2D, 3D & VR experiments and tutorials in Godot 3 & 4

Production-grade engineering skills for AI coding agents.

A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.

아래한글 hwp viewer and editor by rust and wasm

headless remote desktop to your dgx spark in crystal clear 4k

π RuView: WiFi DensePose turns commodity WiFi signals into real-time human pose estimation, vital sign monitoring, and presence detection — all without a single pixel of video.

Build ultra fast, tiny, and cross-platform desktop apps with Typescript.

An autonomous agent for deep financial research

RLAnything & DemyAgent: General and scalable agentic RL algorithms across terminal, GUI, SWE, and tool-call settings

Korea Investment & Securities Open API Github

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

This repository contains the code and data of the WebMall benchmark for evaluating the capability of Web agents to find and compare product offers from multiple e-shops.

AlpaSim is an open-source autonomous vehicle simulation platform designed for development and testing of end-to-end AV policies

A monitor of resources for DGX Spark

An Enhanced TOP program to monitor your Nvidia DGX SPARK's Hardware

The best ChatGPT that $100 can buy.

This Docker image is purpose-built for training and inference using Unsloth and vLLM on NVIDIA Blackwell (SM 10.0/GB10, DGX Spark) GPU architectures.

NVIDIA DGX Spark Playbooks

Web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss locally.

Collection of step-by-step playbooks for setting up AI/ML workloads on NVIDIA DGX Spark devices with Blackwell architecture.

Shopping MMLU: A Multi-Task Online Shopping Benchmark for LLMs.

A framework for few-shot evaluation of language models.

Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs

Training library for Megatron-based models with bidirectional Hugging Face conversion capability

Tools for merging pretrained large language models.

Curated list of datasets and tools for post-training.

Qwen3-omni is a natively end-to-end, omni-modal LLM developed by the Qwen team at Alibaba Cloud, capable of understanding text, audio, images, and video, as well as generating speech in real time.

Tool for generating high quality Synthetic datasets