
A classroom AI notebook for elementary science. Students collect AI-made explanations, images and videos on a board, then record evidence and their own explanation. The teacher controls daily spend.

A classroom AI notebook for elementary science. Students collect AI-made explanations, images and videos on a board, then record evidence and their own explanation. The teacher controls daily spend.

Turns a constrained language instruction into a physical pushing task in MuJoCo. Across 24 runs, I compared a single planned push with repeated observation and replanning, including success, time, and failure records.
A Korean travel merge game developed with AI-assisted code, image generation and iterative testing. Merge items, fulfill orders and explore a growing village in a playable phone frame.
Turn Korean craft and travel into a merge game, then iterate on AI-assisted implementation through real browser interactions and automated checks.
A web prototype in a phone frame; gameplay does not call a live AI model. The iOS project is prepared, but real-device testing, Xcode compilation and App Store release are not complete.

Compare predictions of clicks, conversions, engagement and repeat purchases across 10 real public datasets, 12 tasks and 4 methods, with bilingual explanations of the process, expectations, results and scores.
Distinguish changes in model scores from live service improvements by comparing prediction methods on the same test records.
Offline predictive evaluation on public data. Live click, purchase and revenue gains, and causal effects, remain untested. No real ROAS measurement with linked revenue and ad spend.

An MLOps lab for validating LLM changes and preparing release candidates. It exercises the real HTTP gateway under injected faults and blocks quality regressions and artifact tampering before packaging.

Tracks people and line crossings. Three new clips cover perspective, occlusion and reappearance, comparing four detectors and three tracker settings. Synchronized videos, 63 runs and a missed-crossing case are published.

Integrated public vision models with evaluation and visualization across 18 technology pages. The lab presents recorded results and errors in object relations, motion comparison, simulated control, tracking, pose estimation, motion capture, and anomaly detection, while distinguishing executed stages from stages awaiting model release, access, or required files.

360° VR space experiences built from NASA 3D models, satellite maps and original photos: Voyager 1's Pale Blue Dot, the ISS interior and night over Korea, an Artemis I ride from the launch pad to the lunar far side seen through the capsule windows, Earth's rotation and revolution with Moon phases and seasonal constellations, a tour of the Sun and the eight planets, the story from the Big Bang to Earth's first oceans, and a cosmic calendar that squeezes 13.8 billion years into one year, as browser previews and 4K 360 videos.
AI video generators struggle with seamless equirectangular 360° footage and consistent scale. Scenes are generated in Python and rendered with a Blender panoramic camera; AI is used where it is strong, such as narration.
Distances and sizes are compressed for the experience, and some glows are artistic. The seasonal scenery, constellation art, cabin, Sun artwork and Mercury map are AI-generated images. ESA interior photos are used non-commercially with credit.
A PC cleaner in which Chiikawa and friends each look after a room of the house, find the caches, temp files and old downloads piling up, and always ask before tidying anything. Built for Windows and macOS in a Korean edition and a global edition (handwritten Japanese speech bubbles with an English UI). An unofficial personal fan project.
Cleanup tools are hard to read and a little scary. Here each character shows what has piled up in its room and how much, and only tidies what the user agrees to.
Chiikawa characters belong to nagano (©nagano / chiikawa committee). As an unlicensed personal fan project, the source code and installers are not published or distributed; only a screen recording of the demo mode, which runs on made-up data, is shown here.

A 3D tour of Sydney Opera House, Seoul Arts Center and the National Gugak Center. Explore exteriors and interiors, open doors, walk through connected spaces, and control viewpoints, lighting and audience animation.
Photo-informed venue reconstructions become repeatable spaces for exploration and staging. Seats, props and doors remain individually editable in Blender; the web viewer merges and instances static geometry for display.
A visual reconstruction based on photographs and public references. Some dimensions and connections are inferred without surveyed drawings; it is not an exact digital twin of every facility.

A 3D browser racing game set in Manhattan- and Gwanghwamun-inspired cities at sunset. Choose from 15 vehicle configurations and six courses to race four AI rivals or enjoy free driving.
I wanted a game people could open in a browser and immediately enjoy driving through a city at sunset. As vehicle and street detail increased, I refined the rendering workload, handling, and race adjudication together.
This page publishes the project overview and actual screenshots; the playable demo is not public yet. The cities are game interpretations rather than surveyed or scanned reconstructions. Physics uses an arcade approximation and does not reproduce manufacturer performance. Frame rate varies by device and browser, with occasional delays remaining. Vehicles include third-party 3D models. The cover screenshot uses aarajesh’s Tesla Model 3 under CC BY 4.0, adapted with game placement and materials.

A 3D assembly drawing that builds a Boeing 737-8 in eight stages, from the bare airframe to the engines. Pick assemblies from a numbered exploded view and parts list, then explore a 154-seat cabin remodelled from researched references, the cockpit and LEAP-1B engines, and operate window shades, tray tables and wing controls.
Starting from a supplied aircraft model, I corrected window-to-skin alignment and door/bin rigging, then extended the static geometry into a web experience for exploring internal structures and mechanisms.
This is a visual reconstruction fitted to public specifications and the supplied model. The seats are modelled from references, not manufacturer CAD or licensed replicas. The build order is an illustrative arrangement in which no part passes through one already installed, not the sequence of a real assembly line. Internal sections, linkage dimensions and motion paths without manufacturer CAD are illustrative; animation timing serves inspection. It is not a complete aircraft-parts or flight-procedure simulator.

