Refract
Build it visually. Build it with AI. Ship it in one line.
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.
Does a similar job
all alternatives →- G2GPT-2 implemented using graphics shaders2025 · github.com · ▲228
Back 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!
- MSMCP server for Blender that builds 3D scenes via natural language2025 · blender-mcp-psi.vercel.app · ▲151
Hi 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: -…
- IWI wrote a C++ ray tracer from scratch without AIJun 2026 · github.com · ▲155
- DODemo of Agent Based Model on GPU with CUDA and OpenGL (Windows/Linux)2023 · github.com · ▲55
Demo 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)
- VAVSC – An open source 3D Rendering Engine in C++2025 · github.com · ▲101
Been making this rasterizer engine in C++ for the past few months, now also adding ray-tracing functionality to the system. Simply load a model or generate a mesh, add some lights, and render.
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 19d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
Launched alongside, March 2026
the whole month →
Switch from ChatGPT to Claude with import memory feature
AI · Mar 2026 · claude.com
