All writing

28 essays, notes, and practical write-ups on AI, developer tools, and software craft.

May

2026

19 May 2026 8 min read

Zero: Vercel Labs' agent-readable programming language

Zero is a pre-1 systems language experiment where the compiler, standard library, and diagnostics are designed for AI agents first.

#ai #developer-tools #open-source

April

2026

13 Apr 2026 9 min read

Ollama Cloud is a sleeper option for AI coding workflows

Ollama Cloud quietly combines serious open models with a low-faff toolchain for Codex, Claude Code, OpenCode, and OpenClaw.

#ai #llm #developer-tools

March

2026

23 Mar 2026 8 min read

Understand-Anything: a knowledge graph for your codebase that hit 5K stars in a week

A deep look at the Claude Code plugin that turns codebases into interactive knowledge graphs — how the multi-agent pipeline works, what the dashboard looks like, and where the rough edges are.

#ai #claude-code #developer-tools

20 Mar 2026 7 min read

Mole: the open-source Bash+Go tool replacing $60+ of paid Mac apps

A look at tw93's Mole — a CLI tool with over 40k GitHub stars that consolidates CleanMyMac, DaisyDisk, iStat Menus, and AppCleaner into a single free utility.

#open-source #macos #developer-tools

19 Mar 2026 7 min read

just-bash: a full shell in pure TypeScript for AI agents

Vercel Labs reimplemented bash and 70+ Unix commands in pure TypeScript, giving AI agents a sandboxed shell that runs anywhere JavaScript does.

#ai #developer-tools #typescript

18 Mar 2026 11 min read

GLM-5 vs Kimi K2.5 vs MiniMax M2.5: a practical coding showdown

Three Chinese MoE models claim frontier-class coding at a fraction of Opus pricing. Here's how they actually perform in Claude Code, Cursor, and real developer workflows.

#ai #llm #developer-tools

16 Mar 2026 8 min read

Stop giving your AI agent tasks — give it goals

The difference between managing and micro-managing AI agents is the same gap that separates good tech leads from bad ones. Share the why, not just the what.

#ai #claude-code #developer-tools

14 Mar 2026 5 min read

Browse: a faster alternative to Playwright MCP for AI agents

Introducing browse, a CLI tool that wraps Playwright behind a persistent Unix socket daemon for sub-30ms browser automation commands.

#ai #developer-tools #cli

12 Mar 2026 8 min read

Nemotron 3 Super: NVIDIA's 120B open-weight model built for agentic workloads

NVIDIA's Nemotron 3 Super packs 120B parameters into 12B active, combining Mamba-2, Transformers, and a novel LatentMoE — all open-weight and purpose-built for multi-agent systems.

#ai #machine-learning #llm

11 Mar 2026 7 min read

cmux: a purpose-built terminal for the parallel agent workflow

cmux is a native macOS terminal built on Ghostty's rendering engine, designed for running multiple AI coding agents in parallel with rich notifications and a scriptable API.

#ai #developer-tools #cli

11 Mar 2026 6 min read

NotebookLM without the browser: automate AI podcasts from your terminal or your chatbot

notebooklm-py gives you programmatic access to Google NotebookLM. Even better, it works as an AI agent skill — so you can generate podcasts, quizzes, and slide decks just by asking Claude or ChatGPT.

#ai #open-source #cli

8 Mar 2026 7 min read

Scheduled tasks in Claude Code: automate the boring waits

Claude Code can poll deployments, babysit PRs, and remind you to push — all with a single /loop command or a plain-English sentence.

#claude-code #developer-tools #ai

4 Mar 2026 6 min read

OpenAI's WebSocket mode: persistent connections for agentic workloads

OpenAI's Responses API now supports WebSocket transport. For tool-call-heavy agent loops, it cuts end-to-end latency by up to 40%.

#ai #openai #websockets

2 Mar 2026 8 min read

Kimi K2.5 vs Claude Opus 4.6: a practical comparison for developers

Kimi K2.5 delivers 95% of Opus 4.6's coding capability at 10-25× lower cost. But the benchmarks don't tell the whole story.

