DAZ Studio plugin: embedded HTTP server for executing DazScript remotely and returning results as JSON

RTX 6000 96GB/Spark 128GB vLLM Recipe for Qwen 3.8 Flash Next

Orca is the ADE for working with a fleet of parallel agents. Run any coding agent with your own subscription. Available on desktop, mobile and remote runtime.

worlds via code, from fable 5.1

Linux filesystem defragger written in Rust and Qt Quick/Kirigami

RTX 6000 Pro Wiki — Running Large LLMs (Qwen3.5-397B, Kimi-K2.5, GLM-5) on PCIe GPUs without NVLink

SimpleBLE - the all-in-one Bluetooth library for MacOS, iOS, Windows, Linux and Android.

A location-based exploration RPG played over LoRa mesh radio

vLLM inference solutions for NVIDIA GB10 (DGX Spark, sm121) — KIMI-K3 B12X_MLA + DSpark, GLM-5.2

A declarative interface for every secret provider.

TaskView is a self-hosted project and task management platform focused on clarity, ownership, and control. TaskView is built for teams that want a transparent, self-hosted alternative to SaaS task …

experiment in performant nvfp4 inference on DGX Spark

LMCache: Supercharge Your LLM with the Fastest KV Cache Layer

Orchestrate multiple coding agents from desktop and mobile

A vLLM patch + hand‑written SM120 SASS kernels: 2‑bit MoE experts + an FP4 "delta" cache that recovers precision — matching the official (NV)FP4 checkpoint's quality on consumer Blackwell cards

The diary of Tom Riddle for the reMarkable Paper Pro — write with your pen, the page drinks your ink and answers in a flowing hand

Dancing Script fonts

Your own search engine

DeepSeek 4 Flash and PRO local inference engine for Metal, CUDA and ROCm

Coder plugin for remote development support in JetBrains Toolbox

Tutel MoE: Optimized Mixture-of-Experts Library, Support GptOss/DeepSeek/Kimi-K2/Qwen3 using FP8/NVFP4/MXFP4

A PyTorch native library for training speculative decoding models

Dynamic Intent Resolution Grounding Engine

Ship correct and fast LLM kernels to PyTorch

General plug-and-play inference library for Recursive Language Models (RLMs), supporting various sandboxes.

htop-like TUI for real-time RDMA network monitoring.

Secure environments for developers and their agents

Backrest is a web UI and orchestrator for restic backup.

Kubernetes (k8s) device plugin to enable registration of AMD GPU to a container cluster