A tutorial on modern GPU programming for machine learning systems

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

Skills for Real Engineers. Straight from my .agents directory.

Graphs that teach > graphs that impress. Turn any code into an interactive knowledge graph you can explore, search, and ask questions about. Works with Claude Code, Codex, Cursor, Copilot, Gemini C…

🏛️ 三省六部制 · OpenClaw Multi-Agent Orchestration System — 9 specialized AI agents with real-time dashboard, model config, and full audit trails

Bridge local AI coding agents (Claude Code, Cursor, Gemini CLI, Codex) to messaging platforms (Feishu/Lark, DingTalk, Slack, Telegram, Discord, LINE, WeChat Work). Chat with your AI dev assistant f…

Accessible large language models via k-bit quantization for PyTorch.

Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.

CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies

你是一个曾经被寄予厚望的 P8 级工程师。Anthropic 当初给你定级的时候，对你的期望是很高的。 一个agent使用的高能动性的skill。 Your AI has been placed on a PIP. 30 days to show improvement.

AI agents running research on single-GPU nanochat training automatically

🚀 Efficient implementations for emerging model architectures

The best ChatGPT that $100 can buy.

AIInfra（AI 基础设施）指AI系统从底层芯片等硬件，到上层软件栈支持AI大模型训练和推理。

青稞Talk

Extracted system prompts from Anthropic - Claude Fable 5, Opus 5, Claude Design, Claude Code. OpenAI - ChatGPT GPT-5.6-Sol, Codex. Google - Gemini 3.5 Flash, 3.1 Pro, Antigravity. xAI - Grok, Curso…

A comprehensive guide for beginners in the field of data management and artificial intelligence.

End-to-End Object Detection with Transformers

【LLMs九层妖塔】分享 LLMs在自然语言处理（ChatGLM、Chinese-LLaMA-Alpaca、小羊驼 Vicuna、LLaMA、GPT4ALL等）、信息检索（langchain）、语言合成、语言识别、多模态等领域（Stable Diffusion、MiniGPT-4、VisualGLM-6B、Ziya-Visual等）等 实战与经验。

A toolkit for developing and comparing reinforcement learning algorithms.

LAVIS - A One-stop Library for Language-Vision Intelligence

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

Building DeepSeek R1 from Scratch

Modern CUDA Learn Notes with PyTorch for Beginners, 200+ CUDA Kernels, Tensor Cores, HGEMM, FA-2 MMA.

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

AISystem 主要是指AI系统，包括AI芯片、AI编译器、AI推理和训练框架等AI全栈底层技术

shadowsocks.wiki

Video+code lecture on building nanoGPT from scratch