Skip to content
View rdegraci's full-sized avatar

Block or report rdegraci

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
rdegraci/README.md

Rodney Degracia

I'm a senior iOS engineer, and I've spent many years building and shipping production mobile apps. I work mainly in Swift and SwiftUI, and most of my attention goes to the parts that decide whether an app holds up over time: architecture, concurrency, performance, and how the pieces of the system fit together.

These days I also write code with AI tools like Cursor, Claude, and Codex. They help me move faster, but I still review every change and own the architecture, so the speed doesn't cost me maintainability or correctness on the platform. I especially enjoy writing Python this way. I use it to build developer tools, and I write up how each one works.

I've shipped enough real software to recognize the patterns that cause trouble later, and I keep learning as Apple's frameworks and AI-assisted workflows change. I enjoy mentoring and working through hard technical problems, and I like helping teams ship software they can rely on.

Site and case studies: rodneydegracia.com

Current development status: rodneydegracia.com/status-board

Projects

  • LoreBuilder CLI: A persistent world you can talk to, built as a Python CLI with RAG, Chroma, and SQLite sessions.
  • Bugmiester: A localhost trainer for spotting Swift bugs, built with Python, FastAPI, and free-text scoring.
  • Monitor: A personal AI coding agent CLI, a Python REPL with tools and task planning.
  • ultra-trace: Deterministic Swift static analysis that keeps assist and gate as separate steps.
  • Desktopper: Turns an ordinary-language request into a local schema-driven app with Python, SQLite, and Safari.
  • Maximus: An LLM harness for contest machine learning, with a person approving each training run.
  • Greenfield: A spec-first harness for building a new app one verified unit at a time.
  • super-duper: A planning and execution CLI that turns a goal into a hierarchical plan and validated workspace artifacts.
  • llm-platform: An LLM tool-calling runtime with a plugin host that works across model providers.
  • World-Sim: A local narrative simulation with split storage, grounded play modes, and a companion World Builder.

Pinned Loading

  1. monitor monitor Public

    Monitor is an AI-assisted developer CLI with an interactive REPL, built-in commands, LLM-callable tools, macros, task planning, and an optional local HTTP server.

    Python

  2. lorebuilder-cli lorebuilder-cli Public

    LoreBuilder CLI is a modular, developer-friendly command-line interface for world-building and context-rich character conversations. It integrates Retrieval-Augmented Generation (RAG) with ChromaDB…

    Python 2

  3. Desktopper Desktopper Public

    Local macOS app that builds information models from ordinary language. You describe tables and screens in Ops. An LLM returns an additive schema diff. Python validates the diff and applies it to SQ…

    Python

  4. greenfield greenfield Public

    Python CLI for a **spec-first greenfield coding harness**: LLM-assisted planning, bounded codegen, repair, and deterministic verification. Greenfield turns a project idea into structured specs, sca…

    Python

  5. llm-platform llm-platform Public

    Capability-agnostic LLM tool-calling runtime with a plugin host

    Python

  6. ultra-trace ultra-trace Public

    Ultra-Trace is a Python-based CLI tool intended to analyze Swift repositories, find risky code patterns, and generate structured reports

    Python