Keep
Password strength meter with a pixel scene inside the control. Open source.
Weird, visual, playful software: simulators, clocks, campaigns, experiments that are more art than SaaS. 174 builds on this page, each with the original post.
Password strength meter with a pixel scene inside the control. Open source.
Open source Blender extension from PlayCanvas. Paste a SuperSplat URL and the splat shows up in the viewport.
A voxel destruction engine from one Fable 5.2 prompt. Playable in the browser.
Browser engine that renders small 3D dioramas as pixel art, with time of day, weather, and sound. Made with Opus 5.5.
A bottle studio in the browser. Glass and light in one HTML file. Built with Opus 5.5. Open source.
Browser editor that zooms a screen recording where you click and type, then exports an MP4. Built with Opus 5.5. Open source.
Local film studio on ComfyUI. Write, direct, generate picture and sound, then edit. Open source.
Middle-click value scrubbing for Cinema 4D. Open source.
Learns a brand, makes ads from what is already winning, and launches them.
Splits a song into vocals, drums, bass, and chords, and writes the MIDI. Runs on a Mac. Open source.
YouTube picked from videos Hacker News keeps recommending. No login. Thumbnails are a frame from the middle of the video.
Native Android TV app for HackerTube. Pick a video and it plays on YouTube on the TV. Built with Opus 5.5.
AI radio that talks about your calendar between songs. Self-hosted, with a site to try it.
Claude skill for visual builds that have to match your reference images. Open source.
Pixel effects written as code, with a skill that renders a clip and fixes the frames. Open source.
Learn a harmony part, record every voice yourself, and stack them in the browser. Open source.
Turns an AI video into a skeletal animation on your own rig. ComfyUI nodes. Open source.
Blender add-on that drafts, sews, and simulates a shirt. Open source.
Native Windows player for YouTube Music, with a mini player. Open source.
Mac desk of tasks drawn as daruma dolls. An eye fills in when you finish one. Built with Opus 5.5.
Open source AI film studio on Comfy. Storyboards, restyle, and character boards, local or in the cloud.
Browser editor for short videos, with scripting and discovery. Open source.
Makes an image or video look like it is playing on a 1980s TV. Simulates the analog signal, a VCR, and the tube. Open source.
A 4 km by 4 km voxel world in the browser. Lighting is baked on the GPU and cached on the machine. Three.js and WebGPU.
Three.js tour of a chip fab. One speck of dust kills the wafer. Made with Opus 5.5.
One Blender tab for image, video, 3D, audio, and texture models. Open source.
Pixel-art normal maps, as a CLI and a wasm library. Open source.
A live 3D model of the solar system, with planets on their real orbits. Built with Opus 5.5.
A gallery that explodes everyday objects so you can read what each part does.
An open source director agent. A sentence or some notes go in, and a narrated explainer video comes out.
A native Mac video editor with an AI color grade for DJI D-Log M footage, and an MCP server so an agent can edit too.
An open source Blender plugin that puts a 3D team in the editor: concept, model, rig, materials, cameras. Claude Code can run it through MCP.
Pronunciation practice that roasts you and flirts with you, in Chinese, Japanese, Spanish, and Korean. Voices from Fish Audio Drama 3.
Talking-cat toy on Sarvam Bulbul V4 Flash. Chat, repeat after it, or throw a tongue twister. 83 voices, 11 languages.
Open-source workbench for CAD made with agents. Versions per chat, tools per project, files ready to print at home.
Camera controls for generated images and video. The studio behind a WorldLabs clip, now open source.
Walk the Silo. Cafeteria, farms, stairs, living quarters, mechanical. An interactive 3D set.
Draw a selection box and let go. A doodle pops in with a note. 26 of them to find.
The obelisk in Sultanahmet, readable. One HTML file, Three.js, Opus 5.5.
A whole university campus, walkable in the browser. Three.js.
FFT ocean, moving clouds, reflections and caustics, plus a Gaussian splat mode. CUDA kernels compile to WGSL and run on WebGPU.
Ten isometric objects. Change the light and the theme color. Each object does something different when you touch it.
A Grok Bot lays out a personal newspaper overnight. Printable edition you can run yourself, plus the pen-plotter version Karen uses.
One monolith splits into 32,000 shards, then reforms as a cathedral and a whale. Opus 5.5 and Three.js. Public repo.
Words held in a vacuum by thousands of threads. Drag them, strum them, they glow and snap. Live WebGL, one conversation with Opus 5.5.
Open-source film style library for Opus 5.5. 39 styles, director guide, deterministic Canvas and WebGL frames. MIT.
Photographic shallow water in one HTML file. WebGL2 waves, refraction, caustics. The X video is a real-time capture.
Japanese garden sandbox in the browser. Rake sand, set stones, waterfall, lanterns. Four styles and seasons.
Node Canvas character rig, frame checks, and FFmpeg. The ant colony film has matching source.
Code-drawn paper-lightbox frames plus a spoken-word track. Matching project for the Shaml scene.
Applies Lightroom presets without opening Lightroom. Fast, uses the presets you already have.
Build a platformer level in the browser, hit publish, and it becomes part of the world everyone else walks through. No download.
Illustrate and animate with deterministic code. Hand-drawn styles, storytelling, and music wired in.
Draw a flower, write a note, plant it in a shared garden. No accounts. No feeds.
Map an e-drum kit onto Ableton's stock kits so the pads hit the right sounds. Efnote first. Point an agent at the repo for other kits.
New tab becomes a gallery wall. 106 public-domain paintings, custom frames, works offline.
Free open-source Photoshop-like compositor for Mac. 12MB. Layers, masks, healing, clone stamp. Built to drop Adobe.
Build a Lego set out of anything and leave it on the internet.
Playable Three.js and WebGPU sandboard. Multitouch on mobile. First-party, source on GitHub.
Ten original loopable cozy fantasy tracks for RPGs. Royalty-free on itch.
Disk caching and chunked long video generations so Comfy-style LongVideo nodes stop OOMing.
302-neuron C. elegans wiring trades simulated SOL. Silence a neuron and replay the market.
Open-source charting engine with MediaPipe hand tracking. Pinch to zoom, swipe to pan, all in the camera.
Native macOS app to run YuE2 open-source music generation on Apple Silicon with MLX.
Browser sound-effects tool for game developers. FM synthesis, layers, export WAV. Playable on itch.
Timelapses from 3D-printer slicer G-code. Filament, plate, lighting, and camera are yours to set. Files stay on device.
Interactive fold study. Scrub black screen vs frosted glass, slow the motion, watch blur and snap. Playable.
Two Astra prompts, a reference video, and a product page. Playable React fold demo.
Sunset to nightfall to moonrise to Milky Way, all JS, no images. First-party Astra build.
Open-source ComfyUI nodes and workflows for Reactor endpoints, including MiniMax FastH3.
HeyGen open-sourced real-time AI avatar demos with OpenAI GPT-Live-1, LiveAvatar, and HyperFrames.
GPT Astra / Claude skill that locks one face, voice, and light across many videos.
