GRAYFORGE LABS

// Personal software studio

Curiosity. Learning. Joy.

Forging software, one spark at a time.

▾

// 02 Products

Undercurrent

Undercurrent

for iOS

A private notebook for symptoms and the daily events that surround them. Log in four taps or just tell the on-device AI assistant in plain language. Insights surface the patterns hiding in your own data — co-occurrences, time-of-day clusters, and day-of-week peaks. Export a clinician-ready PDF for your next appointment. Everything stays on your device.

undercurrent.grayforgelabs.com →
Undercurrent event logging Undercurrent timeline view Undercurrent pattern insights
Homebound

Homebound

for iOS

A minimalist one-tap arcade game about launching cute, lost creatures back to their home planet. Tap to fire, time it right, and watch where they land. 250 handcrafted levels, a fresh Daily Challenge, Game Center leaderboards, and a campaign that plays fully offline.

homebound.grayforgelabs.com →
Homebound gameplay: tap to land creatures on a spinning planet Homebound mechanics: dodge moons, belts, meteors, pulses, eclipses Homebound Daily Challenge: five levels, one leaderboard
Goblin Mob Boss

Goblin Mob Boss

open source · for macOS, Windows, Linux

A desktop app for orchestrating Claude Code multi-agent workflows. Attach context, configure agents, plan features interactively, then execute with parallel agent teams or delegated subagents. Handles git branches, worktrees, and validation across repos. Built with Tauri, React, and Rust.

github.com/llrowat/goblin-mob-boss →
Goblin Mob Boss agent configuration Goblin Mob Boss execution view Goblin Mob Boss system map
Agent Corral

Agent Corral

open source · for macOS, Windows, Linux

A desktop app for managing Claude Code configuration across repositories. Visual editors for agents, hooks, skills, MCP servers, and settings. Built with Tauri, React, and Rust.

github.com/llrowat/agent-corral →
Agent Corral overview dashboard Agent Corral agent studio Agent Corral settings
Botwash

Botwash

for Web

The car wash for AI text. Paste AI-generated content, pick a community-made wash formula, and get natural-sounding writing back. Browse, remix, and publish reusable transforms that strip the robotic tone from LLM output.

botwash.io →
Botwash Run Bay Botwash Formula Hub Botwash formula detail

// 03 Dev Log

Notes from the forge: thoughts on AI, software, and whatever else sparks.

2026.05.22 The Growth Bet #ai Every technology leap offers two paths: cost savings, which has a floor, and growth, which does not. The historical record on which one we take is more lopsided than the current AI discourse suggests. 2026.05.17 The Reaction Is the Character #product Reactions, not writing or voice acting, are the load-bearing structure of emotional connection in games. The half-second between a player acting and a character responding is where the work happens. 2026.05.08 The Field Got Wider #career The guilt engine raised the ceiling on what you can build. The orchestrator role widens the field of what you are managing right now. Notes on agent management overhead and the cost of running parallel. 2026.05.03 The Wild West of AI Tooling #ai A new AI tool goes viral on X every week. Some of it is influencer pump. The data underneath shows something more interesting, and the convergence is already happening. 2026.04.29 The Tip and the Wave #ai ChatGPT just hit 900 million weekly users. That's about 10% of the world. The exhaustion of keeping up with AI is real, but it's mislocated. 2026.04.25 AI Writes the Code. Who's Testing It? #ai AI coding tools shipped first and shipped loud. The agentic testing wave arriving now is the more interesting story, and the benchmarks are starting to lean its way. 2026.04.19 A Weekend with Claude #ai A weekend of using Claude Design, Claude Code, and Claude Cowork. Notes on what Anthropic's stack looks like from the inside, and why the handoffs are what changed. 2026.04.17 The Guilt Engine #career Why the more you build with AI, the further behind you feel. Notes on the ambient pressure to keep shipping, and how to tell useful guilt from the kind that just burns fuel. 2026.04.14 The Llama That Wouldn't Fit #ai I tried to ship a 3B parameter Llama inside an iOS app. iOS had other ideas. What jetsam, extended memory entitlements, and Apple Intelligence taught me about on-device AI. 2026.04.10 The Models That Work Too Well #ai Anthropic won't ship Claude Mythos. OpenAI is staggering Spud. Two frontier labs, one week, the same flinch. Default-ship is quietly becoming default-gate. 2026.04.09 Everyone Hates AI in Games. Everyone's Already Using It. #ai 85% of players reject AI in games. 90% of developers already use it. The gap between those numbers is where the future of game design actually lives. 2026.04.08 AI Gave Robots a Brain. The Hard Part Just Started. #ai Jensen Huang called 2026 the "ChatGPT moment" for physical AI. The real story is more interesting, and more complicated. 2026.04.06 The Three-Year Forecast for Knowledge Work #ai AI hasn't wiped out knowledge jobs yet. But the next three years will reshape them beyond recognition. 2026.04.05 The Spark Came Back #career AI coding tools didn't just make me faster. They brought back the part of building I thought I'd lost for good. 2026.04.04 Work Work: How Claude Code Joined WoW's Addon Arms Race #ai When Blizzard killed WeakAuras, RWF guilds turned to Claude Code to build custom boss addons mid-race. AI coding tools just became part of competitive raiding. 2026.04.03 OpenClaw: The AI Agent That's Selling Out Mac Minis #ai OpenClaw turned the Mac Mini into a personal AI appliance. Here's what it is, why people are buying dedicated hardware for it, and what can go wrong. 2026.04.02 What's the Difference Between LLMs and World Models? #ai Yann LeCun just raised a billion dollars betting that world models are the future. Here's what that actually means. 2026.04.01 Strawberries, Sisters, and Carwashes: What Viral LLM Failures Actually Reveal #ai Why the internet's favorite LLM gotchas aren't random bugs, but windows into how models actually work. 2026.03.31 The Software Developer of Today Writes No Code #career I handed off all code writing to Claude Code. The job already changed. 2026.03.31 Botwash: A Post-Mortem for a Product That Got Out-Evolved #product Building for a problem with a shelf life, and what I'd do differently next time. 2026.03.30 Slipstream: Building a 51M Parameter F1 Expert LLM in a Weekend #ai A transformer from scratch, trained on F1 Wikipedia articles. 51M parameters, 3.5 hours on a MacBook Pro.
view all posts → subscribe via rss

// 04 About

Lloyd Rowat
Lloyd Rowat Builder. AI tinkerer. Lifelong learner.

I'm a software developer with over a decade of experience building platforms, shipping products, and leading technical direction across companies of all sizes. I have a Master's in computer science from the University of Waterloo, and my career has taken me from telecom systems to data analytics to construction tech.

These days, AI is where my energy goes. I see it as the most important shift in software since the internet, and a turning point for humanity as a whole. I'm excited to keep learning and to be building at its edge.

Grayforge Labs is my personal forge — where I take the ideas that won't leave me alone and turn them into tools that actually work. I build software the way a blacksmith works metal: with patience, precision, and an obsession with getting the details right.

// 05 Contact

Want to collaborate, have a question, or just want to talk shop?

GH GitHub @ Email