What I learned from looking at 900 most popular open source AI tools

Chip Huyen analyzed 896 open source AI repos (845 software) to map the modern AI stack into three layers: infrastructure, model development, and application. The analysis reveals the dominant tool categories — including agent frameworks, RAG pipelines, code assistants, and evaluation tools — and highlights how rapidly the ecosystem has grown (now 15K repos). Key findings include the prevalence of Python, the dominance of certain architectural patterns like RAG, and notable divergence between Western and Chinese open source ecosystems.