awesome-japanese-nlp-resources

Why we included this project

Japanese text processing has its own tooling, and most English-first resource lists skip most of it. This curated index collects the pieces that actually matter for that ecosystem, from Python libraries and pretrained models to dictionaries and corpora, spread across hundreds of GitHub repositories and Hugging Face entries. The Claude Code skills bundled with the project are the more interesting part: you can search the dataset, ask for resources similar to a tool you already use, or have it hunt for repos and models that are not listed yet. That makes it a practical starting point when you are scoping a Japanese NLP project and want to know which libraries and models are worth trying first.