Laser and other tech projects,
always free for your use.
Every post has the details, process, and exact settings to duplicate it yourself. The site is live and maintained — and most of the work here, including this site itself, is done with LLMs.
Latest projects
Builds, guides, and experiments from the shop.
TransForge: Translate a Static Site With a Local LLM, Only the Pages That Changed
TransForge is the command-line tool that keeps this site in seven more languages. It sends Markdown pages to a model on my own GPU box, checks every translation before writing it, and only re-translates a page when its English source actually changed. Free, MIT.
ThemeForge: a Drop-in CSS Theme System an AI Agent Installs in One Step
ThemeForge is a single folder, `ui-theme/`, that gives a web app thirteen colour themes, a picker, design tokens and ready-made component classes — and it's written so an AI coding agent can install it in one step from a one-line Python command. Plain CSS, no build step, no dependencies; MIT; source and zip below.
StudioForge: A GPU-Only LLM Server That Replaced LM Studio
I wrote the model server I wanted: an OpenAI-compatible llama.cpp gateway on port 1234 that plans VRAM before it loads, refuses a model instead of spilling it to the CPU, keeps pinned models warm, and gives an agent on another machine 29 MCP tools to run the rig. Free download, source on GitHub.
StudioForge 2.0: Accounts, Scoped API Keys and a Safe Upgrade Path
StudioForge 2.0 locks the model server down by default: loopback only, an owner account, and a scoped API key per client. What breaks on upgrade, the ten-minute way through it, and screenshots of the new panel.
Run DisPatch and My AI Tools in Docker: One File, One Command
A private AI chat app for your home, running in Docker. Copy one file, run one command, answer a short setup wizard, and chat with a model on your own computer. Every step tested, with screenshots.
MailForge: A Local-LLM Email Assistant That Never Sends
A self-hosted email triage assistant: an IMAP listener, a local model, and a drafts queue. It classifies, labels and writes the reply, then stops. Sending is a human click, always. Free, MIT, download below.
InfoForge: Offline Wikipedia as a RAG Source for My Local AI Agents
All of English Wikipedia — 19.19 million entries, 52.69 GB, no internet — sitting behind a local search index my AI agents can query. Every answer cites its articles, and when it can't find one it says so instead of guessing.
DisPatch: A Self-Hosted Chat App for Local AI Agents
A self-hosted chat app for local AI agents, with a drag-drop file server and a server-enforced PIN lock. It replaced my 30-container Rocket.Chat install. The download is the 3 MB 2.0 zip; version 3.0 with family profiles is on GitHub.
DisPatch 3.0: Family Profiles, a Setup Wizard and Agents That Ask First
DisPatch 3.0 swaps one PIN and Safe Mode for real profiles: an Owner, Admins, Members, and Restricted kids' profiles with quiet hours and daily limits. Plus a setup wizard, encrypted backups and agent tasks.
Browse by type
AI & Local LLM
Running AI on your own hardware — local LLMs, agents, and image generation. No subscriptions, no cloud, no computer-science degree.
Laser Projects
Cutting, engraving, and the occasional small fire. Each post has the details, process, and settings you need to duplicate it yourself.
Tools & Downloads
Small apps and utilities I built and actually use. Free downloads for personal use, source included.