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!

Discourse around AG-UI:

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

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.

‍

Get daily updates-follow CopilotKit on Twitter @CopilotKit