
JavaScript
LiteRT.js Browser AI Without a Server
A production-minded LiteRT.js guide for running compatible AI models locally in the browser, from conversion and WebGPU execution to fallbacks, memory cleanup, caching, and testing.
100% private · no tracking · works offline100% client-side/no data leaves your browser/no accounts/works offline
Every tool runs 100% in your browser — zero servers, zero tracking. Plus practical articles & tutorials for modern developers.
Search 85+ tools · works offline after first load
§ 01 — Why developers trust it
Every tool executes locally. Nothing is uploaded — your code never leaves the tab.
No analytics on your inputs, no accounts, no cookies you didn’t ask for.
Load once and keep working on a plane. All 85+ tools, no paywall.
§ 02 — Toolchain index
A taste of the kit — all 85+ tools run in your browser.
§ 03 — Latest writing

JavaScript
A production-minded LiteRT.js guide for running compatible AI models locally in the browser, from conversion and WebGPU execution to fallbacks, memory cleanup, caching, and testing.
Developer Tools
A step-by-step walkthrough of installing ZCode, configuring Z.ai's open-weight GLM-5.2 model, running Goal Mode and MCP, and calling the API directly — plus how it stacks up against Claude Code, Cursor, and GitHub Copilot.
LLM
Context engineering, not prompt engineering, is what keeps AI agents coherent past a few turns. This guide covers the four core techniques (write, select, compress, isolate) with runnable Python examples for each.
§ 04 — Guided learning
Verify if images have proper alt text.
Open tool →AI Agents
A practical breakdown of GitHub Copilot's new AI Credits billing — how tokens convert to dollars, what every plan includes, and how to keep one agent session from eating your month's allowance.