Learning

An opinionated todo list that drags AI agent development from demo culture back to software engineering.

It packages a professor's decade of SIGMOD and NeurIPS experience into structured AI skills, bridging the 'last-mile' gap where generic guides and busy advisors leave grad students stranded.

A Claude Code skill that turns blind copy-pasting into structured lessons on what you’re about to ship.

A self-contained course on the harness engineering that gives LLMs state, action, and limits, dissected across 24 sections and three real systems.

It reverse-engineers Pi Agent into a progressive, hands-on TypeScript course for Chinese developers.

It exists to replace 'formula first, API later' with broken experiments that teach you why PPO actually works.

An open-source Chinese curriculum that tries to bridge the chasm between LangChain demos and production-grade agent systems.

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

Curated examples and notebooks for running Liquid AI's open-weight LFMs on desktop, browser, mobile, and edge hardware without treating on-device inference as an afterthought.

An open-source curriculum for the Forward Deployment Engineer, the hybrid role that ships complex AI and data systems into hostile, real-world client environments.

Someone had to catalog the explosion of tools trying to herd AI coding agents in parallel.

An open-source field guide that teaches WorkBuddy through real jobs, not feature lists.

A Jupyter Book that rebuilds classic algorithms in NumPy and shows you the math actually working.

This curated list maps the chaotic AI-security tooling landscape—from triage bots to MCP scanners—with a color-coded honesty system that separates open source from commercial hybrids and restrictive researchware.

A curated learning path that collects step-by-step explainers on the math and engineering behind modern LLMs, from tokenization to inference optimization.

It maps the sprawling landscape of AI tools that promise to automate every stage of modern research, from literature review to slide deck.

A systematic, open-source knowledge base that closes the gap between scattered CUDA tutorials and actual AI infrastructure engineering.

An open library of 165 agent skills that grounds AI lesson planning, assessment design, and live tutoring in named research instead of classroom folklore.

It turns scattered AI agent prompts into a browsable, installable inventory that refreshes itself daily.

Because Karpathy's autoresearch demo spawned an entire ecosystem of recursive agents, and the community needed a field guide.