{"slug": "i-built-an-x86-64-kernel-from-scratch-and-it-made-me-hate-ai-documentation-tools", "title": "I built an x86_64 kernel from scratch, and it made me hate AI documentation tools. So I built my own.", "summary": "A developer building an x86_64 kernel named TaterTOS64 found that AI documentation tools hallucinated incorrect code dependencies and failed to understand the project's repository structure. In response, they built TaterBookBuilder, a deterministic documentation compiler that resolves include directives to actual file locations and allows for local-first, perpetual ownership without cloud subscriptions. The tool is distributed as a 77MB Linux AppImage with a one-time purchase model, aiming to provide reliable, architecture-specific documentation for systems developers.", "body_md": "Six months ago, I started building TaterTOS64, an x86_64 kernel. As any systems dev knows, once you hit the 10,000-line mark across a mix of C, Assembly, and Linker scripts, your brain starts to leak. I needed a way to document the architectural \"why\"—how the interrupt vectors hand off to the scheduler, how the paging logic relates to the physical memory map.\nNaturally, I tried the modern approach: I fed the code to LLMs.\nThe Result was a Disaster.\nGeneric \"AI Doc\" tools failed me in three specific ways:\n.c\nfile but completely hallucinate the #include\nchain. They had no idea where the paging.h\nconstants were actually defined in my repo structure.Building the Solution: TaterBookBuilder\nI decided to stop building the kernel for two weeks and build the documentation compiler I actually wanted. I call it TaterBookBuilder.\nInstead of a simple \"text-to-prompt\" wrapper, I built a deterministic analysis engine first.\nHow it actually works:\n#include\n(C) and %include\n(Assembly) to its canonical repository node. No more guessing where types come from.src/kernel/sched.c:L45-L120\n.The Philosophy: Local-First and Perpetual\nDocumentation is a permanent asset. It shouldn't depend on a cloud subscription.\nI'm shipping TaterBookBuilder as a 77MB Linux AppImage. It's completely turnkey—I even bundled a static binary of Pandoc inside it so you don't have to install a single dependency.\nAnd for the pricing? I'm using the JetBrains Model. You buy it once, you own that version forever. You get a year of maintenance, and if you don't want to renew, your documentation pipeline keeps working exactly as it did on day one.\nDocumentation should be as rock-solid and local as the code it describes.\nCheck out the workbench and download the trial here:\nhttps://taterlabs.shop/taterbook.html\nI'd love to hear from other systems devs—how are you handling the \"trust gap\" with AI-generated architecture maps?", "url": "https://wpnews.pro/news/i-built-an-x86-64-kernel-from-scratch-and-it-made-me-hate-ai-documentation-tools", "canonical_source": "https://dev.to/taterlabsllc/i-built-an-x8664-kernel-from-scratch-and-it-made-me-hate-ai-documentation-tools-so-i-built-my-3dp2", "published_at": "2026-05-20 07:54:06+00:00", "updated_at": "2026-05-20 08:03:00.371141+00:00", "lang": "en", "topics": ["developer-tools", "open-source", "large-language-models", "artificial-intelligence", "products"], "entities": ["TaterTOS64", "TaterBookBuilder", "LLMs", "Pandoc", "JetBrains", "Linux AppImage"], "alternates": {"html": "https://wpnews.pro/news/i-built-an-x86-64-kernel-from-scratch-and-it-made-me-hate-ai-documentation-tools", "markdown": "https://wpnews.pro/news/i-built-an-x86-64-kernel-from-scratch-and-it-made-me-hate-ai-documentation-tools.md", "text": "https://wpnews.pro/news/i-built-an-x86-64-kernel-from-scratch-and-it-made-me-hate-ai-documentation-tools.txt", "jsonld": "https://wpnews.pro/news/i-built-an-x86-64-kernel-from-scratch-and-it-made-me-hate-ai-documentation-tools.jsonld"}}