Viewer-requested 3D assets made live on stream. Random collection, free on itch.
Interactive 3D character for Everdraw RPG Pathfinders guild. Playable in the browser.
Turns a favorite song into a custom blind-box toy. Built with Reve. Playable.
Cut photos into holographic die-cut stickers in the browser. One Fable 5.1 prompt. First-party, client-side only.
Disk storage visualizer in the Jurassic Park control-room style. Playable WASM, first-party from Makepad.
A parametric card design tool, plus shaders and orbs. First-party from a Stripe design manager.
SwiftUI shader experiments, same drop as Murmur. First-party, with a demo.
Interactive 3D QR codes as a React package. Themes, logos, transparent backgrounds, and a live editor.
YMM4 plugin that draws cut-out magazine lettering, one glyph at a time. First-party, with a sample.
A kilogram of iron and a kilogram of cotton look nothing alike. 3D volumes for mass, instead of a number.
Ask Codex or Claude Code to add VRM facial expressions. First-party, with a demo of the avatar moving.
Hundreds of thousands of particles self-organize. Mutate them, pick the ones you like, share permalinks. Built for a desktop GPU.
Inception-style WebGL carousel. Three.js, GLSL, and a render target that looks back into itself.
A free Blender extension that paints geometry onto surfaces. First-party, with a demo.
Claude Code plugin for generative art. Determinism from a hash, same piece at 400px and 4000px, rarity checks before minting.
Generative art where the model writes JavaScript in an isolated worker instead of getting a tool per shape.
Speaks numbers and processes, draws charts and diagrams while you talk. Local Whisper. Cannot invent a number you did not say.
Frustrating Three.js Plinko and pinball demo, plus Blender-to-Three.js workflow notes for the Three.js conference.
Spy-simulator in the browser on real data: planes, ships, satellites, traffic cameras. Talk to the planet. MIT.
Driver for a TM-20 thermal printer so ChatGPT can spit out whatever art it wants onto paper.
Chrome extension that diffuses the page as you scroll, type, click, and navigate. Motion-sickness warning included.
Native macOS screen recorder the author built after two years of stitching Screen Studio and CapCut together.
Chrome extension for football scouts: clip a match from the browser, tag by player and action, export highlight reels.
Agent skill that turns any video into a scroll-controlled website.
Copy-paste prompt factory that turns a Doodles OG into a physical-toy render.
Apple-native motion canvas for iOS and macOS. Export liquid-glass interactions in 4K.
Open-sourced Three.js prototypes: FFT ocean, procedural grass and trees, particle fluids, tectonic planets.
Open-sourced 3D scroll-driven landing page. Whole codebase under 1 MB, so it actually loads instantly.
Make your own image grids. A polyptych tool after the site carousel got worse.
Webcam emulator inside a spreadsheet, built in Google AI Studio on Gemini 3.7 Flash. Export images and CSVs.
Free Aseprite extensions, including a normal-map generator that reads layer groups instead of a height map.
Text-swirling and other SwiftUI animations. Code in the public repo.
Aseprite extension that builds normals from layer-group arrangement instead of a height map.
GLM-5.3 built this site after four hours. Live demo plus full repo to fork.
Jigsaw of hand-drawn Icons art. 58 pieces, easy/hard, optional 4×4.
Anti-AI grid-noise animator. Playable in the browser.
Steal the design: code and assets open-sourced.
Paint a mask, export hidden-picture images for X. 100% in the browser.
Open-source motion-graphics framework and skills from HeyGen.
Terminal-style site with the trophy and top player in ASCII.
Svelte animation playground. The post that pulled 3k likes; a whole suite of live demos.
Generative art from math-class doodles, in JavaScript. Live demo plus repo.
Digital archive of the books people grew up reading in Nigeria: Ige Adubi, Ralia the Sugar Girl, Eze Goes to School. Built with Claude Code.
GLSL fireworks after missing the real festival. Live project page.
Independence Day site telling India's story through the web. Eight days of work.
Cinematic one-page site for Arsenal's first trophy of the season. Gemini 3.7 Flash plus Seedance.
AI Studio app: type a sound, generate Omni Flash video, slice isolated SFX. Built because Google has no SFX model.
Interactive Three.js, GLSL and Web Audio piece from reference images. Gemini 3.7 Flash on Antigravity.
Silly isekai generator. Gemini 3.7 Flash built the baka-game people had been imagining.
Game of Thrones lore site: characters, houses, dragons, battles, map and timeline. Made with Kimi K3.
Kimi K3 site with 3D, generated assets and UI in a couple of hours. Live plus source.
Make a Grok Bot-style mascot and export it as SVG animations. Playable in the browser.
Gallery of mid-century annual-report design, starting with General Dynamics 1967–1977.
Write whatever is on your mind, then burn it. No accounts, no setup. A quiet space to get thoughts out of your head.
Experimental three.js record-label landing page, built with Claude Code and fully open-sourced.
Git submodule of the ASCII art animations from Pauline Vos's Laracon US talk. Open to animation requests.
Color picker you flip through like a record bin. Three.js, no image assets, palettes from the rack only.
Interactive graph of what to watch before Avengers: Doomsday. Built against the Disney+ list.
An interactive, sound-on experience of what it took for India to get independence. Built and open-sourced for 15 August.
Splits any AI-generated image into editable layers for subject, text, logo and background, so each piece can be restyled independently.
Independence Day site walking through 80 years of India’s science and technology milestones.
The Braun BC02 alarm clock rebuilt as a fully interactive web app with Claude Code.
Hang a lucky charm on your Mac. Small, playful desktop toy with extra interactions, more charms coming.
Free Framer portfolio template for designers. Bold type, editorial layout, CMS projects, remixable.
3D interactive explorer of 8 historical empires. Explore daily life, homes, maps and interiors. Near one-shot vibe-coded with Kimi K3 + Three.js.
Turns any real place on Earth into an accurate 3D world automatically from open map data, in the browser, in minutes.
Figma plugin for UI motion: select, pick hover/press/enter/exit/loop, customize, apply. Live on Figma Community.
Take a photo with someone and the app instantly adds a branded frame with their name and contact info, so the photo becomes the business card.
Upload your photo and measurements to see exactly how clothes will look and fit on your body.
Sends files between phones with no WiFi, Bluetooth or network. QR codes flash on one screen into the other camera at 129KB/s. Built in one night with Claude Code.
SpaceX Falcon 9 launch, stage separation, boostback and landing simulation one-shotted in Three.js with Claude inside Claude Code.
Web font explorer that browses type by feel and property, not just a name dump.
Vibe-coded tool that redesigns your room using real furniture you can actually buy, with a full shopping list.
Complete official ByteDance Seedance 2.5 prompt guide turned into a ready-to-use Claude skill with 67 templates.
3D fluid particle sim on a Waveshare ESP32-S3 AMOLED. Tilt the device, the liquid moves. Opus 5 wrote the C renderer. Repo is public.
Azure's CTO made Doom playable inside Microsoft Paint at 35fps by pasting frames through the Windows clipboard. Ctrl+Z rewinds time.
