init to record my learning path of AI Infra, especially on inference.

Learn it. Build it. Ship it for others.

Moved to Codeberg

Kepler (Kubernetes-based Efficient Power Level Exporter) is a Prometheus exporter that measures energy consumption metrics at the container, pod, and node levels in Kubernetes clusters.

Go wrapper around iptables utility

A Git-compatible VCS that is both simple and powerful

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

Instant K8s service dependency map, right to your Grafana.

agent-sandbox enables easy management of isolated, stateful, singleton workloads, ideal for use cases like AI agent runtimes.

Build your own AI SRE agents. The open source toolkit for the AI era.

Node feature discovery for Kubernetes

Writing an OS in 1,000 lines.

Automatically set GOMEMLIMIT to match Linux cgroups(7) memory limit.

SSH server docker container

kubectl plugin to gain access to a node - you need to be able start priviledged pods with host pid

Kubectl Plugin to make ssh'ing into your nodes faster

A kubectl plugin to access nodes or remote services using a SSH jump Pod

A Go framework for end-to-end testing of components running in Kubernetes clusters.

P2P Docker registry capable of distributing TBs of data in seconds

External-DNS Plugin to manage EfficientIP's SOLIDserver DNS Records

minimalistic Kubernetes network plugin that just works

Load Balancing as a Service (LBaaS) for OpenStack. Mirror of code maintained at opendev.org.

Load balancing service for OpenStack

Community-Driven Thanos Charts 💪

Metrics dashboards on terminal (a grafana inspired terminal version)