Build along
Projects you can follow Each one ends with something running. What you need is listed before you start.
Dark mode Project
You need A Linux machine with an NVIDIA GPU and Python 3.11 or newer.
You end up with A model answering OpenAI-style requests on your own machine. 2026-11-12 · 5 min read
Project
You need A Linux machine with an NVIDIA GPU and its driver, Docker, and sudo rights.
You end up with vLLM running as a container that restarts with the machine, answering on a local port. 2026-11-12 · 9 min read
Project
You need The Docker setup from part 2 and one NVIDIA GPU with 24 GB of memory or more.
You end up with A Qwen3 server that chats, shows or hides its reasoning, and calls your functions. 2026-11-12 · 9 min read
Project
You need The Docker setup from part 2, about 70 GB of free disk, and one A100 80GB or two A100 40GB cards.
You end up with A private coding assistant behind an OpenAI-style chat endpoint, with a template you wrote and tested. 2026-11-12 · 9 min read · Partly tested
Project
You need A working vLLM container from parts 2 to 4, a host name for the server, and a TLS certificate for it.
You end up with One HTTPS endpoint where each person has their own key, a rate limit and a usage log, and nothing else is reachable. 2026-11-12 · 11 min read · Partly tested
Project
You need The GPU host and Docker setup from part 2. About 2 GB of disk for images and data.
You end up with Dashboards for CPU, memory, disk, every GPU and the model server, plus alert rules, all started by one command. 2026-11-12 · 10 min read · Partly tested
Project
You need The monitoring stack from part 7, and a Telegram account. The test in section 6 needs only Prometheus, Alertmanager and Python on any machine.
You end up with Urgent alerts that ring your phone, minor ones that arrive silently, a way to pause them during maintenance, and a check that the alerting itself is alive. 2026-11-12 · 12 min read · Partly tested
Project
You need A Mac mini with Apple silicon on macOS 14 or newer, 16 GB of memory or more, and your home network.
You end up with A private assistant that is always on, answers in a browser on your phone and laptop, and speaks the OpenAI API to your scripts. 2026-11-12 · 9 min read
Project
You need Claude Code, a project folder, bash and jq. On Windows, Git for Windows provides bash.
You end up with Five working hooks in .claude/hooks, one settings file that registers them, and a script that proves each one behaves. 2026-11-12 · 9 min read · Tested
Project
You need Claude Code installed on macOS or Windows, a terminal, and Python 3 for the practice server.
You end up with One remote and one local MCP server connected, one plugin installed, and the commands to manage both. 2026-11-12 · 13 min read · Tested
Project
You need Python 3.10 or later and Claude Code. No GPU, no API key and no packages for the first version.
You end up with A to-do list server that Claude Code connects to and can use through three tools, in two versions: hand-written and SDK-based. 2026-11-12 · 16 min read · Tested
Project
You need Claude Code, bash and jq. On Windows, Git for Windows provides bash.
You end up with A current version with the built-in protection on, one extra hook that blocks tool calls carrying your address, and a repository with no personal settings file in it. 2026-11-12 · 12 min read · Partly tested
Project
You need A vLLM server with a model that supports tool calling, and Claude Code. Section 4's test needs only Python and Claude Code.
You end up with Claude Code talking to a model on your own hardware, with a clear view of what works, what does not and what it costs in context. 2026-11-12 · 9 min read · Partly tested
Project
You need Claude Code and Python. No API key and no model: the requests go to a recorder on your own machine.
You end up with The size of your own setup, part by part, and a short list of what to trim. 2026-11-12 · 10 min read · Partly tested