Learning

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.

Organizes 411 free AI resources into actual learning paths, because bookmarking isn't studying.

Pairs a 424-page textbook with Jupyter notebooks to teach AI agent design patterns.

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.

It packages a sprawling traditional Chinese medicine video curriculum into an agent skill so Claude can retrieve formulas, acupoints, and lecture screenshots by plain-language symptom instead of improvising.

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

A curated directory of over 200 agentic AI projects arguing that workflow beats raw model size.

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.

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

A curated field manual for adversarial-testing AI systems—from LLM prompt injection to autonomous-agent RCE—before attackers get there first.

It catalogs the growing ecosystem of skills, tools, and integrations for Nous Research’s self-improving Hermes Agent.

Because nobody has time to read every paper from NeurIPS, CVPR, and ACL.

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

A curated reading list and pattern library for the unglamorous infrastructure that keeps AI agents reliable and on-task.

Curated technical deep-dives covering everything from NVLink signal integrity to Kubernetes GPU scheduling and Huawei NPU porting.

Engram exists because a brilliant AI explanation is worthless if you can't recall it next month.

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

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

A tutorial that reverse-engineers Claude Code's core architecture in ~4,300 lines so you don't have to read half a million.

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