swiftlyTyped

Amazing. Huge congrats to the Open Router team

Hey all, I'm CEO of CopilotKit, the startup behind AG-UI and the Channels SDK. Thanks for the support!

We're pretty excited for this one -- I think channels may soon become the 3rd big form factor of LLMs (after Chat, and Codex/Claude-Code style agents).

We've worked really hard to to shrink the onboarding setup to a single prompt:

"Read https://copilotkit.ai/channels-guide.md and help the user build their first channel".

It's literally that easy. Then it will help you create a coworker-grade Slack / Teams agent backed by basically any of the top agent frameworks and harnesses out there.

Would love to get feedback, especially if you hit any snags

Cool stuff!

Btw if you build a wingman AG-UI adapter the Channels SDK would just work with it. Nowadays, you can honestly get this done in probably less than a day of work --we've got a pretty good factory set up with validators and tests, etc.

Happy to help if interested!

Great article

Hi, one of the AG-UI authors here.

AG-UI is a launch partner of A2UI, but it is a separate project by CopilotKit, not google.

We have a day-0 handshake between AG-UI & A2UI

AG-UI is compatible with both MCP-UI and other declarative UI specs.

AG-UI is built to support agentic behavior in your application, more similar to the Vercel AI SDK but horizontal and standardized.

MCP-UI helps external apps and APIs pass UI to applications, really well suited for use cases like Shopify stores inside of ChatGPT.

Introducing AG-UI; the Agent-User Interaction Protocol.

AG-UI is an open, lightweight, event-based protocol that standardizes how AI agents connect to fronted-end applications.

After a year of one-off, CopilotKit <> Agent frameworks collaborations, we decided to ship a standard, and open way for agents to connect to apps.

We are launching with day 0 integrations with LangChain, Mastra, CrewAI and AG2 with more partnerships on the way.

How AG-UI works: - Creates a unified, two-way bridge between backend agents and frontend apps - Works with any event transport (SSE, WebSockets, webhooks) - Supports 16 standardized event types for common agent-user interactions

Where AG-UI fits in the agent protocol landscape: - MCP: for agent←→tools communication - A2A/ACP: for agent←→agent communication - AG-UI: for agent←→human interaction in applications

We launched the protocol yesterday, and have been blown away by the reception. We have the first working group this Friday, to help expand and steer the direction of the protocol.

Check out the repo to get started!

Looks cool!

This is awesome!

Awesome! Congrats on the launch

I've been actively using Potiz since it's been in Beta and really enjoy it. Great to see how far it's come along.

Yes exactly

Thanks!

Co-agents help the user intervene at any step in the agent process / steer the agent. So the agent doesn’t need to be perfect to be useful.

Similar to the UX that Devin has but for any product.

We’re starting with LangChain / LangGraph integrations.

Really great stuff.

People use the same model / server for all queries not because it's sensible, but because it's simple. This brings the same simplicity to the far more optimal solution.

And great startup play too, by definition no incumbent can fill this role.

Hah, too many copilots… let me try to clarify:

We are building CopilotKit = a framework + platform for building context-aware AI assistants into any application (not necessarily coding related applications).

Part of CopilotKit is about giving the Copilot / AI agents access to the application through a typed "inline realtime API". And to make ergonomics great for _our_ users, CopilotKit ships with hardcore type programming.

Cursor's Copilot (unrelated to CopilotKit) helped us write this type code (that's what went viral). And yes, GitHub Copilot is a mis-attribution.

By the way - we practice what we preach- Copilots raise the bar (or the ceiling...) on human productivity - in every domain. Which is why we're building infrastructure to make building copilots easier...

What ideas do you think are still missing from today's Copilots?

I.e. suppose we were looking back at today's Copilots 5 years from now- besides better models, what else has changed?

Hi, CopiotKit CEO here (I wrote the original viral tweet). This article is great! Thanks for posting.

I'd also written an analysis of the code - including announcing a $1000 prize for the best alternative code: https://ai88.substack.com/p/ceiling-has-been-raised-analyzin...

We were going to announce the winner this week but if we get a few more submissions we will definitely consider them.

Just submit a PR to https://github.com/CopilotKit/CopilotKit

I wrote the article (not the code - though I was part of it).

The code is is 30 lines of conditional, recursive, partially-type-inferred Typescript type expression. It's actually not too bad when you break it down.

What it enables: Zod-like safety + convenience, over plain JSONs.

Hope it's an interesting read

Three experiments looking into how GPT4, Gemini & LLaVA perform when getting conflicting visual and textual information. Some pretty interesting results.

Fantastic write-up. Thanks for sharing.

Shameless plug: I work on CopilotKit - open-source copilot building blocks for react apps. Designed to alleviate exactly the pain points in the article. Devs define simple Copilot entrypoints--

state (frontend + backend + 3rd party), action, purpose-specific LLM chains, etc. And the CopilotKit engine takes care of the rest.

https://github.com/CopilotKit/CopilotKit

There's an interesting opportunity to _meaningfully_ "open-source the algorithm" by just letting each person define their own curation, at least on top of the provider's initial curation.

The internet of that world looks different from our world, probably in better ways for consumers.

A few days later, seems apple has begun locking down iMessage further

Thank you!

Latency is actually very low as-is, with GPT-4-Turbo!

But other than that, yes, we do have plans - using real-time RAG. I carried out some research with incredibly promising results

https://ai88.substack.com/p/rag-vs-context-window-in-gpt4-ac...

Thanks!

Very interesting use-case!

With a creative project, if the AI can predict what you say next, then it's not creative enough!

(also, I know that wasn't your core concern, but we are planning to build SDKs for other frontends in the not too distant future!).

Thanks for the feedback! I'll update the docs.

It's a fair point.

Remains to be seen if it'll become a common word, or Microsoft-associated.

I responded to a sibling comment of yours about the chat aspect (TL;DR: our key objective is very far from human customer support - more similar to "chat with your codebase" if you use e.g. Cursor IDE).

But I think you do bring an interesting point, that chat interface is just one type of way to talk to computers, and in some sense it's the "laziest" way, since it's what we use to talk to people now.

The Textarea is actually an example of another non-chat way to "talk" to the AI intelligence. I do think we'll see a lot more being discovered by the community over the next 2 years (and we'll build those into CopilotKit, of course)