Zelogx™ MSL Setup (Multiverse Secure Lab Setup) – the Multi-tenant Enabler. It automates virtually partitioning a single Proxmox host into secure, SDN+VPN-backed, multi-tenant environments for each…

A minimal, cross-compatible CPU/GPU telemetry monitor with accurate data directly from vendor APIs and beautiful ASCII visualization.

🚀 Open source Claude Code CLI source code. Advanced AI Agent for developers. Includes TypeScript codebase for LLM tool-calling, agentic workflows, and terminal UI. Remember this is just the skeleto…

🚦 Cachet, the open-source, self-hosted status page system.

Official inference framework for 1-bit LLMs

A tiny command line DNS client with support for UDP, TCP, DoT, DoH, DoQ and ODoH.

MacOS App wrapper for Supermicro's IPMIView/iKVM java app

A redesigned desktop interface for HyperHDR with built-in controls and simplified setup.

Cell tower logger and anomaly detector for Linux mobile devices. Monitors cellular connections, logs tower data with GPS, and detects suspicious activity.

Tensor library for machine learning

OpenBLAS is an optimized BLAS library based on GotoBLAS2 1.13 BSD version.

oneAPI Deep Neural Network Library (oneDNN)

ncnn is a high-performance neural network inference framework optimized for the mobile platform

Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

The open source coding agent.

Run frontier AI locally.

Effortless token usage tracker for OpenCode

A modern web-based management interface for ZFS pools, datasets, snapshots, and SMART disk monitoring built with Python FastAPI and HTMX. Runs on Linux, FreeBSD, and NetBSD.

Run Claude Code on OpenAI models

General purpose GPU compute framework built on Vulkan to support 1000s of cross vendor graphics cards (AMD, Qualcomm, NVIDIA & friends). Blazing fast, mobile-enabled, asynchronous and optimized for…

LLM inference in C/C++

AirLLM 70B inference with single 4GB GPU

Headless remote desktop setup for NVIDIA DGX SPARK using Sunshine streaming

Blogpost about building the SCION 25 Gbit/s Workstation

llama.cpp fork with additional SOTA quants and improved performance

The software powering Stoat

Why is this running?

Code for building ConceptNet from raw data.