A task-specific AI tuning design tool for policy-adherence failures, ticket misrouting, missing document fields and content-review errors. Connect data, target outputs and evaluation criteria, then share recipes and test plans.
Changing tone alone is not a strong reason to fine-tune. The product starts with recurring business errors and distinguishes problems to address with prompting, retrieval or structured outputs from those worth evaluating with training.
The public build is a frontend product demo. Responses and dial indicators are rule-based examples; APIs, file analysis, training and customer deployment are not connected. Invented improvement figures were removed. Evaluation criteria are unexecuted plans, and provider training support and account access require separate verification.

A 3D anatomy explorer with system separation, search, and original-model export.

RAG used on the personal PC of a professor treating breast cancer at Anam Hospital. Installed in October 2025 with ongoing remote updates; public evaluation and tuning use separate synthetic data.
A LangGraph multi-agent reference with rewrite loops and offline structural verification.
The skeleton of a multi-agent system — orchestration, memory, evaluation — should be verifiable independently of model quality. A minimal-complete reference that generalizes the 'verifiable agent' principles learned shipping med-rag.
Offline mocks verify wiring, not model quality or improvement on every run.

A personal AI workspace with model routing, tool approvals, usage records, and Docker self-hosting.
A four-person team project for a location-aware AI guide. As PM, I handled product planning, priorities, scheduling and role allocation, and worked on the place-data pipeline and promotional video.
A personal team project planning a location-aware AI guide around the places visitors explore and the context of their trip.
This page presents the promotional video I created and my responsibilities in the team project.

An internal meeting assistant currently running on RTX 4090. The public interface is a sample-data demo.

63 dependency-free demos reproducing well-known interface designs in code — one file each, live preview beside its source, bilingual down to the text inside every demo.
A design reference you can only look at in a screenshot is dead. I wanted a living one — open it, poke at it, copy it straight into your own project.
With no build step there is no component reuse between demos, and curation cost grows with the collection.

Upload a document and Claude turns it into a deck through Structured Outputs, then it exports genuinely editable PPTX — vector text and shapes, not image snapshots.
Rebuilding slide design from scratch for every presentation is wasted work. Encode real brands' design systems as tokens, and one click restyles a whole deck.
The static demo has no API key, so AI generation is disabled there (editing, theming and export all work). Complex PPTX imports lose some fidelity.

An emotional-support app for iOS, Android, and web. Independently planned, designed, and developed, with a working browser emulator.
My first end-to-end app began with a simple idea: a companion that listens without judgment on difficult nights.
Not yet released to app stores. Server-dependent features, including AI conversations, are limited in the demo.

A post-breakup support app with a calming timer, a 90-day recovery journey, and simulated AI conversations. Available as a working browser emulator.
Impulsive contact after a breakup can lead to regret. I built a tool that helps users pause at that moment.
Not yet released. Contact protection is an in-app intervention, not an operating-system block. AI responses in the emulator are demo responses.

Themed walking routes in Seoul, with a character preview that follows pedestrian paths on a 3D map.
A walk involves personal preferences as well as directions. Users choose a theme and time, receive a suggested route, and preview the walk before setting out.
Currently limited to eight routes in Seoul. Live GPS tracking during a walk is not implemented.

A restaurant-management demo connecting orders, reservations, CRM, and AI analytics.
Restaurant owners juggle separate tools for orders, reservations, customers and payroll. TableON puts them in one subscription with an AI business analyst on top.
The demo resets on refresh; real payments/SMS need integration keys.

A web app that gathers diary entries into a book, with Google sign-in and guest access.
I wanted scattered daily records to become a coherent collection, with the tangible feeling of a book.
PDF or physical-print export, search, and tags are not yet implemented.

A local production tool connecting scripts, work orders, generation, and assembly.
Every short drama, explainer or ad meant writing prompts from scratch again. Encode the structure once as a work order, and the medium and template become parameters instead of a rewrite.
Generation needs an authenticated external API with credits, so this one is not publicly deployed. It runs locally against a queue runner.

Transaction prices on a live map, neighbourhood search by local nickname, and a financing engine that turns cash + salary into an LTV/DSR loan ceiling, acquisition tax and the cash you actually need — plus redevelopment news signals and regulation monitoring.
Looking for a flat meant checking transaction prices, neighbourhood reputation, loan limits, tax and regulation on five different sites. This puts them on one map and answers the question that actually matters: can I buy here with what I have?
The transaction API returns no coordinates, so map markers are approximate per complex. News signals are a keyword-based reference, not investment advice, and regulation data is point-in-time. On serverless the geocoding cache lives only in instance memory.

A learning portal that rewrites itself every morning — three concepts, AI news and papers — then holds on to them with quizzes, mind maps and a review queue built from the questions you got wrong. No backend, no external API.
Deciding what to study was eating the time meant for studying. I wanted something that picks the day's material for me and then makes sure I do not lose it a week later.
Progress lives only in browser localStorage, so it does not follow you across devices, and the refresh depends on my machine being awake.

Pick any date between year 1 and 9999 and the planets move to where they actually were, computed from J2000 elements. Then fly it from a cockpit, or watch 13.8 billion years replay as a cinema.
Astronomy simulators tend to be either accurate and inert, or beautiful and empty. I wanted real orbital computation you are allowed to fly through.
Sizes and distances are exaggerated for legibility (at true scale the screen is empty), and the circular-orbit approximation drifts a few degrees from a real ephemeris.

Character-led AI saju readings with traditional calendar calculations, true-solar-time correction, fortune cycles, and symbolic influences, tailored to the user's questions.
I wanted to move beyond generic birth-date readings by incorporating seasonal solar terms, birth time, and birthplace into the traditional saju calculations.
The demo has no real payments, and reviews are samples. A live-service mode requires payment integration.
A legal PDF chatbot with document retrieval and evidence citations.
Public code documents a learning and product experiment.
A content automation experiment connecting generation and publishing modules.
Some scheduler publishing calls are not connected. Fully unattended operation is not established.
No matching projects. Try another name or technology.