Most Popular
CopilotKit integration with CrewAI (Crews)
Copy-paste command to clone the canonical starter
npx copilotkit@latest init --framework crewai-crews
Natural conversation with frontend tool execution
Visible reasoning/thinking chain alongside the final answer
Built-in CopilotChatReasoningMessage renders without a custom slot
Docked sidebar chat via <CopilotSidebar />
Floating popup chat via <CopilotPopup />
Customize CopilotChat via its slot system
Default CopilotChat re-themed via CopilotKitCSSProperties
Minimal custom chat surface built on useAgent
Full chat implementation built from scratch on useAgent
User approves agent actions before execution
Time-picker card rendered inline via useHumanInTheLoop for a booking flow
Agent requests approval via useFrontendTool; the approval UI pops up as an app-level modal OUTSIDE the chat
Original CrewAI HITL demo — kept for backwards-compat
Custom per-tool renderers plus a wildcard catch-all for every other tool
Out-of-the-box tool rendering — backend defines the tools; the frontend adds zero custom renderers and relies on CopilotKit's built-in default UI
Single branded wildcard renderer via useDefaultRenderTool — the same app-designed card paints every tool call
Sequential tool calls with reasoning tokens side-by-side
Long-running agent tasks with generated UI
Agent uses tools to trigger UI generation
Agent invokes client-side handlers registered with useFrontendTool
useFrontendTool with an async handler
Per-token state delta streaming from agent to UI
Bidirectional shared state - UI writes preferences, agent writes notes
Supervisor delegates to research / writing / critique CrewAI sub-crews with a live delegation log
Frontend provides read-only context to the agent via useAgentContext
Agent generates UI from an arbitrary component library
Agent-authored UI that invokes host sandbox functions from inside the iframe
Forward a typed config object (tone / expertise / response length) from the provider to the agent
Runtime-level bearer-token auth via the V2 onRequest hook
Speech-to-text transcription via @copilotkit/voice mounted on a per-demo runtime
Image and PDF uploads routed through the AG-UI attachment pipeline
Branded A2UI components generated by a secondary LLM against a custom catalog
Pre-authored component tree; the agent streams only data into the data model
Streaming structured output via @hashbrownai/react against a custom catalog
Flat {root, elements} spec rendered by @json-render/react against a Zod catalog
Flagship showcase - polished brand-styled chat with A2UI, Open Generative UI, and shared-state todos
MCP server-driven UI via activity renderers
Interrupt-style scheduling via useFrontendTool with an async Promise — time-picker card rendered inline in chat
Headless interrupt via useFrontendTool — time-picker popup appears in the app surface outside the chat
