Byoi
Project management that lives as Markdown in your own repo
What it does
A Git-native board where development work becomes governed instructions for coding agents: capture, AI enrichment, review gate, execution and versioned memory
Ideas and bugs become cards. Cards become complete instructions, scoped with AI, gated by your review. Any agent executes them and reports back to the board. Everything lives as Markdown in your Git Why not just an AGENTS.md and your harness's memory? Because a harness reads the repo. It finds what is near the task. It cannot know what should be built next, in what order, under which constraints, or whether a task is ready to leave Your AGENTS.md does not go away. It gains a source: the board maintains the rules, context and decisions your agents read Every screen below is a real card from the byoi repo. The loop in six moves, with the product on screen Board, terminal or a public feedback…from byoi.app
More dev tools this month
the category →



Open-source GTM skills for technical founders
Dev tools · 29d ago · gtmcofounder.com


OpenTrailPaper is open-source bike computer firmware for the LilyGO T5S3 4.7" E-Paper PRO. It supports offline maps, GPX routes, FIT recording and Bluetooth sensors.
Dev tools · 1d ago · opentrailpaper.com
Launched alongside, August 2026
the whole month →- TL
Life & fun · 10d ago · louisabraham.github.io


- SA
Hello HN! I found that picking out plausible but diverse skin tones for my digital art and game development projects was kind of difficult, and I got curious about if there was a way to define a color space that made it easy. I've built a color picker and procedural generation algorithm based on the space as well as a bunch of other fun js features and demos throughout the page that use the equations. If you find it interesting, I have lots of explanations of how I built it and what properties the space has. The methodology might be a bit shaky, but hopefully the result is as helpful for…
Life & fun · Aug 2026 · toneyalexander.github.io


I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 16d ago · simedw.com