- New York, NY
Highlights
- Pro
Lists (16)
Sort Name ascending (A-Z)
Stars
- All languages
- Assembly
- Batchfile
- Bikeshed
- C
- C#
- C++
- CSS
- Clojure
- CoffeeScript
- Dart
- Dockerfile
- Elixir
- Elm
- GLSL
- Go
- HLSL
- HTML
- Java
- JavaScript
- Jupyter Notebook
- Kotlin
- Less
- Lua
- MDX
- Makefile
- Markdown
- Mathematica
- Python
- Reason
- Roff
- Ruby
- Rust
- SaltStack
- Shell
- Standard ML
- Starlark
- Svelte
- Swift
- TypeScript
- Vue
- WebAssembly
- Zig
Run models larger than your RAM or VRAM by streaming MoE experts from SSD. Built on llama.cpp.
A hierarchical inference engine for frontier MoE models: hot experts on the GPU (CUDA, Vulkan), warm ones in RAM, cold ones streamed from NVMe. Written in C, runs on the hardware you already own.
Atomic Agent is a local-first AI agent. Runs open-weight models on your own machine via llama.cpp.
Declarative dragging for SVG on the web
Architectural methodology for frontend projects
The fastest way to run Qwen 3.8 Flash Next, Qwen 3.8 27B and Ternary Bonsai 2 27B on a Mac: 125 tok/s in OpenCode on an M5 Max, and a 27B model on 16 GB Macs. Native MTP speculative decoding on Appβ¦
Qwen3.8-Flash-Next on any consumer hardware: one-click install for Windows / Linux. Strata inference engine, OpenAI/Anthropic API on localhost, optional image input.
Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4.1, MiniMax-H3, Gemma 4, FLUX and more.
LibreYOLO is a MIT licensed open source computer vision library
Non-autoregressive System 1 decision engine. Typed choice, score and yes/no decisions over any text in a single forward pass, in 100+ languages, with a router that picks the right checkpoint per reβ¦
Local typed decisions, contrastive data curation, and model evaluation.
Sub-50mb agentic, voice and vision intelligence for consumer devices.
why use many token when few token do trick. Skill + local proxy for coding agents: shorter answers, smaller tool output, every original recoverable.
Next generation toolkit for web3D and photorealistic graphics
Convert gaussian splatting PLY file into USD file which can be used in NVIDIA Omniverse.
Sharp Monocular View Synthesis in Less Than a Second
100% private on-device voice models for speech-to-text and meeting transcription on macOS
Render Gaussian Splats using Metal on Apple platforms (iOS/iPhone/iPad, macOS, and visionOS)
GSKit is a macOS 26 experiment for viewing Gaussian splats through a RealityKit-native render path.
Nanite-Style Gaussian Splatting Render
bevy gaussian splatting render pipeline plugin ποΈπ
Lightpanda: the headless browser designed for AI and automation
Ο RuView turns commodity WiFi signals into real-time spatial intelligence, vital sign monitoring, and presence detection β all without a single pixel of video.
An agentic skills framework & software development methodology that works.
Designer Skills Collection: agentic skills, commands, and plugins for design β from research to systems, UI, interaction, and delivery.
Mobile MCP: let AI agents drive your iOS and Android apps. MCP server for simulators, emulators and real devices. Works with Claude Code, Codex, Cursor and any MCP client.