this project is something i'd do, i had the idea about the same time as you did, "why something like cargo for c++ doesn't exist?" and you did it, thanks I guess.

try to picture gravity as de broglie matter waves refracting on a time gradient, it will make a lot of sense. i hope that helps

i wish i could do something for you, i have no money. wishing you luck

Thank you it's just so hard there is little to no help out there andvi have called so many places

https://github.com/krzysztofdudek/Yggdrasil this might interest you

what is OpenClaw and why there is so much fuzz right now?

Its an software that connects an chat with an chatbot with an terminal on your computer: An huge risk of loosing data and/or loosing money

I'm an Industrial Engineering student who got obsessed with program synthesis. Started building a freestanding microkernel in C++ to run genetic algorithms that would generate programs from prompts.

Halfway through I realized: "Wait, I'm just building a compiler with extra steps."

So I pivoted. 4 days later, Yori was born.

It's a meta-compiler that takes natural language/pseudocode and turns it into self-correcting binaries in 21 different languages.

Not trying to replace programmers—trying to create more of them by removing syntax as an entry barrier.

Built it during unemployment/vacation. Now wondering if this could be something bigger.

repo link https://github.com/alonsovm44/yori

share it to others

Hello HN,

I’m the author of Yori. It’s a command-line tool that treats natural language (English/Spanish) as source code and compiles it into standalone executables.

The Problem: I was working on a hobby OS and got tired of the context-switching between "Architecting" (thinking of logic) and "Implementing" (fighting syntax/boilerplate). I wanted a tool where I could write the intent, and the machine would handle the implementation details.

How it works: Yori isn't just a wrapper for an LLM. It acts as a build system that uses the C++ compiler (g++) as a "Truth Filter."

Draft: It reads a .yori file (natural language instructions) and prompts a local model (via Ollama) or cloud model (Gemini) to generate C++ code.

Verify: It attempts to compile the output with g++.

Evolve: If compilation fails, it captures the stderr output, feeds it back into the LLM along with the broken code, and asks for a fix. It repeats this loop until a valid binary is produced.

Features:

100% Local: Defaults to using qwen2.5-coder via Ollama. No API keys or internet required.

Incremental Builds: Can update existing C++ files without rewriting them from scratch.

Unity Build System: Supports IMPORT: tags to merge multiple prompt files into a single compilation unit.

It’s open source and written in C++. I know "AI coding" is a saturated market, but I wanted something that felt like a standard Unix tool—lightweight, local, and focused on producing binaries rather than just chat suggestions.

Repo is here: https://github.com/alonsovm44/yori I’d love to hear your feedback on the self-correction loop logic!