原汁原昧 Claude Code 可运行,可构建, 可调试版; 生产级工程化, 企业级可靠性; 安全无毒, 内存泄露修复

降效插件集合，降低 Claude Code Agent 工作效率的行为艺术插件。目前支持 ADHD 及 ASD 模式。A collection of anti-productivity skills for Claude Code. Currently ships with ADHD and ASD mode. More chaos coming soon.

Universal memory layer for AI Agents

Make Any Website into CLI & Use your logged-in browser by AI agent.

Collection of Composed Image Retrieval (CIR) papers.

Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.

[Up-to-date] Large Language Model Agent: A Survey on Methodology, Applications and Challenges

📚 《从零开始构建智能体》——从零开始的智能体原理与实践教程

A structured curriculum for understanding Anthropic’s Claude Code (CLI agent) implementation, grounded in a large TypeScript source snapshot

将冰冷的离别化为温暖的 Skill，欢迎加入数字生命1.0！Transforming cold farewells into warm skills? It's giving rebirth era. Welcome to Digital Life 1.0. 🫶

A KV storage engine based on LSM Tree, supporting Redis RESP

A Vector Database Tutorial (over CMU-DB's BusTub system)

A course of learning LLM inference serving on Apple Silicon for systems engineers: build a tiny vLLM + Qwen.

Bitcoin Core integration/staging tree

🎯 从零入门RDMA开发！最简洁的双节点示例代码，涵盖CM建链、Verbs收发、远程读写等核心功能。专为C++新手设计，30分钟快速上手高性能网络编程。包含完整API流程解析和实战指南。

🚀 QQ聊天记录、表情包导出工具 | 自动化提取图片/文字/图片消息，支持TXT/JSON导出，高效备份，支持NT QQ

Source code of our SIGMOD 2025 paper "Athena: An Effective Learning-based Framework for Query Optimizer Performance Improvement"

MineContext is your proactive context-aware AI partner（Context-Engineering+ChatGPT Pulse）

Cost-efficient and pluggable Infrastructure components for GenAI inference

LMCache: Supercharge Your LLM with the Fastest KV Cache Layer

🚀🚀🚀 This repository lists some awesome public CUDA, cuda-python, cuBLAS, cuDNN, CUTLASS, TensorRT, TensorRT-LLM, Triton, TVM, MLIR, PTX and High Performance Computing (HPC) projects.

A tutorial on RDMA based programming using code examples

[VLDB 2024] DEX: Scalable Range Indexing on Disaggregated Memory

Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings

Exploring the impact of long-term memory in generative AI

GTP engine and self-play learning in Go

CUDA 算子手撕与面试指南

[EMNLP 2025 Demo] PDF scientific paper translation with preserved formats - 基于 AI 完整保留排版的 PDF 文档全文双语翻译，支持 Google/DeepL/Ollama/OpenAI 等服务，提供 CLI/GUI/MCP/Docker/Zotero

Nano vLLM