from vibe coding to agentic engineering - practice makes claude perfect

Lightweight coding agent that runs in your terminal

All-in-One Sandbox for AI Agents that combines Browser, Shell, File, MCP and VSCode Server in a single Docker container.

Fast, small, and fully autonomous AI personal assistant infrastructure, ANY OS, ANY PLATFORM — deploy anywhere, swap anything 🦀

The awesome collection of OpenClaw skills. 5,400+ skills filtered and categorized from the official OpenClaw Skills Registry.🦞

Markdown to WeChat CLI | 一键排版发布到微信公众号：支持 40+ 排版样式和专业主题 、AI 配图 、批量发布

Open-Source Chrome extension for AI-powered web automation. Run multi-agent workflows using your own LLM API key. Alternative to OpenAI Operator.

A compact implementation of SGLang, designed to demystify the complexities of modern LLM serving systems.

Golang deep variable equality test that returns human-readable differences

A beta Dota2 Bot Script aims to provide better bot game experience

Examples and guides for using the Gemini API

Open-source release accompanying Gao et al. 2025

A workload for deploying LLM inference services on Kubernetes

A shim driver allows in-docker nvidia-smi showing correct process list without modify anything

Simple HTTP, REST, and SSE client library for Go

A golang LRU Cache for high concurrency

Democratizing Reinforcement Learning for LLMs

A blazingly fast JSON serializing & deserializing library

A lightweight Kubernetes-compatible container orchestration system written in Rust, implementing the Container Runtime Interface (CRI) with support for single containers, Kubernetes-style pods, and…

The best ChatGPT that $100 can buy.

bpftop provides a dynamic real-time view of running eBPF programs. It displays the average runtime, events per second, and estimated total CPU % for each program.

Open Model Engine (OME) — Kubernetes operator for LLM serving, GPU scheduling, and model lifecycle management. Works with SGLang, vLLM, TensorRT-LLM, and Triton

Large Language Model (LLM) Systems Paper List

Virtualized Elastic KV Cache for Dynamic GPU Sharing and Beyond

The official implementation of OSDI'25 paper BlitzScale

My learning notes for ML SYS.

Examples demonstrating available options to program multiple GPUs in a single node or a cluster

FlexAttention based, minimal vllm-style inference engine for fast Gemma 2 inference.

An extension of the nanoGPT repository for training small MOE models.

Convert PDF to markdown + JSON quickly with high accuracy