Browser game that generates a drivable 3D world in real time from OpenStreetMap and elevation data. Drive any road on the planet, race friends multiplayer.
Turns the song you're currently listening to into a beautiful animated vinyl wallpaper for Mac.
Full web-based video editor (Premiere/Final Cut style) that can generate videos with your trained likeness models directly inside the timeline.
Upcoming open-source engine-independent framework for procedural generation, animation, rigging, concept art, 3D modeling and generative level design.
Vibe-coded tool that transfers files from computer to phone using only the camera (completely air-gapped).
Open-source tool that turns any phone video into a full walkable 3D world in real time, running 100% locally.
Browser game that gives you 30 seconds to draw a country's outline from memory and scores your accuracy.
Custom desktop applications for high-quality motion previs, planned to be open-sourced.
Design+Code founder open-sources 75 agent skills for web design, landing pages, motion, WebGL and UI, including Video to Super Prompt.
Open-source starter kit + UI component library + AI skills for building micro-apps for designers.
Pressure-free mini-vlog app specifically designed for shy and introverted creators.
Open-sourced the password meter from this post. Repo, live demo, and the skill: Live: pixel-worlds.vercel.app/keep/ Repo: github.com/finktheartist/… MIT. Go make boring UI fun
Password strength indicator. Made with Fable 5.2
Looking for 3D Gaussian splat content for Blender? Install the open source SuperSplat Blender Extension from @playcanvas. 🔍 Search downloadable splats on SuperSplat 📋 Copy/paste the URL to Blender 🪄 Splat appears in Blender's viewport github.com/playcanvas/sup…
The Blender Foundation and the online community proudly present Blender 5.3 🎉 This release wraps up 2026 with new features and improvements across the board. Highlights include: 🔸 Native support for 3D Gaussian splats. 🔸 A new DLSS denoiser in the Viewport on NVIDIA GPUs.
Fable 5.2 built this voxel engine from a single prompt. Try it (sound on), it’s mind-melting: spawn.co/@mattshumer/vo…
Fable 5.2 is the best model ever created. The things I created with it are mind-blowing. It’s also basically a school hall monitor. Here’s my review (with demos): somethingbig.ai/fable-5-2-revi…
the pixel engine is open source now. little 3D dioramas rendered as pixel art in the browser, with time of day, weather and sound. made with opus 5.5 github.com/danieljan-desi… x.com/danjan_design/…
alpenglow - pixel engine made with opus 5.5
Opus 5.5 is great in 3D & art direction I built this premium bottle design rendered in the browser - all in three.js Open source, one HTML file: Live: amirmushichge.github.io/bottle-studio/ Code: github.com/amirmushichge/…
I built Open Cinema Studio: a local, open-weights film studio on ComfyUI. Write, direct, generate video + sound, and edit. MIT code + 26 workflows. Demo: github.com/afj176/open-ci… Repo: github.com/afj176/open-ci… #OpenSourceHiggsfield
🚀 Introducing ValueLadder for Cinema 4D! Houdini-style value scrubbing, now in C4D! 🖱️ Middle-click & drag 🎯 Precise step control ✅ C4D 2026/2027 (Windows) ❤️ FREE & Open Source! 🔗 GitHub: github.com/Aitidi/c4d-val… 🔗 Boghma: boghma.com/zh/c4d/plugins… #Cinema4D #C4D
Today, we’re launching Fastlane 2.0. We're also announcing a $3.5 million seed round. The biggest problem that brands face when running ads is not having enough creatives to test and find winners from. They don’t know what to test, they don’t test enough, and their winners Show more
I open-sourced Song Exploder Drop in any song and hear the vocals, drums, bass and chords on their own. It also writes the MIDI, finds the key and tempo, and puts one song's vocals over another song's beat Runs on your Mac. MIT github.com/royherma/song-… PRs welcome!
Weekend hack: HackerTube. I was annoyed with YouTube's recommendations so I had Claude filter down 43M comments over 20 years of HN to 6,454 videos that keep being recommended. *Significantly* better viewing experience, ~2 hours with Opus 5.5: hackertube.org - Excellent Show more
Loved Karpathy's HackerTube so much I wanted it on my TV, so I built a native Android TV app for it Pick a video and it plays on YouTube on the TV. Built with Opus 5.5 in about an hour. github.com/ephraimduncan/…
Weekend hack: HackerTube. I was annoyed with YouTube's recommendations so I had Claude filter down 43M comments over 20 years of HN to 6,454 videos that keep being recommended. *Significantly* better viewing experience, ~2 hours with Opus 5.5: hackertube.org - Excellent
I built Host-Caster because I wanted to keep up with my day without pausing my music. Now AI radio hosts tell me what's on my calendar between songs. They also judge my playlist. Coming soon to Android. Try it: host-caster.com Self-host it: github.com/eliautobot/hos…
You can make insane pixel art effects with opus 5.5 now! It writes one, renders it, looks at the frames and fixes what's wrong until it holds up. We made 232 that way, no images, all code, and open sourced the lot with the skill! Open source: github.com/patch-gg/pixel…
I just released Stackapella, a harmony-singing app. Learn a part by ear, then record every voice yourself, in the browser. It's open source, Flutter apps for mobile and desktop are on the way. Try it: stackapella.com/?ref=x Code: github.com/stackapella/st…
side projects i have shipped this year beachball.click - Desktop beachball superwhisper.com/kiln - Quickly create bootable drives github.com/superultrainc/… - Fast Github PR TUI github.com/nchudleigh/omac - macOS nav on Omarchy github.com/nchudleigh/sfs… - SFSymbols CLI Show more
I make games and needed animations, so I built MotionBridge: AI video → real game-ready animation on YOUR rigged character. Free, open source, inside @ComfyUI. Type a move → MiniMax H3 acts it out → it lands on your rig as FBX/GLB. github.com/powerhouse90/m… Show more
A full shirt in Blender in 5 minutes. Drafted, sewn and simulated. 🪡🧵 Free. Still building it. DEVIL-DESIGNER v0.10.0 👇 github.com/Artbyo3/DEVIL-… #Blender #b3d #VRChat
I built Tide because I wanted YouTube Music playing while I game, without keeping a browser open. Native Windows app, a tiny mini player, and about 96 MiB RAM including playback helpers in my playback test. Free and open source: github.com/yotam1001/tide…
Introducing Daruma Desk Inspired by the Japanese daruma, every task waits on your desktop with one eye painted, until you complete it.✨ made with @claudeai opus 5.5 @ElevenLabs @threejs Free for Mac 👇 github.com/ashub98-png/da…
I open sourced Higgsfield! With a goal in mind, make it as easy as possible for anyone to create, in the comfy cloud or on your local machine! github.com/Trenchplanet/m… Will continue to work on this github, to make it really the best all in one solution for new or experienced Show more
Introducing Revideo 🎉 Many are paying $199/mo for Revid just to create content That's $2498 a year. Forever. Too expensive So I built a free open-source alternative No subscriptions, no lock-in, no limits Have fun 🥳 Repo :- github.com/SamurAIGPT/rev…
