Ross ROSS = Recommend OSS · open-source software intelligence for agents

HanLP

中文分词 词性标注 命名实体识别 依存句法分析 成分句法分析 语义依存分析 语义角色标注 指代消解 风格转换 语义相似度 新词发现 关键词短语提取 自动摘要 文本分类聚类 拼音简繁转换 自然语言处理 observed · 2026-10-16

github.com/hankcs/HanLP · homepage · Python · Apache-2.0 (permissive) observed · 2026-10-16

Health v2 · maintenance only

77/100

  • Activity 95
  • Release rhythm 40
  • Longevity 100
How is this computed?

round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-10-21. Adoption (stars, forks) is never an input.

  • gap_med: 15
  • age_days: 4394
  • days_rel: 646
  • days_push: 35
  • n_releases_24m: 4

Full methodology

Adoption not part of the score

36510 stars · 10884 forks observed · 2026-10-16

What it is AI-extracted, prompt v1, taxonomy v1, 2026-09-28, confidence 0.97

HanLP is a multilingual natural language processing library for Python, offering a wide range of NLP tasks such as tokenization, POS tagging, NER, parsing, and text classification. It provides pretrained models built on PyTorch and TensorFlow and is designed for production use.

Use cases

  • perform Chinese word segmentation and tokenization
  • extract named entities from multilingual text
  • parse dependency trees for sentences in Chinese, English, Japanese, etc.
  • classify documents or short texts in Chinese
  • convert between simplified and traditional Chinese characters
  • generate summaries of Chinese articles

When to choose

  • You need a production‑ready, high‑accuracy NLP toolkit with multilingual support.
  • You prefer a Python library that offers both PyTorch and TensorFlow back‑ends.
  • You want ready‑to‑use pretrained models for a variety of tasks without training from scratch.

When to avoid

  • You require a lightweight, rule‑based solution with minimal dependencies.
  • Your project is not in Python and cannot use the provided bindings.
  • You have very limited hardware and cannot run the larger deep‑learning models.

Facets

library · maturity active

parser nlp artificial-intelligence machine-learning python windows cross-platform multilingual deep-learning pretrained-models tokenization pos-tagging named-entity-recognition dependency-parsing constituency-parsing semantic-role-labeling amr gpu-acceleration text-classification natural-language-processing linux macos

7 sources

Member repositories

RepositoryRoleHealth v2
hankcs/HanLPmain77
hankcs/pyhanlpsdk23

For agents

markdown · JSON · MCP: product_card(name="hankcs/HanLP")

Data as of 2026-10-19T08:05:51.212177+00:00 · Report a problem