Pinggy Blog

Tunnels, networking, self-hosted LLMs, and AI news

Hands-on guides, protocol deep dives, and field notes on tunnels, SSH, reverse proxies, self-hosting, self-hosted LLMs, and AI - from the people building Pinggy.


Edge Functions on MicroVMs: Why Netlify Left V8 Isolates

Netlify Edge Computing Security

Netlify moved Edge Functions from V8 isolates to Firecracker microVMs and cut median warm latency from 25-40 ms to 5-6 ms. Here is how microVM snapshots, EROFS and rendezvous hashing make that work.

SEO vs AEO vs GEO: How to Rank in AI Search in 2026

AI Search GEO SEO

AI Overviews cut top-result clicks by 58% and AI Mode passed 1 billion users. What SEO, AEO and GEO actually mean, how AI answers pick their sources, and tested steps to get your pages cited.

Running a 0.5B LLM on Seven ESP32-S3 Boards

ESP32 BitNet Edge AI

How an open-source cluster of seven ESP32-S3 microcontrollers splits a Qwen2-0.5B model into 1.58-bit ternary layers, why it fits in 16 MB of flash per board, and why it is slow.

Best Computer Use MCP Servers in 2026: Let AI Agents Control Mac, Windows and Linux

MCP AI Agents Automation

The best computer use MCP servers in 2026, tested: Claude Code's built-in computer-use, Windows-MCP, Cua Driver, Peekaboo, Open Computer Use, macOS-MCP, computer-use-linux and computer-use-mcp, with install commands, tool counts, permissions, and how to reach a remote desktop over a Pinggy tunnel.