Refract
Build it visually. Build it with AI. Ship it in one line.
Refract launched on March 17, 2026 with 4 votes, #2,516 of 23,380 launches that month and more than 75% of that year's launches.
What it does
The first visual compositor for real-time GPU effects. Layer shaders, 3D, text, and animations in one editor. Build by visually by hand or tell AI what to build. It works directly in the compositor, not a code sandbox. 50+ presets. 15 3D primitives with PBR materials. Custom GLSL. Hover, scroll, click, and appear events per layer. With Native AI built in and an MCP server with 22 tools. AI gets the same controls you do. Exports a single HTML file. No SDK. No vendor lock-in.
Compose shaders, text, and 3D into interactive scenes. Export an embed that works in any site. No packages, no build step, no SDK in your project.
Shaders, 3D, and text in one compositor. Export a single embed tag that works on any site. No packages, no build step, no SDK in your project. Gradients, noise, plasma, caustics, chrome, topographic contours, and more. Start from a preset, import your own SVG, or write custom GLSL. Add text, shapes, and 3D alongside your shaders, then animate them. Hover, click, scroll, and viewport triggers. Chain animations across layers and export the whole scene as one embed. 15 font families, custom font uploads, shapes, and colors. Position anything freely on the canvas alongside shader layers. Mouse follow, repel, distort, pulse, and orbit. Click toggles, hover animations, scroll-driven motion, and…from refract.build
Does a similar job
all alternatives →
GPT-2 implemented using graphics shaders2025 · github.com · ▲228Back in the old days, people used to do general-purpose GPU programming by using shaders like GLSL. This is what inspired NVIDIA (and other companies) to eventually create CUDA (and friends). This is an implementation of GPT-2 using WebGL and shaders. Enjoy!
- SLShader Lab, like Photoshop but for shadersApr 2026 · eng.basement.studio · ▲160
Create, stack, and animate shader effects on images, video, text, and 3D models — free, in your browser, powered by WebGPU. Export video, publish to the community gallery, and remix any published scene.
MCP server for Blender that builds 3D scenes via natural language2025 · blender-mcp-psi.vercel.app · ▲151Hi HN! I built a custom MCP (Model Context Protocol) server that connects Blender to LLMs like ChatGPT, Claude, and any other llm supporting tool calling and mcps, enabling the AI to understand and control 3D scenes using natural language. You can describe an entire environment like: > “Create a small village with 5 huts arranged around a central bonfire, add a river flowing on the left, place a wooden bridge across it, and scatter trees randomly.” And the system parses that, reasons about the scene, and builds it inside Blender — no manual modeling or scripting needed. What it can do: -…
Demo of Agent Based Model on GPU with CUDA and OpenGL (Windows/Linux)2023 · github.com · ▲55Demo of agent based model on GPU with CUDA and OpenGL (Windows/Linux) Agent instances on GPU memory Uses SSBO for instanced objects (with GLSL 450 shaders) CUDA OpenGL interops Renders with GLFW3 window manager Dynamic camera views in OpenGL (pan,zoom with mouse) Libraries installed using vcpkg (https://github.com/KienTTran/ABMGPU)
More ai this month
the category →
Paintings by AI models: programs run through a simulation of oil paint.
AI · 21d ago · stillwet.art
PixVerse R2▲381A real-time world model you can explore and change
AI · 30d ago · world.pixverse.video
Source: Product Hunt launch ↗
Launched alongside, March 2026
the whole month →
Switch from ChatGPT to Claude with import memory feature
AI · Mar 2026 · claude.com
Littlebird▲709Littlebird remembers everything across your meetings, messages, docs, and apps, then takes action so you can recall any detail and never lose context.
AI · Mar 2026 · littlebird.ai
