Trending AI & Machine Learning repositories

The foundation layer. Language models, training frameworks, inference servers, embedding pipelines, evaluation kits, fine-tuning toolchains, and the supporting infrastructure that makes those things deployable. The /best/open-source-llms page is the curated top-N; this is the wide cut, mixing model releases, library releases, and infrastructure releases on equal footing because teams adopt them as a stack. Frontier weight drops spike every signal source in the same 48 hours, then settle. Quieter projects — inference servers, evaluation suites, RAG toolkits — hold position more durably than the spike curve suggests. The score weights long-tail engagement so both shapes rank in their right relative position. When picking what to invest in, the things that matter: licence terms on weights versus source (the two often differ — a permissive repo licence doesn't mean permissive weights), evaluation methodology (open leaderboards lie about what you'll see in production), and the maintainer's track record on minor versions.