Learning

This curriculum closes the gap between calling AI APIs and understanding the loss curves underneath.

Because the official docs list features, but never show you how to chain them into a production workflow.

This repo open-sources a full Chinese textbook on AI agent engineering—complete with Markdown source, compiled PDF, and runnable Python demos for every chapter.

Hello-Agents is a free, 16-chapter curriculum that teaches developers to construct truly AI-driven agents from first principles rather than wiring no-code workflows.

To turn graduate-level NLP and AI safety lectures into runnable Jupyter notebooks that anyone can break, watermark, or align.

Why rebuild the same RAG pipeline or agent loop from scratch when you can fork a working template instead?

A course on building the structural harnesses—state tracking, verification, and scope limits—that prevent smart AI coding agents from breaking your codebase and calling it done.

This repo exists because the LLM learning curve is a scattered mess of blog posts, so it organizes the field into three distinct tracks—fundamentals, scientist, and engineer—each paired with runnable Colab notebooks.

It exists to teach developers how to build generative AI applications through 21 modular lessons that mix conceptual explainers with working Python and TypeScript code.

A free, end-to-end ML systems curriculum that treats the repository itself as the course — textbook, build-your-own framework, hardware kits, simulator, and interview prep included.

A curated registry of reusable instruction packages that keep Claude and other agents from reinventing the wheel on every task.

It teaches how LLMs work by implementing tokenization, attention, pretraining, and finetuning in pure PyTorch, one notebook at a time.

MiniMind is an educational training ground that rebuilds every stage of a modern language model—from tokenizer to RLHF—in raw PyTorch so you can see the gears turning instead of just calling high-level APIs.

To teach agentic design patterns through videos, notebooks, and documentation auto-translated into more than 50 languages.

It collects official skill definitions from engineering teams so AI agents don't have to improvise.

A curated field guide for turning Claude Code from a chatty assistant into a repeatable engineering agent.

A living archive of extracted system prompts from Anthropic, OpenAI, Google, and xAI that exposes the hidden instructions shaping tone, tools, and guardrails.

A community knowledge base that reverse-engineers hundreds of GPT-Image2 examples into structured, agent-ready prompt protocols.

It collects copy-paste role-play prompts that cast ChatGPT as a Linux terminal, proofreader, or interviewer for Chinese-speaking users.

A structured 12-week curriculum that teaches symbolic AI, neural nets, and even genetic algorithms—without pretending deep math or cloud ML don't exist.