Get early access
Copilot Kit Logo
Back

Big Updates on AG-UI: Massive Traction and Adoption

By Uli Barkai
June 2, 2025
Big Updates on AG-UI: Massive Traction and Adoption

We launched AG-UI one month ago, and it’s been incredible to see the reception and adoption.

Millions of views for content on AG-UI, tens of thousands of developers building and new contributions & integrations in the pipeline by some of the most important players in the space including Agno, AWS, LlamaIndex, Alibaba and more!

__wf_reserved_inherit

Discourse around AG-UI:

https://www.youtube.com/watch?v=BFWviieMyGw&t=382s

__wf_reserved_inherit

Recap on AG-UI

AG-UI is meant to help developers bring AI agents from backend processes that occur in the background - to interactive, key parts of AI native applications.

CopilotKit, has been innovating on this front for over a year, but AG-UI allows us to address this gap in the ecosystem in a far more powerful way, which will also bring immense positive externalities to the agent ecosystem.

MxN —> M+N

AG-UI serves as a bridge between Agents and Clients. Agents emit AG-UI compatible events as they are executing their workflow (one of 16 events), and AG-UI Clients read and interrupt these events.

Agent frameworks have to make simple changes, and they get full Frontend functionality right out of the box with Clients like CopilotKit.

But what is even better, that these frameworks will also receive support for any additional AG-UI compatible client created. There is already a team of contributors from AWS, creating a SMS/Whatsapp client with AG-UI.

This means that every AG-UI compatible framework, will get instant support for features by new AG-UI Clients. So your LangGraph agent will be able to receive human-in-the-loop feedback from WhatsApp, without LangChain having to implement this, and without the WhatsApp client having to implement LangChain support.

This means that instead of every client and every framework needing to collaborate, each just has to support AG-UI, and a world of functionality is unlocked.

Instead of M frameworks * N Clients, you have M frameworks + N Clients.

__wf_reserved_inherit

‍

Get daily updates-follow CopilotKit on Twitter @CopilotKit

Top posts

See All
Build Generative UI Agents on Amazon Bedrock AgentCore with AG-UI and CopilotKit
Anmol Baranwal and Nathan TarbertJune 30, 2026
Build Generative UI Agents on Amazon Bedrock AgentCore with AG-UI and CopilotKitAmazon Bedrock AgentCore now runs AG-UI agents natively, so auth, scaling, and session isolation come managed. We build one agent that renders charts inline, syncs a todo canvas both ways, and pauses for human input. Pick Strands or LangGraph at deploy time, and the same frontend runs against either.
Switching to Fable 5: The Tuesday That Cost $22,000
Jordan Ritter June 12, 2026
Switching to Fable 5: The Tuesday That Cost $22,000CopilotKit swapped their coding agents to a new model (fable-5) on a Tuesday, and by Wednesday had run up a ~$22,000 Anthropic bill. No bug or runaway script caused it — five engineers doing normal work triggered it, because the new model interpreted their English-prose behavioral rules ("keep sub-agents small," "converge to zero") far more loosely than older models did. The result was four simultaneous drift modes: bloated sub-agents, runaway review loops, exploding fanout, and oversized single turns. What kept it from being far worse was their "skills" system — small, named instruction packs that agents auto-load to encode team conventions. Their instrumentation caught the runaway in 12 hours instead of 12 days, isolated worktrees contained the blast radius, and the fix lived at the rules layer (swapping vague adjectives for hard numeric budgets and machine-checkable gates) rather than in application code. The takeaway: if you let AI agents do real work, you need a guardrails layer that encodes desired behavior separately from the agents — small, composable, and faster to change than a model. Because models will change, and the team with a rules layer pays $22K and writes a blog post; the team without one pays more and writes a press release.
Build AI Agents That Live Inside Your App — CopilotKit Explained
Nathan Tarbert June 12, 2026
Build AI Agents That Live Inside Your App — CopilotKit ExplainedCopilotKit is a complete set of building blocks for developers and teams who want to add agents to their app and assemble, debug, and ship the interface layer between their agents and users. It's also framework-agnostic and supports any LLM and every popular agent framework. There are two options for chat. Pre-built components, if you want something already built or Headless UI, which allows anyone to build custom agent interfaces.
Are you ready?

Stay in the know

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