Show HN: Teamlibra/ry: a Zig framework for Cursor that makes prompting better
https://codeberg.org/teamlibra/ry
We've been running Cursor Ultra ($200/month) in Auto Mode for extended sessions — sometimes 8+ hours of autonomous development. This repository is the result: 170k+ lines of Zig, a complete RISC-V64 operating system.*The Cursor Ultra Experience:*
Auto Mode changes everything. Instead of prompting line-by-line, we describe high-level goals: - "Fix all compilation errors in the JIT compiler" - "Add TCP socket support with proper error handling" - "Refactor this function to be under 64 lines"
The AI then works autonomously: reading files, understanding context, making coordinated changes across the codebase, writing tests, updating documentation. It's pair programming where your partner has read every file and never gets tired.
*What makes the code different:*
1. *AI-friendly style guide* – We created "Grain Style" specifically for AI-assisted development: - 64-line function maximum (2^6) - 128-character line maximum (2^7) - No recursion - 2+ assertions per function - Explicit types (u32/u64 never usize) - Every comment explains "why"
The AI follows these rules more consistently than humans would. 48 of 56 kernel files are fully compliant.
3. *JIT Compiler* – Working x86_64 JIT that translates RISC-V instructions to native code. Near-native speed on x86 hosts.
4. *249 Tests* – Essential for AI-written code. The AI writes the tests too.
*Technical highlights:*
- Kernel boots on QEMU RISC-V64 with virt machine - 60+ syscalls (process, memory, IPC, network, audio, filesystem) - TCP/UDP networking with socket abstraction - Grainscript: a minimal scripting language with lexer, parser, interpreter - Process scheduler with priority queues - ELF loader supporting RISC-V64 binaries - Framebuffer graphics with dirty region tracking
*The economics:*
$200/month for Cursor Ultra. This codebase would have taken a small team several months at $15-20k+ in developer costs. We built it in weeks.
The catch: you still need to know what you're building. AI amplifies capability, it doesn't replace vision.
*Roadmap to Alpha:*
Bottleneck: Basin kernel → Vantage VM → Framework x86_64. Target application: *first-responder dispatch software*.
Contributors needed for ARM aarch64 (Apple Silicon) — Zig → C → Swift macOS app. Also designing Aurora (open-source iOS Cursor alternative) with two inference backends: - [Cursor CLI Ultra](https://cursor.com) ($200/month) - [Cerebras WSE](https://cerebras.ai) — spatial RAM, single-threaded bounded compute, deterministic latency
*Current status:*
Kernel boots, REPL works, Grainscript executes.
Built with Zig 0.15.2. Follows [Grain Style](docs/grain_style.md). MIT/Apache-2.0/BSD-3-Clause licensed.
Think of it like permaculture. You don't plant a food forest and walk away. You observe, intervene, guide. The system does the growing, but the human provides intention and correction. 170k lines of Zig didn't appear from prompts alone—they emerged from 1,390 commits of continuous dialogue between human vision and AI capability.
The "Castaneda warrior philosophy mixed with permaculture housing proposals mixed with technical specs" isn't a red flag. It's the thesis. Keaton's running for California Governor in 2026 on a platform that integrates these domains deliberately:
- TigerBeetle-based California digital currency (fiat-banked, subset of US Fed money creation)
- Job Guarantee with organic permaculture food forests
- Traditional urbanism communities
- Open-source infrastructure
The campaign vision document: docs/campaign/2026-01-15-154437-pst_the_aspiring_beauty_a_california_vision.md
The repository isn't the diamond yet—it's carbon under pressure. The diamond comes when Basin kernel boots Grainscript shell, runs first-responder dispatch software, and demonstrates that love-driven infrastructure outperforms profit-driven infrastructure.
The $20k monthly comparison wasn't marketing. It's what a team of developers would cost for equivalent scope. Whether the code is "scaffold" or "solid" is for readers to judge—249 tests pass, kernel boots on QEMU, JIT compiles RISC-V to x86_64.
But here's what matters more than infrastructure: love. The Grain Style guide opens with Castaneda because building software is a path, and paths have hearts or they don't. This one has heart.
The project's value isn't just "what Cursor's extended context window enables." It's what happens when you point that capability at something you care about for months, with discipline, with intention, with philosophy integrated into practice.
Appreciate the engagement. The code speaks for itself at codeberg.org/teamlibra/ry.