Universe Screen
A spatial interface for seeing active projects, files, and AI agents as a living solar system.
A living index of built, researched, tested, shipped, paused, and learned-from work across software, science, hardware, civic life, and business.
Catalog: JW-COMP-001
Rev: 0.6
A spatial interface for seeing active projects, files, and AI agents as a living solar system.
A provenance-first civic intelligence workspace for local decisions, infrastructure, and public records.
An open research workflow for prioritizing uncertain variants in familial hypercholesterolemia genes.
An offline iOS ingredient scanner for identifying terms associated with glutamate.
A model-rocketry program spanning custom airframes, launch hardware, sensors, simulation, and flight data.
A small iOS utility that turns end-of-shift register counting into exact instructions.
A macOS workspace for talking to multiple AI providers with shared, live-updating context.
An open civic infrastructure database and field atlas for public water-storage landmarks.
A deterministic-first methodology for carrying raw genetic data as far as reliable evidence allows before expert interpretation.
A reproducible public-data analysis for finding candidate places where roads and wildlife movement may collide.
A human-owned, agent-readable knowledge system that makes long-running AI collaboration more coherent without surrendering control of the record.
A manifest-first workbench for running genomic evidence tools through explicit, reusable contracts.
A public-interest study of how a fragmented nationwide search system could become more reliable, legible, and technically modern.
An early Pomodoro-style iOS app built before coding agents became part of the workflow.
A local telemetry dashboard for understanding the token and monetary cost of persistent AI-agent work.
A permanent, transferable record for a house, maintained with low-friction AI assistance.
Open-source infrastructure for a shared, typed, versioned map of educational knowledge and capability, beginning with mathematics.
A local-first iPad mathematics prototype built around deterministic practice and inspectable mastery evidence.
An Apple Music-oriented listening interface that filters unwanted album artwork while preserving the music workflow.
A portable capability layer that gives different coding agents the same documented, repeatable tools.
An agent-led challenge concept for making the invisible household burden of illness easier to document and compare with public evidence.
A portable, local-first annotation format for user-controlled mute, skip, and visibility decisions in media.
A macOS pedometer for the person who walks around carrying a laptop while AI agents do the typing.
A grounded LLM wiki for fictional worlds, using layered truth to separate canon, interpretation, adaptation, campaign, and private invention.
A private game server for friends whose setup and debugging are increasingly delegated to an AI coding agent.
Experiments with persistent personal agents that clarified when continuous autonomy is useful—and when a steadier coding environment is better.
An idea-stage address-safety research tool that assembles public context without pretending to predict personal safety.
A small iOS experiment that turns a receipt into a deliberately theatrical roast of the purchase.
A browser-extension experiment for distinguishing subtle promotional influence from ordinary page content.
A family of experiments that let AI agents see, touch, navigate, and manipulate interfaces beyond a text-only shell.
A small app experiment used to study how easy cloning has changed the economics of consumer software.
A local WebRTC bridge that lets a Mac-based agent use an iPhone as a user-controlled camera.
A recursive knowledge graph and reasoning workbench for tracing how industries, firms, resources, and constraints connect.
A playful iOS experiment that presents a home's estimated value as if it were a live market ticker.
An evidence-driven BLE toolkit for understanding and eventually controlling a personally owned Wyze Band.
An abandoned project-idea feed whose failure led to a better question: can agents find grounded problems worth solving?
A concept for interviewing a business owner and turning operational context into a concrete AI implementation guide.
An intergenerational crowdfunding and mentorship network that exposed the cold-start cost of trust-based marketplaces.
A working video-to-agent utility, first archived as a product and now rebuilt as a smaller public Lab experiment.
An early meal-prep and inventory app that shipped too soon and became a lesson in domain depth and product restraint.
A concept architecture for a continuous agent organization, developed before Josiah encountered OpenClaw or similar harnesses.
A field-companion concept for planning rockets, launch sites, weather, checklists, compliance, and flight logs.
A privacy-preserving concept for asking nearby, citizen-owned cameras about a specific public event without opening a general surveillance feed.
A paused propulsion concept that documents an ambitious fabrication path without claiming a completed or working motor.
A local app that offers men one small, concrete daily action for showing love to their families.
A reproducible computational search that records no three-hit incongruent restricted disjoint covering system below interval length 108.
A facility-level map of the twenty industrial handoffs between rare-earth ore and a customer-qualified high-performance magnet.
A native macOS launcher that turns a cinematic desktop into a functional video-game-style main menu.
An explicitly AI-generated and unverified mechanistic-interpretability experiment on emotion-related representations in two small language models.
A four-phase research program testing whether exact deterministic computation can live inside a language model's forward path.
No records match those filters.