An Open-source, self-hosted AI model hub with Hugging Face compatibility, accelerating vLLM/SGLang performance.

Ascend TileLang adapter

A kernel library written in tilelang

Common recipes to run vLLM

Praise The Omnissiah

Community maintained hardware plugin for vLLM on Apple Silicon

The best-benchmarked open-source AI memory system. And it's free.

✈️ Kubernetes-native platform for deploying and managing AI inference across multiple providers

Stateful API logic for agentic applications using vLLM

Client for OpenClaw — Connect ClawWork to your own OpenClaw and unlock 10x multi-session productivity.

Hands-on lab scripts for "When Kubernetes Restarts Your Pod — And When It Doesn't" — ConfigMap sync, Secret rotation, image updates, Istio xDS, in-place resize (K8s 1.35 GA), and Stakater Reloader

⭐AI-driven public opinion & trend monitor with multi-platform aggregation, RSS, and smart alerts.🎯 告别信息过载，你的 AI 舆情监控助手与热点筛选工具！聚合多平台热点 + RSS 订阅，支持关键词精准筛选。AI 智能筛选新闻 + AI 翻译 + AI 分析简报直推手机，也支持接入 MCP 架构…

FlagScale is a large model toolkit based on open-sourced projects.

FlagGems is an operator library for large language models implemented in the Triton Language.

Agent skills for vLLM

Run OpenClaw more securely inside NVIDIA OpenShell with managed inference

my talks/sessions in KubeCon, KCD and other activities.

C-ray — X-ray your containers. See beneath the runtime.

Tooling for optimized, validated, and reproducible GPU-accelerated AI runtime in Kubernetes

The largest open-source medical AI skills library for OpenClaw🦞.

An open-source Collaborative Multi-Agent OS for transparent, human-in-the-loop task coordination via Matrix rooms.

Azure SRE Agent is an AI-powered reliability assistant that helps teams diagnose and resolve production issues, reduce operational toil, and lower mean time to resolution

The Coordination Layer for Multi-Agent AI