Run GLM-5.2 locally with Unsloth
A hands-on guide to running GLM-5.2 locally with Unsloth Dynamic GGUFs and llama.cpp, including memory requirements, quant selection, and the full launch command.
Guides
Simple, practical guides for developers building with modern tools.
Zero-Touch OAuth for MCP: authorizing AI agents without a browser
How Enterprise-Managed Authorization (EMA) and the ID-JAG token chain let headless AI agents access MCP servers without a browser redirect or per-server consent screen.
Build launch videos from the command line with brag
Learn how to use the brag CLI skill for Claude Code to turn any project into a shareable launch video in one command, with a full walkthrough on a real OSS repo.
Apple-style Liquid Glass effects in React with liquid-glass-react
How to add Apple's iOS 26 Liquid Glass effect to a React app using the liquid-glass-react library, including modes, props, browser compatibility, and a live nav bar example.
SSH tunnels from scratch: local and remote port forwarding explained
Learn how SSH local, remote, and dynamic port forwarding work, when to use each, and how to set up sshd_config so your tunnels actually work.
Persistent Memory for Claude Code Sessions with Recall
Set up Claude Code persistent memory safely with built-in memory, the third-party Recall plugin, and the separate Recall web-app MCP path.
How to Stop AI Agents from Bankrupting You: Rate Limits, Budgets, and Kill Switches
An AI agent ran up a $6,531 AWS bill in 24 hours while scanning a hobbyist network. Here are five controls to add before you deploy an agent.
How to use Ponytail to make your AI coding agent write less code
Ponytail is an agent-portable skill that turns any AI coding agent into a lazy senior developer — 80-94% less code, 47-77% less cost, 3-6x faster.
How to Generate Lottie Animations with Claude Code (2026)
Three ways to generate production-ready Lottie animations with Claude Code: the diffusionstudio skill, the Lottie Creator MCP, and the 21st SDK agent pattern.
The Planner-Executor Pattern for AI Coding (with shadcn/improve)
Use your most capable model to audit and plan, then hand the work to a cheaper executor. A practical guide to the planner-executor pattern using shadcn/improve.