My NTSCRT tv distortion app is so accurate that you can zoom in and see each individual scanline on the TV. Does anybody notice? Probably not... but I made it for myself, because I'm extremely picky about that shit. It's not a "filter," it's more like a simulation of the entire Show more
BakedVoxelLighting - a 4km x 4km world running in the browser. Three.js + WebGPU, with voxel lighting baked on the GPU and cached locally. A little walk through the grass and trees. Still lots to fix but getting there! github.com/SamG-Coder/Bak… Try it: samg-coder.github.io/BakedVoxelLigh…
how a chip is made: sael.net/chip-fab one invisible speck of dust can kill it! made with Opus 5.5 and Threejs
Wouldn’t it be cool to use wax seals to digitally sign documents? 😍 I built a few different more styles of digital wax stamps. It's so fun and cool, all one shot by Claude Opus 5.5 Live: wax-stamp.wasmer.app Code: github.com/thebuggeddev/w…
A 3D wax seal stamp created using Claude Opus 5.5 💮
we just open sourced the last @Blender AI plugin you’ll ever need github.com/scenario-labs/… > 500 models, one tab. images, video, 3D, audio, textures, worlds > built for humans and agents > live now
Open-sourced my pixel art normals generator! It compiles to a CLI and a wasm lib. github.com/Hugo-Dz/sprite…
I made a hyper accurate simulation of our solar system with Opus 5.5 Download it here: github.com/ChrisJDiMarco/…
Learn object mechanics with Claude/Codex I built a gallery where you can explode everyday objects, read about every part of them & see how they work Codex + Ryan’s Anatomy skill anatomy.amirmushich.com
Just open-sourced Frametell 🎬 Turn your ideas, notes into narrated explainer videos. An AI director agent plans the storyboard, writes the script, voices it and animates every page. One sentence in, a 1080p film out. github.com/sitor-ai/frame… Watch it turn one sentence into a Show more
I built a native macOS editor with an AI color grader for my DJI D-Log M footage. It also comes with an MCP server so your agent can use eddie to edit your videos for you. github.com/champ3oy/eddie
We open-sourced an entire 3D team for Blender. Meet the Scenario plugin. github.com/scenario-labs/… Work directly in Blender, or put Claude Code in charge through MCP. 📁/scenario-plugin ┃ ┣ 📁 Concept Designer ┃ ┣ 📁 Concept Art From a Prompt ┃ ┗ 📁 References From Your Show more
haiya, I built a dictionary that can roast you AND flirt with you 🗣️ You need both to survive in another country for real. Now in 4 languages. Zero textbook energy. sound-dictionaries.vercel.app All pronunciations by @FishAudio Drama 3 ⬇ 🧵 Learn Chinese, Japanese, Spanish & Korean Show more
$52M seed round. 15M+ users. But this is what we're most proud of yet. Introducing Drama 3: the most emotive and controllable TTS model in the world And yes, it's open-weight. You can now control how even a single word should sound, change its tone, and shift your voice
Do you all remember talking tom? I built a little version of it with Bulbul V4 Flash. Meet Billu! You can chat with it, make it repeat after you, and challenge it with tongue twisters. 83 voices, 11 languages, and <250ms time-to-first-audio. bulbul-v4-studio.vercel.app
Today, we're introducing Bulbul V4 Flash, our latest text to speech model built for natural, expressive speech across Indian languages. Flash brings frontier-quality speech into a smaller, more efficient model, preserving the subtle details that make voices sound natural while
Yes, CAD! Releasing today Enclose.dev – my second open-source project. With AI rapidly learning how to output 3d models, I feel like I needed an app that standardized the way I made fast iterations, controlled versions per-chat, custom tools and interactions Show more
I've open-sourced the vibe-coded app that helped me create this video with our API. If you want camera control for your image/video, try this out! Try: camera.wlt-ai.art Code: github.com/worldlabsai/ma…
what did Ilya see?
Silo lovers I initially wanted to build a game around Silo, but though what if we could just be inside the Silo? So I played around & built an interactive 3D visualization to explore the cafeteria, farms, stairs, living areas, mechanical and more. silo-two-tau.vercel.app
designers drag selection boxes hundreds of times a day. I made a tiny thing to make you smile :) draw a frame, let go, and a doodle friend pops in with a little note just for you 💌. 26 friends to find. go meet 'em! framefriends.vercel.app
Walked by the Obelisk of Theodosius in Sultanahmet the other day and I thought, what if there was an app I could use to read what it says? There is one now. Just @threejs and one HTML file Built with Opus 5.5 👉 obelisk-390.vercel.app
Built my entire university campus in browser with @threejs mount-alison-3d.vercel.app
Built with Three.js, TSL and my WebCUDA. The .cu kernels compile to WGSL and run on WebGPU - FFT ocean, moving clouds, reflections and caustics on the sand, with a full Gaussian splat mode. github.com/SamG-Coder/dyn… samg-coder.github.io/dynamic-gaussi…
I made another VST plugin. And this one is also free. It’s an 808 bass plugin called Big Booty Bass. Enjoy: github.com/kenwheeler/big…
One isometric object wasn’t enough, so I made 10 :) iso-figures.vercel.app Added dramatic lighting, customizable theme colors, and a different interaction for every object. Inspired by @wheresryan22’s isometric object and @0xbigturk' skill.
The prompt: "/isometric-objects i would like another svg isometric but this time it will be a physical old screen like Apple first PC with the logo of anthropic on the screen, and we like to have a keyboard with a cable"
Connected my AI agent to a pen plotter to properly draw me a personalized newspaper Using @grok bot I also made a printable version so you can try 👇
Lavoisier was right: nothing is lost, nothing is created, everything is transformed. So I made it visible: one monolith, 32,000 shards, a cathedral, a whale and back again. Built with Opus 5.5 using Three.js. Source code: github.com/iamtechartist/…
@AnthropicAI What on earth have you been cooking with this Opus 5.5 model? Probably the best representation of this Midjourney image I created a while back. I asked it to bring it to life, and it went to town. Feel free to have a play with it here: tension-type.vercel.app It Show more
我建了一个新项目 OPUSCAR / opus5.5的奥斯卡 这两天一直沉迷用 Claude Opus 5.5 做视频,做了100 多支,挑了 39 个风格,开源成 Lemo-Opuscar,链接放评论区 39 种风格,每种都有风格提示词和一支纯代码做的样片,还有导演、分镜、配乐的方法文档。 Show more
opus 5.5 is something else.. so many people asked me to open source the 3d water from my last post. a few even wanted to buy it so here it is. my first open source drop code » github.com/Aureliengmz/cl… demo » aureliengmz.github.io/clearwater/ show me what you make with it
claude opus 5.5 one shotted this incredible 3d water from a video reference.. almost 1:1
Claude Opus 5.5 animated this. With code. Not a video model. I turned the process into a skill. Drop it in your Claude and create your own Claude animation: github.com/buildwithhanif…
A thread of early explorations with Claude Opus 5.5: A short story about a watermelon created by @kevin_t_ngo.
