I build systems that have to answer to reality: agents that stop before they fabricate, tools that keep humans in the loop, and experiments where the edge cases are the point. Currently in Orange County, trying to get back to the Bay.
A windowed x86 desktop OS with its own TCP/IP stack. Every keyword is an Arnold Schwarzenegger quote.
ToaruOS-Arnold is about 22,000 lines of ArnoldC plus 3,400 lines of hand-written assembly: a 32-bit desktop operating system with a window manager, a terminal, five playable games, a virtual filesystem, and a TCP/IP stack that can wget a real web page over an emulated Intel E1000. Every keyword in the source is an Arnold Schwarzenegger quote. LISTEN TO ME VERY CAREFULLY declares a function. STICK AROUND is a loop. HASTA LA VISTA, BABY is on the shutdown screen. The whole thing boots from a 212,576-byte binary, and the window above is that binary, running in your browser.
A compiler for a language made of Arnold quotes, rebuilt to emit bare-metal x86 so the joke could boot.
ArnoldC is an esoteric language where every keyword is an Arnold Schwarzenegger quote. The original compiler targets the JVM, which is fine until you want to write an operating system in it. ArnoldC-Native is my Scala fork that adds three new backends: freestanding C (-native), NASM x86 assembly (-asm), and kernel packages (-kernel).
Automated theorem prover that caught its own AI cheating at math.
I wanted to see if LLMs could prove real math. Not "what's 2+2". Actual formal proofs that compile in Lean 4, a proof assistant that won't let you hand-wave. You either have a valid proof or you don't. The compiler is the judge.
One equation graph for GPU training, from the cost of a token down to the speed of light.
gpustack started in the overlap between my AI work and my physics brain. The question was simple enough to be annoying: when people say frontier training is just "more GPUs, more data, more money," where does that sentence actually bottom out? Not rhetorically. Physically.
An attempt to decipher the Indus script that has accepted exactly one claim, and zero readings.
The Indus Valley script has resisted decipherment for a century. Nobody knows what language it writes, whether signs are sounds or words, or even whether it's fully a writing system. That makes it a perfect trap: the space of plausible stories is enormous, and most "I decoded an ancient script" projects quietly work backward from the answer they wanted.
Finds curb in San Francisco you can legally park on, free, for the next N hours. Closest first.
CurbRun is a native Android app for one question: where can I park for free, legally, for the next N hours, as close as possible to here? It's a fast navigation surface, not a civic-data browser. Duration, vehicle size, candidate curbs, the reason each one is legal, and the hand-off to Google Maps all live on one screen.
PhysicsLab Your phone as a real physics instrument. 35 experiments, 9 sensors, FFT and filters written from scratch.Kotlin · Jetpack Compose · DSP · Sep 2026
Manim Director A coding-agent toolchain for math animation: Rust control plane, Manim runtime, and a real workbench.Rust · MCP · Python · Sep 2026
codex-canmore Gives a coding agent a medium layer: disposable visual surfaces it can read back as events.Rust · MCP · stdio · May 2026
Waypoint Differentiation Lab Turns a lesson map and a learner profile into classroom supports, with receipts on every recommendation.TypeScript · MCP · Vite · May 2026
Small things
BennyCuTools SaaS for local service contractors. 400 cold emails. Zero conversions. The lessons aren't dead.
claude-sfx Sound effects for the terminal. Every sound synthesized from math.sin(). Zero dependencies.
agent-rate-forecast Reads your coding-agent logs and forecasts when you'll hit the rate limit. Says 'unknown' when it should.
Pact Phones down, everyone in. A group phone-locking concept built on honest friction, not fake DRM.
Background
Ranked 5th nationally in Egypt in high school. Studied CS and physics at Minerva. Taught ML and AI to 250+ students at iD Tech across 20+ college campuses, three summers in a row. Before that, fine-tuned multilingual LLMs for a mental health chatbot at Findhope, deployed across 20+ Indian colleges in Hindi, Telugu, and Urdu, shipped to production in three months.
What I optimize for: build the thing far enough that the hard boundary shows up; make the human hand-off explicit; prefer projects with an audit trail; write READMEs as inspection guides, not trophy cases.