A high-throughput and memory-efficient inference and serving engine for LLMs

User-friendly AI Interface (Supports Ollama, OpenAI API, ...)

SkyPilot: Run AI and batch jobs on any infra (Kubernetes or 15+ clouds). Get unified execution, cost savings, and high GPU availability via a simple interface.

A Vault swiss-army knife: A CLI tool to init, unseal and configure Vault (auth methods, secret engines).

Terraform Selectel provider

Container runtimes on macOS (and Linux) with minimal setup

A collection of all my personal cheat sheets and guides as I progress through my career in offensive security.

kro | Kube Resource Orchestrator

Langflow Helm Charts

vLLM’s reference system for K8S-native cluster-wide deployment with community-driven performance optimization

A fast inference library for running LLMs locally on modern consumer-class GPUs

A Gradio web UI for Large Language Models with support for multiple inference backends.

Jupyter Interactive Notebook

Langflow is a powerful tool for building and deploying AI-powered agents and workflows.

Web Application Security Scanner Framework

The ZAP by Checkmarx Core project

Robust Speech Recognition via Large-Scale Weak Supervision

Kubernetes-native security toolkit

A self-extracting archiving tool for Unix systems, in 100% shell script.

Kube Startup CPU Boost is a controller that increases CPU resource requests and limits during Kubernetes workload startup time

Fast linters runner for Go

MII makes low-latency and high-throughput inference possible, powered by DeepSpeed.

SGLang is a fast serving framework for large language models and vision language models.

Flexible SQL Exporter for Prometheus.

Move Kubernetes PVCs between Storage Classes and Namespaces

[CNCF Sandbox Project] Managing your Kubernetes clusters (including public, private, edge, etc.) as easily as visiting the Internet

Fully open reproduction of DeepSeek-R1