It only gets better. Opus 5.5 JavaScript animations are really good for content creation. I collected all the learnings from the most trending posts today and packaged it into a skill you can use to create these seamlessly. Github link to the skill in comments:
Opus 5.5 is honestly impressive for video generation and I am having a lot of fun tinkering around my own custom skill for generating these. I will have the skill on my Github soon. (this was made on xhigh effort)
Since 99% of my Lightroom use was just applying presets, I made a little app that does that. Maybe useful if you only use Lightroom like I did. Super fast, works with your existing Lightroom presets, plus some QoL stuff. github.com/changs/bp_phot…
i may be building the most accessible platformer-maker ever. you don't download anything to make a WAMP level you go to wamp.land, click the editor, build the level you want, then you press publish & it's part of the world everyone else walks through.
Beautiful! If anyone is looking for a skill to help do stuff like that, I just open sourced Anidoodle. github.com/alexgreensh/an… Helps you illustrate and animate with 100% deterministic code. Storytelling methods, music etc all wired right in.
Claude Opus 5.5 drew each frame of this animation in JavaScript. Here's "how browsers work" in 40 seconds.
I made a tiny corner of the internet called Little Garden. You can draw your own flower, write a little note, and plant it in a shared garden for other people to find. No accounts. No feeds. Just flowers and little messages. little-flowers.vercel.app made with React + Supabase
It's been a while since I posted anything here. Just sharing an anti-aliasing plugin I made for Aseprite. That's all :) wibuka.itch.io/aaaa
"i" built a tool that lets you use your e-drums with all the stock @Ableton kits and have them mapped correctly currently works just w/ efnote but point your agent at the code and it'll work with anything github.com/david-alexande…
I just launched & open-sourced Corridor · Art New Tab 🎨 Turn every new tab into an art wall with 106 masterpieces, daily picks & custom rotation. You can also use your own photos, posters, product shots or flashcards. yearnst.github.io/corridor-newta…
I built a Photoshop-like image editor. It’s called Compositor. robbietilton.com/compositor I originally built it for myself to get off my Adobe subscription, but decided to release it for free and make it open source. It has all the essential tools I need for compositing, with none Show more
okay wait, this actually worked: wishlist-lego.vercel.app/lin you can build a lego set out of anything you want and just leave it on the internet? here's how i made it 🧵
I built a little sandboard in @threejs and webgpu to play with, and yes, on mobile multitouch is supported still a first draft, but i really like the feel of it You can play at: sand.scottsun.io Source: github.com/scottstts/Sand…
Game devs, I made you some music! 10 original loopable cozy fantasy tracks for RPGs, exploration, towns, menus and story-heavy games. Royalty-free, ready to drop into a project. yannz41.itch.io/cozy-adventure… #GameDev #IndieDev #GameAudio youtube.com/watch?v=CXe9bD…
Was watching Avatar 2 & 3 and randomly thought, “what would a water vs fire button look like?” so I made it🌊 vs 🔥 which one do u like ? water-fire.vercel.app
I made some optimizations for disk caching and better memory management for LongVideo nodes. runs long generations in chunks to avoid OOMing. very useful for those who can only gen 5 seconds or less at a time. github.com/RealRebelAI/Mi…
I built NEMA. 🪱 302 neurons. One market. Published worm wiring powers a neural model that trades simulated SOL. Watch its activity, silence a neuron, and replay the market to see what changes. An 8-bit worm with an open-source nervous system. github.com/ashleyotooliga…
Holy Fu*K, this is insane. I built the most inefficient way to chart and unfortunately it goes incredibly hard. Turn on your camera and start moving charts with your hands. Pinch to zoom. Swipe to pan. Identify trading concepts. Vela handles the charts. Google’s MediaPipe Show more
🎵 YuE2 is pushing open-source music generation surprisingly close to models like Suno, with the latest WildSongBench results showing it competing with Suno v5/v6. I made YuE2Mac, a native macOS app using MLX to make it easier to run on Apple Silicon 🔗 github.com/arinltte/YuE2M…
I made oto maker, a browser-based sound effects tool for game developers 🎮🔊 Explore presets and FM synthesis, layer effects, trim & normalize, and arrange sounds on multiple tracks. Export your creations as WAV. iwao0.itch.io/oto-maker #gamedev #indiedev
I built a web app called LayerLift that allows you to super easily create timelapses from your 3d Printer's slicer Gcode files. Change the filament, build plate, lighting, motion, speed, camera style & more. Try it out at layerlift.studio
Inspired by this fold animation, I built an interactive study. Black screen vs. frosted glass. Scrub through the motion, slow it down, and see how blur, shading, and endpoint snapping change the feel. Try it: iphone-fold-animation-study.vercel.app
绝了! iPhone Duo的设计灵感吗?
astra. 2 prompts. gave it a reference video and the product page. insane lmao react component btw github.com/jal-co/iphone-… iphone-duo.vercel.app
i had to really push astra on this, but it did end up coding this nice transition from sunset -> nightfall -> moonrise -> milky way there's not a single image in here. it's all just JS code. i'm mildly impressed repo: github.com/kunchenguid/fl…
Open-sourced a bunch of @ComfyUI nodes and workflows for @reactorworld endpoints. This includes their endpoint for MiniMax FastH3. The repo still needs cleanup but it's ready to use. Enjoy: github.com/stefanionescu/… Might be useful for others participating at Worlds Hackathon Show more
Real-time AI experiences are now solved AND open sourced. We worked closely with @OpenAI to build the best framework for it, combining GPT-Live-1, @TryLiveAvatar, and @HyperFrames_ Check out the demos below and show us what you build with it. github.com/heygen-com/liv…
Good prompts are rare and making them sucks so i shipped a GPT Astra / Claude skill Can make you 50 of these in under 30 min ads? lock a character or product same face. same voice. same light. across 50 videos free: one-face-lock.vercel.app
So delicious 😋 Seedance 2.5 Prompt: Create a 30-second fast-paced cinematic Japanese anime cooking video showing the preparation of authentic katsudon, entirely from the text description below. IMPORTANT: Do not display, recreate, trace, reference, or imitate any storyboard,
The viewer-requested assets that we've made live on stream are available now! kaylousberg.itch.io/mixed-bag-1 It's a truly random collection of things that at least 24 of you asked for 😂 so I hope you enjoy! #gamedev #blender3d #indiedev
I made a 3d view for a character for the guild i am in on @Everdraw_RPG You can interact with the character in pathfinderwink.vercel.app what do you think ? Still working on it but it is perfect in my eyes now Pathfinders for lifeee @LoveCrypto15
✨ @Everdraw_RPG Art Contest ✨ Our beloved characters are making the rounds through all four guilds! Contest Guidelines: - Show Wink, Rabbit or Glyph repping one of the four guilds: 🛡️ Pathfinders | 🩸 Bloodforged | 🌟 Starweavers | 🌳 Greenbound - Media: Digital,
I love the design of 3 things very dearly: spray paint cans, album art, & collectibles ..so I built a little site with @reve that turns your fav song into a custom blind box toy sound on for more fun :) rattlers.vercel.app
i used fable 5.1 to one shot this sticker shader tool i can now cut out pictures of my puppy and turn them into digital stickers 🐶
We’re introducing Claude Fable 5.1 and Claude Mythos 5.1. They're the world’s most advanced models for coding and knowledge work.
