--- title: CopilotKit's Channels SDK wants to kill your... description: CopilotKit has released the Channels SDK, which lets developers build an AI agent once and deploy it across multiple messaging platforms — Slack, Microsoft... canonical: https://daily.dev/posts/copilotkit-s-channels-sdk-wants-to-kill-your-per-platform-agent-integrations-endnogo7k twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: CopilotKit's Channels SDK wants to kill your per-platform agent integrations | daily.dev og:description: CopilotKit has released the Channels SDK, which lets developers build an AI agent once and deploy it across multiple messaging platforms — Slack, Microsoft... og:url: https://daily.dev/posts/copilotkit-s-channels-sdk-wants-to-kill-your-per-platform-agent-integrations-endnogo7k og:image: https://api.daily.dev/og/posts/enDnOgo7k.png og:image:alt: CopilotKit's Channels SDK wants to kill your per-platform agent integrations og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # CopilotKit's Channels SDK wants to kill your per-platform agent integrations **[Trends](https://daily.dev/sources/trends)** · 2 min read · 1 upvotes · 0 comments ## Summary CopilotKit has released the Channels SDK, which lets developers build an AI agent once and deploy it across multiple messaging platforms — Slack, Microsoft Teams, Discord, Telegram, and WhatsApp — without writing separate integrations for each. The SDK handles streaming responses, tool calls, file handling, and platform-native UI components like Slack Block Kit and Teams Adaptive Cards. It supports popular agent frameworks including LangGraph, CrewAI, Mastra, Pydantic AI, and Google ADK. A human-in-the-loop approval mechanism lets agents pause and request confirmation before consequential actions. A reference app called OpenTag (a Python LangGraph on-call triage agent) is included. The SDK is MIT-licensed and open source, but CopilotKit Intelligence manages platform credentials and routing, meaning it is not fully self-hosted — a tradeoff teams should evaluate before committing to production use. ## Content If you've built an AI agent and tried to deploy it across Slack, Teams, Discord, and WhatsApp, you know the pain: each platform has its own API quirks, auth flows, and UI primitives. Most teams end up with four separate integrations to maintain. CopilotKit just shipped an open-source SDK that tries to collapse all of that into one. The pitch is straightforward. You build your agent once, point the Channels SDK at whichever platforms you want, and it handles the plumbing. Slack Block Kit, Teams Adaptive Cards, Telegram messages — the SDK translates your agent's output into whatever native UI the platform expects. Underneath, it uses the AG-UI protocol to stream responses, route tool calls, and manage file handling without touching your agent's core logic. The feature list is doing real work here: agents retain memory across conversations, can render interactive UI natively on each platform, and can pause mid-task to request human approval before taking consequential actions. That last one matters if you're building anything that touches production systems or sends messages on someone's behalf. Supported agent frameworks include LangGraph, CrewAI, Mastra, Pydantic AI, and Google ADK. The reference app, OpenTag, is a Python LangGraph agent built for on-call triage — complete with human approval gates — and it's meant to show production deployment patterns, not just a toy demo. The SDK is MIT-licensed and on GitHub. CopilotKit Intelligence handles platform credentials and ingress on their end; you run your own agent and listener process. The honest caveat: this is sponsored content from svpino, who has a partnership with CopilotKit. That doesn't make the SDK less real, but it does mean the reception here is mostly amplification rather than independent developer feedback. Whether the abstraction holds up under the messiness of real platform integrations — rate limits, webhook failures, platform-specific edge cases — is still an open question. The concept is sound. The proof will be in production. ## Questions this post answers ### How can I deploy the same AI agent across Slack, Teams, Discord, and WhatsApp without building separate integrations for each? CopilotKit's open-source Channels SDK lets you build an agent once and deploy it across multiple chat platforms by handling platform-specific translation automatically. It converts agent output into native UI like Slack Block Kit or Teams Adaptive Cards, uses the AG-UI protocol to stream responses and route tool calls, and supports frameworks including LangGraph, CrewAI, Mastra, Pydantic AI, and Google ADK. The SDK is MIT-licensed and available on GitHub. _daily.dev surfaces tools like this for developers weighing how to scale an agent across chat platforms without duplicating work._ ### What is the OpenTag reference agent used to demonstrate the CopilotKit Channels SDK? OpenTag is a Python LangGraph agent built for on-call triage, designed as a reference implementation showing production deployment patterns rather than a toy demo. It includes human approval gates so the agent can pause mid-task and wait for confirmation before taking consequential actions, which matters for agents touching production systems or messaging on someone's behalf. _anyone evaluating agent frameworks for production triage work can track real-world examples like this through daily.dev._ ## Community take How the wider developer community reacted, aggregated from 1 discussion and 23 comments across hackernews (as of 2026-09-13). **TL;DR:** The community is broadly enthusiastic about the idea of a unified SDK for deploying agents across chat platforms, though several commenters raise legitimate concerns about whether the "open-source" framing is accurate given that the hosted service is closed, and some question how it truly differs from existing tools like Vercel's Chat SDK. **Sentiment:** 55% positive · 30% mixed · 15% skeptical **The case for** - AG-UI as the transport layer provides genuine flexibility, enabling the same agent to work across Slack, Teams, web, and mobile over a single protocol. - The unified SDK approach that adapts to different chat clients is seen as a strong solution offering the best of both worlds. - Shrinking onboarding to a single prompt is highlighted as a meaningful developer experience improvement. - Chat interfaces are increasingly viewed as the most natural home for useful, task-specific agents. **The pushback** - The MIT license applies only to the client