scripts/start.sh open localhost:3010. that's it. the underrated part: the repo ships a prompt.txt you paste into claude code or cursor and it walks the whole setup for you. every claim in it is verified against the actual repo. what it actually costs: the code is MIT, free forever. you pay your own model tokens. intelligence has a free tier and can be fully self-hosted if you want zero external dependency. works with any AG-UI agent. langgraph, mastra, crewai, pydantic ai. repo in in the CS.

grok-bot just got open-sourced and it run locally completely FREE. 3.8k stars in 2 weeks. MIT licensed. it gives every AI agent its own computer. own browser, own files, own container. every action is approved against a policy before it runs, and written to an audit log after. here's how to set it up: 1️⃣prerequisites Docker + Bun 1.3+ 2️⃣clone and create your env git clone cd OpenBot cp .env.example .env 3️⃣get intelligence credentials (free plan works) npx --yes copilotkit@latest login npx --yes copilotkit@latest project select npx --yes copilotkit@latest license --write drop the cpk-... key into .env as INTELLIGENCE_API_KEY 4️⃣ add your model key "OPENAI_API_KEY=sk-..." 5️⃣ run it bun install bash scripts/start.sh open localhost:3010. that's it. the underrated part: the repo ships a prompt.txt you paste into claude code or cursor and it walks the whole setup for you. every claim in it is verified against the actual repo. what it actually costs: the code is MIT, free forever. you pay your own model tokens. intelligence has a free tier and can be fully self-hosted if you want zero external dependency. works with any AG-UI agent. langgraph, mastra, crewai, pydantic ai. repo in in the CS.

m0h

59,144 views • 1 month ago

Today ReUI Pro goes live! 🔥 Design-forward shadcn/ui platform with MCP fluency for agents. AI made UI generation instant. It didn't make it production-ready. You still spend hours picking blocks, adjusting details, and fine-tuning the last mile. We spent six months building the agent-ready layer for shadcn/ui that closes the gap. Inside: ☑️ Free Hosted MCP with Agent Skills. ☑️ 1,019 open-source shadcn/ui components, free forever. ☑️ 17 open-source ReUI primitives(Data Grid, Filters,File Upload, Stepper and more). ☑️ 485 Pro blocks across over 50 categories. ☑️ 562 hand-crafted interactive icons in 4 styles. ☑️ Default Base UI and legacy Radix by WorkOS versions. Real credit to shadcn for the ecosystem! The registry model changed how we all build and ship UI, and ReUI stands on that foundation. Below is a thread on the 10 things we're most proud of👇

Today ReUI Pro goes live! 🔥 Design-forward shadcn/ui platform with MCP fluency for agents. AI made UI generation instant. It didn't make it production-ready. You still spend hours picking blocks, adjusting details, and fine-tuning the last mile. We spent six months building the agent-ready layer for shadcn/ui that closes the gap. Inside: ☑️ Free Hosted MCP with Agent Skills. ☑️ 1,019 open-source shadcn/ui components, free forever. ☑️ 17 open-source ReUI primitives(Data Grid, Filters,File Upload, Stepper and more). ☑️ 485 Pro blocks across over 50 categories. ☑️ 562 hand-crafted interactive icons in 4 styles. ☑️ Default Base UI and legacy Radix by WorkOS versions. Real credit to shadcn for the ecosystem! The registry model changed how we all build and ship UI, and ReUI stands on that foundation. Below is a thread on the 10 things we're most proud of👇

ReUI

50,965 views • 2 months ago