Stars
More than a skill manager — manage skills, MCP servers, plugins, hooks, CLIs, configs, memory & rules across every AI coding agent. 🌟 Star if you like it!
《Designing Data-Intensive Application》DDIA 第一版 / 第二版 中文翻译
AI 每日新闻简报 · GitHub 热门 + X 热门文章 + 行情技术分析 · 23 个数据源聚合 + LLM 中文摘要 · 本地或 GitHub Actions 部署
Bash is all you need - A nano claude code–like 「agent harness」, built from 0 to 1
Comprehensive open-source library of AI research and engineering skills for any AI model. Package the skills and your claude code/codex/gemini agent will be an AI research agent with full horsepowe…
General Skills Development Pipeline - Claude Code & Codex
Latency and Memory Analysis of Transformer Models for Training and Inference
Releasing the spot availability traces used in "Can't Be Late" paper.
The LaTeX format for my research statement, which has a right figure column
Puzzles for learning Triton
SGLang is a high-performance serving framework for large language models and multimodal models.
Modern CUDA Learn Notes with PyTorch for Beginners, 200+ CUDA Kernels, Tensor Cores, HGEMM, FA-2 MMA.
RAG - Personal Knowledge Base Assistant
verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework
code for `A Hybrid Human-in-the-Loop Deep Reinforcement Learning Method for UAV Motion Planning'
code for `Autonomous navigation of UAV in multi-obstacle environments based on a Deep Reinforcement Learning approach'
Supplementary source code for the ECRTS 2019 paper 'Response-Time Analysis of ROS 2 Processing Chains under Reservation-Based Scheduling'
A self-tuning anomaly detection system to address the challenges of method selection and hyper-parameter tuning without access to a sufficient number of human supplied, ground truth labels.