I made a wasm build so you can actually see it. Fake filesystem of course. makepad.nl/files/ Code: github.com/makepad/makepad not mobile friendly.
Hey fable write me a disk storage visualizer, but like, jurassic park style.
I always wanted to be a creative person who shared things I've made freely: So I'm working on it with some of the latest here: github.com/krispuckett/Sw… github.com/krispuckett/mu… github.com/krispuckett/mu… github.com/krispuckett/Si… Shaders, orbs, and a parametric card design tool.
I always wanted to be a creative person who shared things I've made freely: So I'm working on it with some of the latest here: github.com/krispuckett/Sw… github.com/krispuckett/mu… github.com/krispuckett/mu… github.com/krispuckett/Si… Shaders, orbs, and a parametric card design tool.
Just released an open-source React package for interactive 3D QR experiences. npm i designqr import { DesignQR } from 'designqr'; import 'designqr/style.css'; <DesignQR value="github.com/johnson7543/de…" transparentBackground={true} /> Try editor: design.johnson7543.com/qr
新しいプラグイン「YMM4 Ransom Note(切り抜き文字)」を公開しました! 新聞や雑誌の活字を切り抜いて貼り付けたような文字(脅迫状風)を描く図形プラグインです。フォントも紙の形も1文字ずつバラバラに貼り付けられます。 ダウンロードはこちら github.com/namakemono-san… #YMM4 #YMM4Plugin
1kg of iron vs 1kg of cotton. Same weight. Completely different volume. This is why I built Weight2View — a 3D way to see weight instead of just reading a number. Try it: w2v.amirhbuilds.com Open source: github.com/AmirHBuilds/we…
イラスト1枚でVTuber3Dモデルが生成できる「VTuberオリキャラメーカー」が話題ですね! 3Dモデルと言えば、CodexやClaude Codeに依頼するだけでVRM感情表現を拡張出来る『VRM Expression Agent Harness』というツールを公開しています アバター表現を拡張したい方はぜひ github.com/shinshin86/vrm…
Introducing Fluoddity.com! Hundreds of thousands of particles self organize into a stunning variety of structures. Explore a world of possibilities with mutation and artificial selection! This is my personal tool for exploring Fluoddity, rebuilt for the web by Opus 5
I’ve been experimenting with recursion in WebGL, and I built this inception-style carousel using Three.js and GLSL. The secret sauce? Using WebGLRenderTarget try yourself:infiniterecursiveslider.onrender.com git: github.com/MohammadAyaanN… thanks and credit to @akella Al-Hamdulillah 😊
Free Blender extension to paint geometry on surfaces. Share if you think it's useful for the community. #b3d github.com/riouxr/BB_Simp…
I built a Claude Code plugin for generative art. It teaches @claudeai the actual craft: determinism from a hash, same piece at 400px and 4000px, honest rarity, plus tools to verify a sketch before minting. Free & open source 👇 github.com/camilleroux/ge…
A fun experiment with Code Mode and Flue to make generative art. Instead of inventing a tool for every possible shape, the model can write JavaScript and run it in an isolated worker. repo: github.com/paperwing-dev/…
grok voice is fast. i built something that would make that speed visible. my open source engine draws what you speak, while you're still speaking. numbers become live charts. processes become diagrams. it cannot hallucinate a number, it only plots what was actually said. right Show more
Hey everyone! I made a very frustrating Plinko + Pinball game demo along with some Blender & Three.js workflow tips for the @threejsconf @codrops celebration!!🥳🥳 Article: tympanus.net/codrops/2026/0… Demo: …for-threejs-conference-ten.vercel.app Vibed Code: github.com/andrewwoan/cod… Show more
God’s Eye View V1 is open source. It feels like a spy simulator in your browser -- except the underlying data is real, and you can talk to the planet too. Track planes, ships, satellites, traffic cameras, and critical infrastructure. Use voice mode to ask what’s happening, Show more
told chatgpt to make whatever art it wants
what if websites felt less like separate states and more like a continuously evolving field of pixels? i made a chrome extension that diffuses the page as you scroll, type, click, and navigate. try it to spice up your web browsing experience: github.com/cindehaa/pixel… not Show more
2 years later, I made my own tools in a single macOS app: Screen.Movie 🤯
I'm using @screenstudio to record my screen and Capcut for editing. 🙌 These tools are simple and incredibly useful. 🔥
so I built a Chrome extension for football scouts: record match clips straight from browser, tag them by player + action, and compile per-player highlight reels - all in one click, no editing software scouts and clip-makers - test it out github.com/marg1elaxd/Sco…
for everyone in the @doodles community who’s ever wanted a toy of their OG: the wait is over. i built a tool for that gives you a copy and past prompt to make your own toy. try it out at ⬇️ og-toy-factory.vercel.app
tryprokinetic.vercel.app updates I just shipped allows you to export native liquid glass interactions in 4K just burned through my weekly limit so visuals land here early Tuesday
I just open sourced my threejs prototypes I have been working on for the past month - Poseidon (FFT ocean simulation) - Gaia (procedural grass generation) - Dryad (procedural tree generation) - Tiamat (particle based fluid dynamics) - Demiurge (tectonic based procedural planet Show more
I open-sourced Nadir landing page codebase < 1 mb, so it loads instantly - kinda insane for a 3d scroll-driven experience! Live: nadir-livid.vercel.app Repo: github.com/rishabdesigns/… btw it took a ton of time, tokens & polish; so hit follow if you want more of these :)
I built a tool to make my own image grids from now. Try it here: tych.kiira.in
The new image carousel is the biggest UX downgrade in this site's history. There was an entire art form around 4x image polyptych, especially among Japanese photographers, who I learned a lot from stylistically. With 4 seen all together you create a mood, its very impressionist
👋📊 I built a spreadsheet webcam emulator app in @GoogleAIStudio (using Gemini 3.7 Flash), so you can play around with this yourself! Also allows you to export images and CSVs: spreadsheet-webcam.ai.studio
we are roughly 48 hours away from someone streaming the entire @wnba playoffs inside =INDEX(MATCH())
Here’s a text swirling animation that I built with the #swiftui framework. I love spending time building random ideas and animations that pop into my head. For things like this, I honestly can’t imagine going back to UIKit. Code in my GitHub repo. github.com/Shubham0812/Sw…
I also made a little Aseprite extension — a normal map generator. Instead of generating normals from a height map, it uses the arrangement of layers within a group. The results are pretty interesting. #Aseprite
I've open sourced it. Live — see it, try it: da7-tech.github.io/da7em/ The full repo: github.com/Da7-Tech/da7em Best on desktop. Fork it, change it, make it yours — just credit Da7_Tech. Enjoy.
