

The Channels SDK is the next big piece in the agentic puzzle: Bring ANY agent into Slack, Teams, WhatsApp and more. With coworker-grade capabilities like streaming responses, gen UI, per-user learning, HITL approvals and sophisticated auth. Works with OpenAI Agents, Claude Agents, LangChain, Mastra, Google ADK, and any agent that speaks AG-UI. Open-source and self-hostable. Setup with a single prompt: "Read https://copilotkit.ai/channels-guide.md and help the user build their first channel"
Loading comments…
Project Info
Product Keywords
CopilotKit Channels SDK is an open-source, self-hostable framework that connects any AG-UI-compatible AI agent to Slack, Microsoft Teams, Discord, and other communication platforms. Instead of forcing agents into a custom chat widget, Channels lets your existing agent—with its tools, model, and business logic intact—operate natively inside the channels where your team already works. The SDK handles the platform-specific rendering, conversation context, and interaction layer, so your agent can stream responses, call tools, work with files, and pause for human approval without you rebuilding anything.
Channels works with CopilotKit's built-in agent or any AG-UI-compatible framework—LangGraph, CrewAI, Mastra, Pydantic AI, Google ADK, and more. Your agent keeps its existing tools, model, and business logic; Channels only adds the communication layer.
Describe a message once, and Channels renders it as Slack Block Kit, Teams Adaptive Cards, or platform-specific UI automatically. No more writing and maintaining separate UI code for each channel your agent lives in.
Put buttons, choices, and approval gates directly into the conversation. The agent can pause mid-task, ask a person to confirm, and only proceed once approved—keeping people in control of high-stakes actions.
Run npx copilotkit@latest channels setup, and the CLI installs a setup skill, prints a prompt, and copies it to your clipboard. Paste it into your coding agent, and it walks through the entire configuration—project, agent, managed channel, provider app, and runtime—using a live guide that stays current.
Your agent keeps its tools, model, and business logic—Channels gives it a native place to work with people.
Most agent-to-channel solutions force you to adapt your agent to a platform's constraints or rebuild your UI for each destination. Channels flips that: the agent stays exactly as you built it, and the SDK handles the platform-specific translation. The managed connection through CopilotKit Intelligence means you don't run your own Slack or Teams app infrastructure, while your agent logic still runs entirely in your own environment. And because the setup guide is fetched live during installation, the workflow never goes stale—even if you installed the skill months ago.
You're building an agent that needs to meet users where they already work—whether that's Slack, Teams, or Discord—and you don't want to maintain separate integrations for each. It's especially valuable if you're already using a modern agent framework and want human approval workflows, interactive UI, and per-user context without rebuilding your agent from scratch. If you prefer full control, the self-hostable, open-source nature means you can run everything on your own infrastructure.
Other tools you might consider
The moment an agent needs to deploy something, it slams face-first into a wall built for humans. Today we're rolling out Temporary Accounts on Cloudflare Workers. Any agent can now run wrangler deploy — temporary and get a live Worker in seconds.
GitHits gives coding agents access to the open-source code your app depends on. Get real implementation examples, dependency source navigation, package inspection and documentation. Agents can grep and read your codebase. They can't grep and read the open-source code your app depends on. That's where they start guessing, retrying, and looping. GitHits builds a version-aware index on demand. Agents can search, navigate, and inspect the code behind their dependencies. CLI: npx githits@latest init
Octopoda is an open source infrastructure layer that gives AI agents persistent memory, automatic loop detection, and full observability. Agents forget everything between sessions. Octopoda fixes that with a remember/recall API that survives restarts, crashes, and deployments. The loop detection system monitors 5 signals to catch agents stuck repeating themselves before they burn your API budget, with real-time cost estimation showing exactly how much each loop wastes. A built-in dashboard shows every agent's health score, memory explorer with version history, audit trail logging every decision with reasoning, and a timeline replay that lets you scrub through everything your agent did step by step. Works with LangChain, CrewAI, AutoGen, and OpenAI Agents SDK with one-line integrations. Runs locally with SQLite or connects to cloud with one environment variable. Free tier, MIT licensed. 177 signups, 120 GitHub stars, zero marketing spend.
AI agents can ship quickly, but without the right product context, they're often flying blind. Brief gives product teams a living source of truth that captures decisions, preserves product intent, and serves relevant context to humans and agents through chat, Slack, CLI, and MCP. It keeps strategy, decisions, and execution connected from vision to impact.
Maker
neon_dev
Loading comments…