11–20 of 32 posts
Is it like a proprietary wrapper for Vercel’s Chat SDK ( https://github.com/vercel/chat )?
Is it like a proprietary wrapper for Vercel’s Chat SDK ( https://github.com/vercel/chat )?
- Generative UI in these surfaces needs to be durable. If your agent composes a Block Kit or Adaptive Cards interface with interactivity, you have to be ready to handle that interactivity weeks later. We handle this with our JSX renderer.
- Chat interfaces are inherently multiplayer. The worst thing you can do is have your agent act like a bot: posting all of the time, creating noise, and offering no customization. I think Claude Tag nailed the user experience here, and now we want to empower developers to create agents with a similar UX via open source.
- Truly agent-and-surface agnostic. We're fully powered by AG-UI (ag-ui.com), so you can bring any agent into Slack and then take that same agent to web or mobile all over the same protocol.
I think your approach of a unified SDK/data structure around a chat that adapts to different clients is a really strong solution that probably just gives you the best of both worlds.
Hi folks! I'm one of the engineers working on the Channels SDK. This is our first public release. Our emphasis has been on making agents act like natural participants in Slack and Teams, while letting them generate UI along the way. It's built on top of AG-UI, so any agent that emits AG-UI can be brought to Slack or Teams. We've been dogfooding this internally and have seen a surge of tiny, task-specific agents enter…
Two points of confusion that I wanted to bring up just so you know what it was like for me as a new reader: "Copilot" is unfortunately an extremely overloaded term right now. Not your fault, but I don't know about CopilotKit, so I was trying to figure out who really was behind this. (Is it Microsoft? etc) I also (like another poster) wondered if I needed your server in order to use this. I love the MIT license, but it wasn't clear to me if this was just a veneer over a closed-source thing or not. I saw in your response that there is a legit open source ability to use it, but that wasn't clear.
Is it like a proprietary wrapper for Vercel’s Chat SDK ( https://github.com/vercel/chat )?
Not proprietary and not a wrapper. Chat SDK served as inspiration, of course, but I think it misses a few hard parts of bringing agents to chat interfaces: - Generative UI in these surfaces needs to be durable. If your agent composes a Block Kit or Adaptive Cards interface with interactivity, you have to be ready to handle that interactivity weeks later. We handle this with our JSX renderer. - Chat interfaces are inh…
> Chat interfaces are inherently multiplayer.
Both chat and channel sdks support subscribing to threads and can control messages that arrive concurrently. In that regard it feels like this depends more on the logic of the app itself rather than gets defined by the framework/dependency it uses.
Is it like a proprietary wrapper for Vercel’s Chat SDK ( https://github.com/vercel/chat )?
From quick glance I don’t think so that’s the case. copliotkit promises ag-ui compatiblity., which means it can work with codex cli, mastra, pi, claude agents sdk and other harnesses as well (there are ag ui adapters as well). I’m actually integrating this with claude agent sdk with ag ui adapter., which i don’t think is possible with vercel chat sdk.
It was pretty limited thought in terms of what I needed, so I had to through it away and build my own telegraf sdk based channel implementation for telegram, but that was a while ago, I assume they should have evolved a lot from the time I last touched it about 3 months ago.
I think this is likely a very good idea. I've thought about the idea of channels a lot building https://wingman.actor and I've gone back in forth on if channel primitives are a good idea at a low level or if existing chat clients are just an already well defined utility you shouldn't rewrite. I think your approach of a unified SDK/data structure around a chat that adapts to different clients is a really strong soluti…
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!