Realtime Kanban — AI-native UI updates with Vovk.ts

Realtime Kanban is an example app. It keeps a Next.js UI in sync with the backend and adds several AI features: an MCP server, OpenAI function calling, a voice interface, embeddings, and a Telegram bot. This series shows how it is built. Users, bots, AI agents, and MCP clients all update the same board in real time, with little extra code. It is an example to learn from and copy, not a framework or a required architecture. Take the parts you need.

All articles in this series are also in one text file for AI tools: realtime-ui.txt.

📘Realtime Kanban Overview ▶️Run Locally with Docker Compose 🚀Deploy to Vercel 🧩State Normalization with Zustand 🗃️Database Setup with Prisma and Zod Generator 🔗API Endpoints 🧠Vector Search via Embeddings 🔄Database Polling with Redis 🔐Basic Authentication and Authorization (Password Protection)💬Text AI Chat Integration with AI SDK and AI Elements 🎙️OpenAI Realtime API with WebRTC 🔌MCP Server 📨Telegram Bot with OpenAPI Mixins

See it in action

AI agent managing the board via MCP

Claude connects to the board through an MCP server and creates, moves, and deletes cards on its own.

Multi-user collaboration with live polling

Several users edit the same board at once. Changes reach everyone in real time through database polling and normalized state.

Chat-driven board updates with function calling

A text chat lets users manage cards in plain language. It uses OpenAI function calling.