Opening Up
How We Make Things.

A free Blender add-on that turns any 3D model into sparkly, painterly 2.5D. It breaks the surface into tiny glossy facets that catch pink, cyan, violet and gold light, paints over them in brush strokes, and puts star glints on the brightest spots, for a hand-painted look that glitters like crushed diamond. Pick from 10 backgrounds and 4 styles (Kira, Soft Paint, Bold Ink and Dreamy), and use the 2.5D slider to turn a realistic render into a painting. It works on downloaded, scanned and AI-generated models alike, and it never replaces your materials, so you can always undo it. Just ask an AI agent such as Claude Code or Codex, and it installs and applies the add-on for you.

A free Blender add-on that turns your 3D models into cute comic-style toon art. Shadows take a colour from the palette instead of grey, hearts and stars are scattered where the light hits, and hatching, rim light and outlines are layered on top for the look of a printed manga. Highlights come in six shapes (dots, hearts, stars, little flowers, sparkles and moons) and there are 13 palettes. It works on characters, props, logos and backgrounds alike. Just ask an AI agent such as Claude Code or Codex, and it installs and applies the add-on for you; then fine-tune it in words while you watch the preview: “fewer hearts”, “make the edges glow”.

A free library of hand-drawn, anime-style (sakuga) game effects: 90 effects across nine elements, including fire, water, thunder, wind and poison, as transparent flipbook sprite sheets. It comes with a Unity 6 (URP) package, a Godot 4 addon and a 4 KB web player with PixiJS, Phaser 3 and Three.js examples, so the effects play in any engine as they are. Recipes chain the charge, the projectile and the impact, so a whole skill effect takes one call. It is made for students, solo developers and small studios with no budget for a VFX artist. The effects are free, commercial use included, for anyone under USD 1M in annual revenue, with a credit; the code is MIT.

A Godot 4 plugin that turns the 2D pixel-art tile maps you already have into a 3D diorama. Houses fold up from their front walls and get their roofs, trees stand up out of the ground, ponds fill with water, and your sprites stand up as cards. Nothing is modelled by hand and no AI generates anything: the geometry is built from the pixels of your tiles. The 2D map and the 3D model are the same mesh, so the switch has no jump and works in the middle of a game. 3D-only touches include wind, cloud shadows, lit windows at night, snow and smoke, butterflies and fireflies, and it looks the same on the Compatibility renderer for the web.

A reference implementation of real-time, two-way coupling between a GPU shallow-water solver (Kurganov–Petrova 2007) and an erodible sand heightfield. Each sand cell carries its own wetness and strength, so a wet, packed wall stands against the surf while a dry, loose pile slumps and washes away — all from unscripted physics. Sixteen Godot 4.7 compute shaders, about 3 ms of GPU time per frame on an RTX 3060.

A real-time water renderer for the browser. It aims for a photographic look above the water, under it, and in the half-submerged “over-under” shot: an FFT ocean, light absorbed and scattered in the water, caustics rippling across the seabed, light shafts, and Snell’s window when you look up from below. A waterline that follows every wave exactly sweeps across the lens, and after the camera surfaces, a water film and drops run down the glass. Built on three.js WebGPURenderer and hand-written WGSL, with no game engine or plugins, it takes about 7 ms per 1080p frame on a laptop RTX 4070 and runs in desktop Chrome.

A WebGPU denoiser that lets path tracing run in real time in the browser. It turns a noisy frame of one sample per pixel into a clean, flicker-free image. A tiny neural network of just 812 parameters (1.6 KB) predicts how to filter each pixel rather than the pixel colours themselves, so it never paints in detail that is not there. Denoising takes about 2.2 ms per 1080p frame on an RTX 3060, more than twice as fast as the standard SVGF method, and a small path tracer for three.js WebGPURenderer comes with it.

Fully offline voice dictation for the Mac. Hold a key, speak, let go, and the text appears wherever your cursor is. It recognizes 30 languages and 22 Chinese dialects and is tuned for Japanese, English and Chinese, including all three mixed in one sentence, with no modes to switch. Recognition runs on Qwen3-ASR entirely on Apple Silicon, so your voice never leaves the machine. Turn on the optional Polish step and it adds punctuation, drops filler words like “um” and, when you correct yourself, keeps only the correction. A free menu bar app, ready to install from a DMG signed and notarized by Apple.

A local QA tool for generative audio. Built on Google’s multilingual EmbeddingGemma 2, which places text, sound, images and video in one shared space, it checks whether a clip matches its prompt, ranks your takes, runs technical QC on loudness, clipping and loop seams, judges how a sound fits the picture, and searches your own library. Use it from the CLI, a browser workbench or an MCP server.

Gives Claude Code, Cursor and any other MCP client a sound studio that runs on your own Mac or Windows PC. Ask in plain language and Stable Audio 3 generates the music or sound effect locally, then loops it seamlessly, sets the loudness (LUFS) and exports it for your game engine or video editor. No cloud, no API key, and nothing to pay per generation.

Japanese subtitles with natural line breaks, from any video or audio file. Without a script, it transcribes the speech with punctuation (Qwen3-ASR); with one, it aligns the script to the audio character by character. Lines break between Japanese phrases, never start with 、 or 。, and never split a number from its unit. It can add furigana, has presets for YouTube, vertical shorts and Netflix Japanese style, and can re-break subtitles made in Vrew, CapCut, Premiere and other tools. Everything runs on your Mac, so your video is never uploaded. Use it from a web UI, the CLI or an MCP server.

Local AI image and video search for artists and filmmakers. Type “torii gate in the snow” and it finds that picture by what is in it, not by file name or tags. Search in Japanese, English or Chinese, show it an example image, or combine the two to narrow things down. Videos are searched shot by shot and play from the matching cut, and real production folders work as they are: RAW, PSD, EXR / HDR and more. Google’s EmbeddingGemma 2 runs entirely on your Mac, so nothing is uploaded. Use it from a web app, the CLI or an MCP server.