GLM-5.3 made this after 4+ hours!
like i said, i will be adding more artworks to puzzle game i built. i have added the 50 art contest winner made by the community except the one that's like animation. - go to: iconpuzzlebycheff-ucjd.vercel.app - choose an icon (58 available) - pick a 4×4 grid (optional) - switch Show more
i came across @theiconsart yesterday while doomscrolling on x. i spent some time going through every post from the intern and instantly fell in love with the art. so i built a puzzle game for the icons collection: iconpuzzlebycheff-ucjd.vercel.app • choose an icon • pick a 4×4 grid
Idea with an old Needy Girl Overdose art I made ages ago using the anti-AI tool grid-noise-animator.vercel.app
You can steal this design now - code, assets etc. Open sourced it for you - so create your own Link: github.com/amirmushichge/…
隠し絵 — the hidden picture. The image below is hiding something. Tap & hold it. I built TAPREVEAL studio, a free, open-source tool that crafts these reveal images for X. Paint a mask, export, done. 100% in your browser: nothing is ever uploaded. ⊹ enudimmud.github.io/tapreveal/ 👁 Show more
here's how we did it and the open sourced @HyperFrames_ code in thread 🧵 i did a quick screen recording as a quick explainer our open source framework & motion graphics skills: github.com/heygen-com/hyp…
we've eval-ing K3 and we were legit shocked K3 is incredibly good at @HyperFrames_ , winning over GPT-5.6 and Fable 5 at a few of our benchmarks it recreated motion graphics from @leomeethewoo with minimal prompting (i didn't further tune the animations to show raw output)
I couldn't just watch the final and not build something. 😂 So I made a tiny terminal-style website that displays the trophy and the top player in ASCII art. 💻🏆 Sometimes you don't need a reason to code... you just need an idea. (Link below 👇) 2026-world-cup-job.vercel.app
"A website about #JAEMIN " 🩷To celebrate Jaemin's birthday, I made a birthday website for him🐰. 🩷#HAPPYBIRTHDAYJAEMIN #재민 #najaemin 🩷 🔗:nan-asworld.vercel.app (PS: Best viewed on desktop; mobile layout may look misaligned)
Here're some of the great stuff people are currently building ✨ You're welcome to add more in the comments. @SamJWasserman 10 apps/tools to help with AI native filmmaking github.com/wassermanprodu… @sfxnz An open sourced tool that allows anyone to serve and run evals for local Show more
The fanzine is out! 🥹 You can read it here : heyzine.com/flip-book/0b6d… Or download it for free here : playback1995.itch.io/lost-records-p… It features 80 pages of content and messages from fans, artists and devs! Thank you to everyone who made this project possible, y’all are awesome!
Didn’t expect the last post to get this much love. Thank youuu Everyone! ❤️❤️ More projects i built: Svelte AI Elements: svelte-ai-elements.vercel.app Svelte 4 Animations: old animation-svelte.vercel.app Svelte Form Builder: svelte-form-builder.vercel.app
wtf this is Crazyyy sv-animations.vercel.app sv-table.vercel.app sv-blocks.vercel.app sv-efferd.pages.dev sv-matrix.vercel.app sv-particles.vercel.app sv-agentation.com
I don't understand the math but the doodles look great so I made this into generative art using Javascript. Live demo: kengocodes.github.io/math_class-2/ Github: github.com/kengocodes/mat…
I built the Nigerian Literature Archive for the books many of us grew up reading and the ones we may have forgotten. From Ige Adubi to Ralia the Sugar Girl, Eze Goes to School and more, it’s a small way to preserve and rediscover Nigerian literature. nigerian-lit.vercel.app
I collected most of the responses to this tweet, cleaned them up, and gave them a home. It’s now a digital archive where you can discover books you grew up reading and add more books to the collection. Made with Claude Code. Link: nigerian-lit.vercel.app
I made some GLSL fireworks by @v0 after missing the real festival. Project Page🔗fireworks-nine-sigma.vercel.app
for(float i,g,T,e,u,R,l;i++<9e2;){g=ceil(i/8e1);T=fract(t*.3+g*.3-mod(i,9.)*.003)*5.;e=max(T-1.,0.);u=fract(i/4e1)*2.-1.;R=e/(e+.5);l=length((FC.xy*5.-r*2.5)/r.y+cos(g*vec2(2,4))-vec2(R*sqrt(1.-u*u)*cos(i*2.4),R*u+sqrt(T-e)*2.5-2.))*139.;o.rgb+=hsv(R,u,exp(3.-e-l));}#つぶやきGLSL
🇮🇳 HAPPY INDEPENDENCE DAY! 🇮🇳 My India project is finally LIVE 🚀 🔗 our-india.vercel.app 8 days of hard work, countless details, and a lot of learning. A small attempt to tell India’s story through the web. Proud of what I built. Even prouder of what it represents. 🇮🇳
Gemini Flash 3.7 + Seedance 2.5 = cinematic websites I built this experimental website dedicated to the Arsenal winning the first trophy of the season in a few hours - all with AI Remix (Google AI Studio): amirmushich.link/arsenal-remix Preview: arsenal-scroll.ai.studio Pipeline🔽 Show more
Vibe coding games with Gemini 3.7 Flash, but missing sound effects? Google doesn’t have a dedicated SFX model (yet?), so I built a quick pipeline in AI Studio: sound idea ➔ optimized prompt ➔ Omni Flash video ➔ isolated audio slices 💥 Full prompt + pipeline breakdown below!