#ai #llm #developer-tools

1 Mar 2026 7 min read

Skills, CLI, and MCP: picking the right tool layer for your AI agent

A practical guide to when Skills, CLI tools, and Model Context Protocol each shine — and why the best agent setups use all three.

#ai #developer-tools #claude-code

February

2026

28 Feb 2026 8 min read

Writing code is no longer the bottleneck

Block cut 4,000 employees while posting record profit. The development pipeline has permanently shifted — and most companies haven't caught up.

#ai #developer-tools

27 Feb 2026 5 min read

Building a self-healing server with Claude Code and a Bash script

How I built openclaw-watchdog — a lightweight monitoring tool that uses Claude Code to automatically diagnose and fix OpenClaw gateway failures.

#ai #claude-code #open-source

25 Feb 2026 7 min read

Give your AI agent a memory: semantic git search with git-semantic-bun

AI coding agents forget everything between sessions. git-semantic-bun lets them search commit history by meaning — locally, offline, and in a format machines can consume.

#ai #developer-tools #cli

22 Feb 2026 5 min read

Self-hosting OpenClaw on Proxmox with an Ubuntu VM

A practical, reproducible guide to running OpenClaw on Proxmox with Ubuntu, including VM sizing, gateway service setup, security hardening, and troubleshooting.

#self-hosting #proxmox #ubuntu

20 Feb 2026 7 min read

Anthropic studied 1.5 million conversations and found we're not checking AI's work

Two new Anthropic studies reveal that users voluntarily cede judgment to AI — and feel good about it until things go wrong.

#ai #machine-learning #ai-safety

19 Feb 2026 6 min read

Gemini 3.1 Pro: Google's reasoning leap

Google's latest frontier model more than doubles its predecessor's reasoning score in three months, leads 13 of 16 benchmarks, and ships at the same price. The adaptive compute architecture is the interesting part.

#machine-learning #llm #ai

18 Feb 2026 10 min read

Claude Code vs Codex for Laravel teams: choosing your AI coding tool in 2026

A detailed comparison of Claude Opus 4.6 and GPT-5.3-Codex for Laravel/Vue/Inertia stacks — benchmarks, costs, ecosystem depth, and practical recommendations.

#claude-code #laravel #developer-tools

17 Feb 2026 9 min read

Claude Sonnet 4.6: Opus-level performance at a fifth of the price

Anthropic's second major launch in two weeks puts near-flagship capability at $3/$15 per million tokens. The mid-tier label is starting to feel like a misnomer.

#machine-learning #llm #ai

17 Feb 2026 11 min read

Superpowers: the Claude Code plugin that enforces what you already know you should do

A look at the most popular Claude Code plugin — how it turns AI coding agents from capable-but-undisciplined into structured development partners through composable skills.

#claude-code #developer-tools #ai

14 Feb 2026 8 min read

A structured workflow for building features with AI coding agents

A seven-step process for turning requirements into shipped features using Claude Code — from scoping with parallel sub-agents to test-driven execution.

#claude-code #ai #developer-tools

13 Feb 2026 8 min read

claude-mem vs auto memory: do you need a memory plugin for Claude Code?

Claude Code now has built-in auto memory, but a 28k-star plugin called claude-mem offers a far more sophisticated approach. Here's how they compare and when each makes sense.

#claude-code #developer-tools #ai

12 Feb 2026 10 min read

MiniMax M2.5: the agent-native model that costs a dollar an hour

A 230B MoE model with 10B active parameters hits 80.2% on SWE-Bench Verified at 1/20th the cost of Opus. Here's what's real and what's hype.

#machine-learning #llm #open-source

11 Feb 2026 8 min read

GLM-5: the open-weight model that's rewriting the frontier economics

Zhipu AI's 744B mixture-of-experts model ships under MIT license with frontier-class benchmarks and aggressive pricing. Here's what actually matters.

#machine-learning #llm #open-source