Highlights
- All languages
- AGS Script
- ASP
- ActionScript
- Alloy
- AppleScript
- Arduino
- Assembly
- AutoHotkey
- Batchfile
- Bikeshed
- C
- C#
- C++
- CMake
- COBOL
- CSS
- Cadence
- Circom
- Clojure
- CoffeeScript
- Common Lisp
- Crystal
- Cuda
- Cython
- Dart
- Dockerfile
- Elixir
- Emacs Lisp
- Erlang
- Fluent
- Forth
- G-code
- GDScript
- GLSL
- Go
- HLSL
- HTML
- Hack
- Haskell
- Haxe
- Ink
- Inno Setup
- Java
- JavaScript
- Julia
- Jupyter Notebook
- Kotlin
- LLVM
- Liquid
- LiveScript
- Lua
- MATLAB
- MDX
- Makefile
- Markdown
- Mathematica
- Max
- Meson
- Mustache
- NetLogo
- Nunjucks
- OCaml
- Objective-C
- Objective-C++
- OpenSCAD
- PHP
- PLSQL
- PLpgSQL
- Pascal
- Perl
- Pony
- PowerShell
- Processing
- Prolog
- Puppet
- PureBasic
- Python
- QML
- R
- Racket
- Rich Text Format
- Roff
- Ruby
- Rust
- SCSS
- SMT
- SWIG
- Sass
- Scala
- Scheme
- ShaderLab
- Shell
- Smalltalk
- Solidity
- Standard ML
- Starlark
- Svelte
- Swift
- SystemVerilog
- TeX
- Text
- TypeScript
- VBScript
- VHDL
- Vala
- Verilog
- Vim Script
- Vue
- WebAssembly
- Wolfram Language
- XSLT
- ZIL
- q
Starred repositories
Global edition of ARTEX — an LLM multi-agent autonomous penetration-testing framework. English default, switchable to Korean/Chinese/Spanish/Japanese. For authorized, defensive and detection use on…
ARTEX - AI autonomous penetration testing system (English translation; upstream: Autumn-27/ARTEX, AGPL-3.0)
Fully playable DOOM running on FNIRSI DMC100 (32KB RAM)
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.
CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies
Windows GPU UNLOCK: RTX3090 UEFI port, Korean no-reset Windows boot guide, verified source and benchmark evidence
Apple MLX native implementations of state-of-the-art generative image & video models
MLX-native TRELLIS.2 inference for Apple Silicon — generate 3D meshes from images on > 16GB Macs
Vercel's fx coding agent running on a RISC-V CPU inside Qwen3.5-4B's weights, controlling the model from within.
NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT.
An open-source, GPU-accelerated physics simulation engine built upon NVIDIA Warp, specifically targeting roboticists and simulation researchers.
A Python framework for GPU-accelerated simulation, robotics, and machine learning.
Official implementation of MotionBricks: Scalable Real-Time Motions with Modular Latent Generative Model and Smart Primitives (SIGGRAPH 2026)
Run OpenAI Codex on Raspberry Pi with Remote Control support, automatic startup, troubleshooting and real-world examples.
Daemon to ban hosts that cause multiple authentication errors
A tool to unlobotomize your NVIDIA card!
Unlock full speed FP16 tensor core of NVIDIA Turing GPUs
GPU tensor unlock source for RTX 4090 and experimental RTX 4070 Ti SUPER; firmware generated locally
Your GeForce runs AI at half speed. This fixes it for 20/30/40 series cards. Up to 2× FP16 / BF16 / TF32 tensor throughput
An LLM running on an NPU inside an LLM. Karpathy's stories260K writing stories on a vector unit compiled into Qwen3.5-4B's weights.
Open-source plugin for designing and reviewing software with agents
Qwen3.5-2B with a SIMT GPU inside its weights, 45 compiled layers in front of Qwen’s own, using its Gated DeltaNet layers as registers and memory.