Zen Mascot

I build simple solutions
for complex problems.

Hi, I'm Ghazi. I build lightweight tools for developers, focused on performance, clarity, and privacy-first systems.

See my projects
file_type_python file_type_mysql
Currently Building

docmd

Build production-ready documentation from Markdown in seconds. No React, no bloat, just content.

DocumentationMarkdownCLIBunNode.jsTypeScript
Check it out →
docmd

memoryblock

Private AI workspaces that run locally, using fewer tokens and less compute.

AILLMPrivateLocalWeb AppCLILibraryBunTypeScript

AIMonitor

Native macOS menu bar app for monitoring AI usage, quotas, and provider status in real time.

macOSSwiftAIMenu BarOpen Source

Latest Rollups

View all →
Nov 8, 2026

FoundationWorlds: Building Better Robot Learning Testbeds

How controlled simulation environments like ToyBlocks are solving the reproducibility crisis in robotics research and enabling systematic model evaluation.

Nov 8, 2026

Gemini Omni 1.2 Flash: 30% Cheaper Video Generation at Scale

Google's latest video model cuts costs by 30%, extends clips to 15 seconds, and improves consistency. What this means for developers building at scale.

Nov 8, 2026

Gemini Omni 1.2 Flash: 15-Second Video Generation at Scale

Google's latest video model drops 30% in cost, extends clips to 15 seconds, and improves consistency. What this means for developers building video-first applications.

Nov 7, 2026

F3 Lightning: How Meta Decoupled Release Speed from Execution Efficiency

Meta's F3 Lightning solves a critical scaling problem: independent feature releases without sacrificing the computational efficiency of shared execution graphs.

Nov 7, 2026

Qwen 27B Can Read Neural Network Weights Too

A 17GB open model running locally can interpret raw network weights without code execution. What this actually means for AI development.

Nov 7, 2026

FoundationWorlds: Why Robot Learning Needs Controlled Testbeds

Introducing ToyBlocks, a simulated environment that lets researchers systematically study robot learning. Here's why this matters for AI development.