kubernetes-website Kubernetes website and documentation repo:

kueue Kubernetes-native Job Queueing

litellm Python SDK, Proxy Server (AI Gateway) to call 100+ LLM APIs in OpenAI (or native) format, with cost tracking, guardrails, loadbalancing and logging. [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, VLLM, NVIDIA NIM]

llm-d llm-d is a Kubernetes-native high-performance distributed LLM inference framework

llm-d-deployer Helm charts for llm-d

llm-d-kv-cache-manager Distributed KV cache coordinator

llm-d-modelservice helm charts for deploying models with llm-d

llm-d.github.io Website for llm-d: This repository builds the website seen at llm-d.ai

LMCache Redis for LLMs

matrixhub

mirrormate One-shot mirror injection for Docker builds and compose workflows.

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

openclaw-gateway-tunnel A zero-dependency openclaw plugin that exposes the local gateway to the public internet via ngrok's embedded Node SDK. Design phase, seeking feedback.

opencode The open source coding agent.

plano Ship agents faster. Plano is delivery infrastructure for agentic applications. A models-native proxy server & dataplane that offloads the plumbing work, so you stay focused on product logic.

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

prom-etl-db A Go-based ETL tool that collects Prometheus metrics and stores them in MySQL database with scheduled execution.

public-image-mirror 很多镜像都在国外。比如 gcr 。国内下载很慢，需要加速。

rbg A workload for deploying LLM inference services on Kubernetes

remove-image-navbar

RouterArena RouterArena: An open framework for evaluating LLM routers with standardized datasets, metrics, an automated framework, and a live leaderboard.

routeworks.github.io Website for RouterArena

samzong.github.io Work, and reflections on life. Explore cloud native, share experiences, contemplate life.

semantic-router Intelligent Mixture-of-Models Router for Efficient LLM Inference

sgl-ome OME is a Kubernetes operator for enterprise-grade management and serving of Large Language Models (LLMs)

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

ShiArthur03-backup

spiderpool Underlay and RDMA network solution of the Kubernetes, for bare metal, VM and any public cloud

training-sample-code learn and try with tensorflow and pytorch

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