SDK, while the service that actually makes it run is closed and license-gated, making the "open-source" claim misleading. - The "Copilot" branding causes confusion about who is behind the project and whether it is affiliated with Microsoft. - Some commenters feel the differentiation from Vercel's Chat SDK is overstated, as that SDK also has JSX card rendering, Block Kit/Adaptive Cards support, and action handlers. - At least one developer expressed dread at the prospect of chatbots proliferating across workplace Slack channels. **By community** - hackernews (mixed): Generally positive on the concept and AG-UI integration, but tempered by real concerns about open-source authenticity, branding confusion, and unclear differentiation from existing tools. **Hottest debate:** Whether the project is genuinely open-source or merely MIT-licensed on the client side while the core hosted service remains closed and proprietary. **Open questions** - Will the hosted service ever be fully self-hostable, or will meaningful functionality always require CopilotKit's managed infrastructure? - How does WhatsApp integration actually work, and when will it be fully supported in the hosted service? - Is Mastodon support planned, given privacy concerns about other platforms? - How can the community contribute additional channel integrations? **Highlights** > I dont think it s really open source, the MIT part is just the client. The service that actually makes it run is closed and license-gated. > — [chengyongru on hackernews · 1 comments](https://news.ycombinator.com/item?id=49199068) > I like the idea of having a much easier way to integrate with all of the chat clients, especially with UI. I've been surprised there wasn't a way to do that more easily before (even pre AI agent revolution). 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. > — [TheTaytay on hackernews](https://news.ycombinator.com/item?id=49199814) > 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 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. > — [mikeryan52 on hackernews · 1 comments](https://news.ycombinator.com/item?id=49199647) > 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 our channels. A lunchbot agent wraps the DoorDash CLI to handle office lunch orders, a pupfood agent wraps the Pup and GitHub CLIs to do incident triage, and a chadbot generates marketing videos on demand from GitHub PRs. We've got even more that compose PostHog, Notion, Linear, and other internal tools we use. I had previously been pretty hot about bringing agents to the web, but I'm increasingly convinced that chat interfaces are the most natural home for useful agents. Happy to answer any questions about our approach here! > — [mikeryan52 on hackernews · 2 comments](https://news.ycombinator.com/item?id=49198966) > 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 > — [swiftlyTyped on hackernews](https://news.ycombinator.com/item?id=49200559) **Source threads** - [hackernews](https://news.ycombinator.com/item?id=49198583) · 101 points · 23 comments --- Tags: [#ai-agents](https://daily.dev/tags/ai-agents), [#slack](https://daily.dev/tags/slack), [#langgraph](https://daily.dev/tags/langgraph) [View this post on daily.dev](https://daily.dev/posts/copilotkit-s-channels-sdk-wants-to-kill-your-per-platform-agent-integrations-endnogo7k) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"CopilotKit's Channels SDK wants to kill your per-platform agent integrations","url":"https://daily.dev/posts/copilotkit-s-channels-sdk-wants-to-kill-your-per-platform-agent-integrations-endnogo7k","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/copilotkit-s-channels-sdk-wants-to-kill-your-per-platform-agent-integrations-endnogo7k"},"datePublished":"2026-08-06T17:54:34.149Z","dateModified":"2026-09-13T19:22:14.352Z","description":"CopilotKit has released the Channels SDK, which lets developers build an AI agent once and deploy it across multiple messaging platforms — Slack, Microsoft...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/40b78f360e550f99dbcaed59a1eb0c36?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/40b78f360e550f99dbcaed59a1eb0c36?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Trends","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"Trends","logo":"https://media.daily.dev/image/upload/s--ZfSp3asX--/f_auto,q_auto/v1780996004/logos/trends?_a=BAMAMiWQ0","url":"https://daily.dev/sources/trends"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/copilotkit-s-channels-sdk-wants-to-kill-your-per-platform-agent-integrations-endnogo7k","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":1},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"ai-agents,slack,langgraph","timeRequired":"PT2M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Trends","item":"https://daily.dev/sources/trends"},{"@type":"ListItem","position":3,"name":"CopilotKit's Channels SDK wants to kill your per-platform agent integrations"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/copilotkit-s-channels-sdk-wants-to-kill-your-per-platform-agent-integrations-endnogo7k#faq","mainEntity":[{"@type":"Question","name":"How can I deploy the same AI agent across Slack, Teams, Discord, and WhatsApp without building separate integrations for each?","acceptedAnswer":{"@type":"Answer","text":"CopilotKit's open-source Channels SDK lets you build an agent once and deploy it across multiple chat platforms by handling platform-specific translation automatically. It converts agent output into native UI like Slack Block Kit or Teams Adaptive Cards, uses the AG-UI protocol to stream responses and route tool calls, and supports frameworks including LangGraph, CrewAI, Mastra, Pydantic AI, and Google ADK. The SDK is MIT-licensed and available on GitHub. daily.dev surfaces tools like this for developers weighing how to scale an agent across chat platforms without duplicating work."}},{"@type":"Question","name":"What is the OpenTag reference agent used to demonstrate the CopilotKit Channels SDK?","acceptedAnswer":{"@type":"Answer","text":"OpenTag is a Python LangGraph agent built for on-call triage, designed as a reference implementation showing production deployment patterns rather than a toy demo. It includes human approval gates so the agent can pause mid-task and wait for confirmation before taking consequential actions, which matters for agents touching production systems or messaging on someone's behalf. anyone evaluating agent frameworks for production triage work can track real-world examples like this through daily.dev."}}]} ```