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.
StudioForge: A GPU-Only LLM Server That Replaced LM Studio on My Rig, Run Remotely by My Agents
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 rather than spilling it to the CPU, pins the ones that must stay warm, and publishes 29 MCP tools so an agent on another machine runs the whole rig. Free download, source on GitHub.
SiftForge: A Local-LLM Email Assistant That Reads Your Mail, Writes the Reply, and Never Sends It
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.
Eight AI Agents, One AMD Box: My Local Agent Stack (OpenClaw)
Eight named AI agents live on one mini PC in my house — a dispatcher, a hard thinker, a 120B local workhorse, a vision bot — with DeepSeek's cheap API doing the heavy lifting for about $24 a month.
DisPatch: A Self-Hosted Chat App for Local AI Agents
A locally hosted LLM chat app, file server, and terminal — available on every device in the house at all times. The ~720KB app I built to replace a 30-container Rocket.Chat install.
DeepSeek Harness (dsh): I Installed DeepSeek's Open-Source Coding Agent, Wired It Into My Chat App, and Benchmarked It
DeepSeek shipped an MIT-licensed coding agent on August 13. Five days later it runs on my Bluefin box as a systemd service, sits next to Reasonix in DisPatch, and passed 15/15 tasks on three models — including a local one. Setup, numbers, gotchas.
The CHUWI AuBox Ai365: My AI Home Lab in a Box
An obscure Strix Point mini PC with dual 2.5GbE, USB4 and a Ryzen AI 9 365 — running Bluefin Linux, hosting eight AI agents, and drawing under 5 W at the chip. It replaced a dead 128 GB tablet, and this post gets updated as the box changes.
My AI Agent Built a Benchmarking Tool for My AI Agents
I asked Hermes, my coding agent, to build a CLI that benchmarks my local models. It came back with bench-llm — 1,660 lines of Python against LM Studio. A year of using it turned it into CrucibleForge: 251 cases, 158 of them hard, graded by execution.
What My AI Agents Actually Cost: DeepSeek vs the Big APIs
Two months of my always-on agent stack cost $30.57 on DeepSeek — $6.49 for July alone. But DeepSeek raises prices on August 16, and the same July workload jumps to ~$14–$27. Full old-vs-new breakdown, plus what GPT-5.6, Claude, Grok, and Kimi would charge.
Reasonix: A Claude-Code-Style Coding Agent on DeepSeek
A terminal coding agent that works like Claude Code — subagents, skills, project memory — but runs against DeepSeek's pay-per-token API instead of a subscription. Setup, model tiers, and a hands-off auto-updater.
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.