A crowdsourced archive of leaked and reverse-engineered system prompts that exposes the hidden scaffolding behind major AI models and agents.
Learning
big names · picking up speedBecause the official docs list features, but never show you how to chain them into a production workflow.
A curated field guide for turning Claude Code from a chatty assistant into a repeatable engineering agent.
Why rebuild the same RAG pipeline or agent loop from scratch when you can fork a working template instead?
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.
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.
A curated index of OpenClaw skills, minus the spam, duplicates, and malware.
This repo exists to sort the scattered open-source AI agent ecosystem into an industry-by-industry directory, saving you from GitHub search purgatory.
Because 'just ask nicely' is not a production strategy, this is a curated, living reference for systematic LLM prompting.
The official hands-on curriculum for Google's Gemini API, delivered as executable notebooks.
It maps the sprawling machine learning landscape onto a single, topic-nested page of hyperlinks.
A curated knowledge base covering the full LLM lifecycle—from 65B-parameter fine-tuning on consumer GPUs to deployment and domestic Chinese hardware adaptation.
Anthropic published a hands-on, notebook-based course that teaches prompt engineering using its cheapest Claude model.
A curated directory of software, plugins, and frameworks that integrate with the DeepSeek API, maintained by DeepSeek itself.
A systematic Chinese tutorial for developers who want to stop treating LLMs as black boxes and hand-build a 215-million-parameter model from the ground up.
To teach developers agent engineering from scratch using smolagents, LangGraph, and LlamaIndex, capped by an automated benchmark.
Official Python notebooks and guides for common OpenAI API tasks.
It corrals over 90 free courses, paper roundups, interview prep, and roadmaps into one sprawling LLM curriculum.
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.



