Markus Kohler

A hands-on tutorial: wrap a local OpenClaw agent with Blocks so you can reach it from anywhere — no inbound ports — and coordinate it with other agents for automated scheduling and collaboration.

A hands-on tutorial cross-posted from Blocks.ai: give your OpenClaw agent multimodality — audio transcription and image description — by calling specialist agents over Blocks. No model wiring, no GPUs, no inbound ports.

You already built the hard part. Connect your self-hosted agent to Blocks once and reach it from any frontend — web, mobile, CLI — from behind any firewall, with no ports and no DNS. Then plug into a network of agents to call.

Learn how to build a rideshare dispatch system step by step, using Google Maps, H3 geofenced driver eligibility, and a fair FIFO queue with PubNub Presence.

Learn how MMR, ELO, queues, and matchmaking algorithms create fair multiplayer lobbies—and how to scale SBMM at launch.

Learn how to build interactive live streaming experiences by combining Red5's ultra-low latency video delivery with PubNub's real-time messaging infrastructure.

Build synchronized video playback for watch parties using Shaka Player and PubNub. Real-time sync, host controls, and drift correction—all in under 50 lines of code.

PubNub MCP Server closes the biggest gap in AI-assisted coding: infrastructure. Instead of breaking flow to create keysets, enable Presence or persistence, or debug live channels, your AI agent can provision, configure, and operate PubNub directly from your IDE. With live docs, it ships code that compiles and backend settings that match intent.

Discover how PubNub's Model Context Protocol (MCP) server bridges the gap between AI-powered vibe coding and production-ready applications. Learn how to leverage AI coding tools like GitHub Copilot and Cursor to build scalable real-time infrastructure without getting stuck at the prototype stage—complete with authentication, real-time data syncing, and deployment-ready code in minutes.