Learning

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

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

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

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

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

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

It catalogs legitimate services offering free API access to large language models, complete with rate limits, model lists, and data-privacy caveats.

Official Jupyter notebooks demonstrating how to wire Claude into production tasks like RAG, SQL queries, and multimodal pipelines.

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

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

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.

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

A crowdsourced archive of leaked and reverse-engineered system prompts that exposes the hidden scaffolding behind major AI models and agents.

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.

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

Open-sources the exact LLM prompts and agent skills that researchers at MSRA, ByteDance Seed, and top Chinese universities use to write and polish papers.

This repo exists to sort the scattered open-source AI agent ecosystem into an industry-by-industry directory, saving you from GitHub search purgatory.

To stop developers from reinventing agent basics by providing 52+ runnable notebooks spanning conversational bots to multi-agent systems.

A free, 26-lesson curriculum marches beginners through classic machine learning the old-fashioned way: with homework, quizzes, and Scikit-learn.