Repolode
Submit
taishi-i

taishi-i/awesome-japanese-nlp-resources

A curated list of Japanese NLP resources covering Python libraries, LLMs, dictionaries, corpora and datasets, plus Claude Code and Codex skills for searching them.

View on GitHubWebsite
Stars
1,027
Forks
59
Open issues
4
Last commit
4 days ago

What is it?

This is a curated directory of open-source resources for Japanese natural language processing. It organizes entries by language and task, including Python, C++, Rust, JavaScript, Go and Java libraries for morphological analysis, parsing, character conversion, preprocessing, sentence splitting, sentiment analysis, machine translation, named entity recognition and OCR. It also lists pretrained models, LLM evaluation tools, dictionaries and IMEs, and corpora such as parallel and dialog data.

Beyond the lists, the repository tracks related Hugging Face models and datasets, and includes multilingual resources that also support Japanese. Many entries show weekly downloads, total downloads, stars and last commit date to help compare maintenance status.

The repository also ships a plugin for Claude Code and Codex with four skills: search, discover, compare and research. These let users query the bundled dataset, find alternatives to a tool, or generate comparison tables and trend reports.

Key features

  • 01Categorized lists of Japanese NLP libraries across many languages and tasks
  • 02Download counts, stars and last-commit dates shown for many entries
  • 03Links to related Hugging Face models and datasets
  • 04Pretrained models, LLM evaluation tools and Japanese corpora
  • 05Claude Code and Codex plugin with search, discover, compare and research skills

Use cases

  • Finding a Japanese tokenizer or morphological analyzer for a project
  • Choosing a Japanese OCR tool for manga or documents
  • Locating datasets and pretrained models for Japanese NLP research
  • Comparing maintenance status of candidate libraries before adopting one

Quick start

  1. 1

    Add the Claude Code plugin marketplace

    /plugin marketplace add taishi-i/awesome-japanese-nlp-resources
  2. 2

    Install the plugin in Claude Code

    /plugin install awesome-japanese-nlp-resources@awesome-japanese-nlp-resources
  3. 3

    Reload plugins and run a search skill

    /reload-plugins

Things to know

  • The skills require Claude Code or Codex to run.

In collections

AI agent skill librariesPDF, OCR & document toolsNatural language processing tools & libraries

Topics

#japanese#nlp#awesome-list#llm#tokenizer#corpus#dataset#ocr#agent-skills#awesome

FAQ

What is awesome-japanese-nlp-resources?
A curated list of Japanese NLP resources covering Python libraries, LLMs, dictionaries, corpora and datasets, plus Claude Code and Codex skills for searching them. This is a curated directory of open-source resources for Japanese natural language processing. It organizes entries by language and task, including Python, C++, Rust, JavaScript, Go and Java libraries for morphological analysis, parsing, character conversion, preprocessing, sentence splitting, sentiment analysis, machine translation, named entity recognition and OCR. It also lists pretrained models, LLM evaluation tools, dictionaries and IMEs, and corpora such as parallel and dialog data.
Is awesome-japanese-nlp-resources free to use? What license does it have?
awesome-japanese-nlp-resources is open source under the CC0-1.0 license. Check the license terms before using it in commercial products.
Is awesome-japanese-nlp-resources still maintained?
Actively maintained. The last commit to awesome-japanese-nlp-resources was on Nov 2, 2026.
What can I use awesome-japanese-nlp-resources for?
Finding a Japanese tokenizer or morphological analyzer for a project Choosing a Japanese OCR tool for manga or documents Locating datasets and pretrained models for Japanese NLP research Comparing maintenance status of candidate libraries before adopting one
How do I install awesome-japanese-nlp-resources?
Add the Claude Code plugin marketplace: /plugin marketplace add taishi-i/awesome-japanese-nlp-resources Install the plugin in Claude Code: /plugin install awesome-japanese-nlp-resources@awesome-japanese-nlp-resources Reload plugins and run a search skill: /reload-plugins
Where can I get awesome-japanese-nlp-resources?
The source code and installation instructions are on GitHub: https://github.com/taishi-i/awesome-japanese-nlp-resources

Summary generated by AI from the project's README. GitHub stats refresh daily.

Related projects