I gave Gemini 3.7 Flash a handful of reference images and a rough idea of what I wanted. Ran /grill-me to align on the vision. Hit /goal & /teamwork-preview and let it cook. A couple of iterations later, this is what came out! An interactive kind of experience.. built with Show more
Gemini 3.7 Flashちゃんにバカゲー作ってもらった🤗 昔妄想したアプリ 『Isekaied Generator』 半年くらいぶりに夢(?)が叶った😂 jemini-abyss.github.io/Isekaied-Gener… note.com/jemini_gemini/…
Built a site for exploring Game of Thrones lore 🐉 Characters, houses, dragons, battles, an interactive map, a timeline, and hours of stuff to explore Built this to see how far I could push generating a content heavy site Made with Kimi K3 got-chronicles.vercel.app
Kimi. Kimi. Kimi. 🔥 You can literally build a beautiful website in a couple of hours using @Kimi_Moonshot 3D effects, images, UI elements, everything gets generated on its own. You don't have to spend time finding assets, fonts, or any other design resources. This is the Show more
This tool is insane! Create your own mascot in Grok Bot style. Export as SVG animations. Save it → bloub.vercel.app
been loving the aesthetics of the annual reports, so I built a gallery of them: annual-reports-gallery.vercel.app
I built a tiny tool called Thought Detox Write down whatever’s on your mind, then burn it and let it go No accounts. No complicated setup. Just a quiet space to get your thoughts out of your head Try it here: thoughtdetox.netlify.app
I made a little experimental three.js landing page with Claude Code. And I’ve open-sourced the whole thing. Live: hxmzaehsan.github.io/last-train-rec… Repo: github.com/hxmzaehsan/las…
Two things: 1. My @LaraconUS talk recording is live on YT (already the livestream before, but it's standalone now) youtube.com/watch?v=o9Lqfu… 2. If you liked the ascii art, I made a git submodule repo for it! github.com/paulinevos/asc… Considering converting it into an executable + Show more
I built a color picker you flip through like a record bin. @threejs + a vanilla Web Component, zero image assets. The paper grain is 900 random flecks on a Canvas. Palettes only suggest colors that exist in the rack. Live: swatch-rack.vercel.app Code: github.com/finktheartist/…
I built a tool for this. mcu.a16.xyz Check it out
I built this so you can relive what it took for us to get independence turn the sound on
Can AI create a luxury campaign that actually feels like a commercial? I built this fictional fragrance concept from two references: one product, one character. 15 seconds. One consistent visual story. NOIR ÉLAN — *The Last Detail.* 🎬 ✨ Created with Grok Imagine @grok
The City That Recognized Her 30 million faces in the city. Tonight, every screen showed hers. And then the drones started looking. ✨ Created with GPT Image 2.0 @ChatGPT Prompt below 👇 Create a cinematic dark cyberpunk scene at midnight in a gigantic futuristic megacity
Magnific just shipped Auto Layers 2.0, and it quietly fixes the most annoying part of AI image work. It splits any image into editable layers. Subject, text, logo, background, all separated automatically. You upload or generate an image, get every layer on its own, then move, Show more
Happy Independence Day 🇮🇳 Built a website to showcase India's science and technology milestones over 80 years. india80.ayushworks.com
I built the Braun BC02 alarm clock as a fully interactive web app. Using Claude Code.
Made in @figma
I built something for fun 😆 It's called LuckyDangle, and it basically lets you hang a lucky charm on your Mac 🧿 Check it out and show some love ❤️
Just launched Chamali™ — a free Framer portfolio template for designers, art directors and visual creatives. Built around bold typography, editorial layouts, CMS-powered projects and smooth interactions. Free to remix ↓ framer.link/u8NDOKB
Your our history shouldn’t be taught in a boring way 🫠 I’ve always loved history, but I could never imagine what life actually looked like back then. So I built Empire Atlas, a 3D interactive explorer of 8 historical empires using @threejs and @Kimi_Moonshot K3 🔥 It lets you Show more
been chatting with some innovative chad in the space - @CournotProtocol building the first AI-native reasoning oracle designed to produce verifiable, auditable resolution for unstructured real-world events - @TradeBoba building the next gen trading terminal with supreme UIUX - Show more
corrected W32 card: the earlier image showed only a subset. This attachment shows all 20 projects from Aug 3-Aug 9, 2026, in manifest order. 1. ds4: DeepSeek V4 and GLM inference across Metal, CUDA, and ROCm. github.com/antirez/ds4 2. Computer (Cloudflare): Durable Object Show more
It’s live! I just launched Animate This UI on Figma Community. A Figma plugin I’ve been building to make UI motion simpler: Select → Choose interaction → Customize motion → Apply Hover. Press. Enter. Exit. Loop. Stagger. Float. Pulse. Breathe. Bounce. Spin.
Met a young founder at the Marc’s meetup today Got stuck in traffic in heavy rain on his way over, so he vibe coded an app in the car You take a photo with him, the app adds a frame with his name and contact info He sends it to you, and the photo is the business card I love Show more
Wouldn’t it be amazing if an e-commerce app could actually show you exactly how that shirt will look on you before you buy it? 🤯 That’s what I built using Claude Opus 5. A real fabric and size aware virtual try on experience where you submit your measurements and photos, Show more
WAIT… YOU DON’T NEED WIFI TO SEND FILES ANYMORE. 🤯 No WiFi. No Bluetooth. No network. Just QR codes flashing on one phone and a camera on the other. ~129 KB/s. 2 MB in seconds. Built in one night with Claude Code. x.com/om_patel5/stat…
Claude Fable 5 high in Claude Code 🔥🔥 > SpaceX Falcon 9 launch, stage separation, boostback, and landing simulation using three js
Claude Opus 5 vs Qwen 3.8 max opus nailed it 🔥🔥 > SpaceX Falcon 9 launch, stage separation, boostback, and landing simulation using three js
Built a web font explorer that works the way I think about type, by feel and property. font-selector-phi.vercel.app
Someone vibe coded an AI interior tool that redesigns your room using furniture you can actually buy, with every piece linked to a real product and a full shopping list in the sidebar. x.com/om_patel5/stat…
ByteDance released an official Seedance 2.5 prompt guide and most people still don't know it exists i turned the whole thing into a Claude skill by the time Seedance 2.5 hits every platform your claude will already be an expert at every prompting style the official ByteDance Show more
This replaces scrolling for me now 😅 Had to take one of those little devices for a spin after seeing them everywhere recently. Opus 5 wrote the renderer and sim in C to get the most out of the ESP32 S3. Will do something that leverages mic + speaker next…
Someone found a way to run DOOM inside Microsoft Paint. Microsoft Azure CTO Mark Russinovich created a project called DoomPaint, which uses Paint as the game’s display. Instead of rendering the game in a normal window, every frame is copied into Paint in real time. The game Show more
i built an app that turns the song you're listening to into an animated vinyl wallpaper vinylformac.com
All this talk about AGI destroying moats and everything made me want to ship again One of the conclusions from all of you was, if you can use AI to ship faster and better, you should just ship way more complex things, like things you could not imagine making before For me Show more
I’m going to publish my engine-independent framework for procedural generation, animation and rigging, concept art, 3d modeling, world simulation and generative level / environment design. Automated playtesting, game marketing and capsule/trailer design. These are all really Show more
Vibecoded a silly little tool that transfers files from your computer to your phone air-gapped using your camera at ~50 Kbps. Nice to have when you're offline or on a plane, or need to send something super duper securely.
someone open-sourced a tool that turns any phone video into a full 3D world in real time. you record a walk around your house, drop the mp4 in, and the entire scene comes back as a walkable 996k-point world at 60fps on your local GPU. no cloud. no subscription. runs 100% Show more
made a game where you draw countries from memory
Sneak Preview of my "Motion Previs Studio" that I built and will open source release for you all to use and make amazing creations with very soon. Got inspired by @JoshDaws and then went to work for a few days on 2 custom desktop apps.
I'm open-sourcing my Agent Skills library. 75 skills for Codex, Claude Code, Cursor, and other agents, focused on web design, landing pages, motion, WebGL, UI styles, and assets. A few favorites: - Video to Super Prompt Turns a screen recording of a design, landing page, or Show more
We called it Toolcraft. A starter kit, UI component library, and set of AI skills for building micro-apps for designers. Hopefully, it will be released this week together with a new YouTube video featuring a full tutorial. Although maybe we should call it a “short,” because the Show more
i built a app that's perfect for shy vloggers meet stitch: the pressure free mini-vlog app that's so low key that anyone can vlog, even if you are a shy introvert