1.Automattic / harper
Offline, privacy-first grammar checker. Fast, open-source, Rust-powered
- developer-tools
- english-language
- grammar-checker
- rust
- webassembly
- chrome-extension
- +3 more
+7,122 stars
from 10,291 · score 8.87
Trending repositories
Ranked by Attention Score: stars gained over the last 180 complete days
72 repositories by Attention Score · May 9, 2026 – Nov 4, 2026 (UTC)
2.openai / tiktoken
tiktoken is a fast BPE tokeniser for use with OpenAI's models.
+1,588 stars
from 18,017 · score 7.37
3.languagetool-org / languagetool
Style and Grammar Checker for 25+ Languages
- grammar
- natural-language
- natural-language-processing
- style-checker
- proofreading
- spellcheck
+881 stars
from 14,354 · score 6.78
4.argosopentech / argos-translate
Open-source offline translation library written in Python
- python
- machine-translation
- transformers
- translation
- language-models
- linux
- +2 more
+733 stars
from 5,892 · score 6.60
5.explosion / spaCy
💫 Industrial-strength Natural Language Processing (NLP) in Python
- natural-language-processing
- data-science
- machine-learning
- python
- cython
- nlp
- +11 more
+635 stars
from 33,387 · score 6.46
6.karpathy / minbpe
Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.
+596 stars
from 10,413 · score 6.39
7.huggingface / tokenizers
💥 Fast State-of-the-Art Tokenizers optimized for Research and Production
- nlp
- natural-language-processing
- natural-language-understanding
- language-model
- transformers
- bert
- +1 more
+586 stars
from 10,634 · score 6.38
8.huggingface / transformers.js
State-of-the-art Machine Learning for the web. Run 🤗 Transformers directly in your browser, with no need for a server!
- browser
- javascript
- transformers
- webml
+568 stars
from 15,832 · score 6.34
9.fxsjy / jieba
TranslatedJieba (结巴, "stutter") Chinese word segmentation
+471 stars
from 34,758 · score 6.16
10.hankcs / HanLP
TranslatedChinese word segmentation, part-of-speech tagging, named entity recognition, dependency parsing, constituency parsing, semantic dependency parsing, semantic role labeling, coreference resolution, style transfer, semantic similarity, new word discovery, keyword and keyphrase extraction, automatic summarization, text classification and clustering, pinyin and Simplified/Traditional Chinese conversion, natural language processing
- nlp
- natural-language-processing
- hanlp
- pos-tagging
- dependency-parser
- text-classification
- +2 more
+427 stars
from 36,108 · score 6.06
11.google / sentencepiece
Unsupervised text tokenizer for Neural Network-based text generation.
- neural-machine-translation
- natural-language-processing
- word-segmentation
+414 stars
from 11,751 · score 6.03
12.nltk / nltk
NLTK Source
+238 stars
from 14,529 · score 5.48
13.microsoft / unilm
Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities
- nlp
- pre-trained-model
- unilm
- minilm
- layoutlm
- layoutxlm
- +14 more
+218 stars
from 22,021 · score 5.39
14.facebookresearch / fairseqArchived
Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
+161 stars
from 32,050 · score 5.09
15.piskvorky / gensim
Topic Modelling for Humans
- gensim
- topic-modeling
- information-retrieval
- machine-learning
- natural-language-processing
- nlp
- +9 more
+161 stars
from 16,350 · score 5.09
16.stanfordnlp / stanza
Stanford NLP Python library for tokenization, sentence segmentation, NER, and parsing of many human languages
+158 stars
from 7,748 · score 5.07
17.karpathy / char-rnn
Multi-layer Recurrent Neural Networks (LSTM, GRU, RNN) for character-level language models in Torch
+143 stars
from 11,990 · score 4.97
18.PaddlePaddle / PaddleNLP
Easy-to-use and powerful LLM and SLM library with awesome model zoo.
- nlp
- embedding
- bert
- ernie
- paddlenlp
- pretrained-models
- +13 more
+130 stars
from 12,857 · score 4.88
19.cjhutto / vaderSentiment
VADER Sentiment Analysis. VADER (Valence Aware Dictionary and sEntiment Reasoner) is a lexicon and rule-based sentiment analysis tool that is specifically attuned to sentiments expressed in social media, and works well on texts from other domains.
+127 stars
from 4,963 · score 4.85
20.spencermountain / compromise
modest natural-language processing
- nlp
- part-of-speech
- named-entity-recognition
+117 stars
from 12,054 · score 4.77
21.mozillazg / python-pinyin
TranslatedChinese characters to pinyin converter (pypinyin)
- python
- pinyin
- pypinyin
- hanzi
- hanzi-pinyin
- python2
- +2 more
+109 stars
from 5,281 · score 4.70
22.facebookresearch / fastTextArchived
Library for fast text representation and classification.
+100 stars
from 26,413 · score 4.62
23.stanfordnlp / CoreNLP
CoreNLP: A Java suite of core NLP tools for tokenization, sentence segmentation, NER, parsing, coreference, sentiment analysis, etc.
- natural-language-processing
- nlp
- nlp-parsing
- named-entity-recognition
- stanford-nlp
+91 stars
from 10,035 · score 4.52
24.flairNLP / flair
A very simple framework for state-of-the-art Natural Language Processing (NLP)
+82 stars
from 14,315 · score 4.42
25.tensorflow / tfjs-models
Pretrained models for TensorFlow.js
+80 stars
from 14,731 · score 4.39
26.fnnx-ai / scikit-llm
Seamlessly integrate LLMs into scikit-learn.
+63 stars
from 3,476 · score 4.16
+61 stars
from 600 · score 4.13
28.allenai / scispacy
A full spaCy pipeline and models for scientific/biomedical documents.
- scientific-documents
- spacy
- custom-pipes
- nlp
- biomedical
- bioinformatics
+59 stars
from 1,940 · score 4.09
29.go-ego / gse
Go efficient fast multilingual NLP and text segmentation; support English, Chinese, Japanese and others.
- go
- segment
- nlp
- gse
- hmm
- jieba
- +5 more
+55 stars
from 2,792 · score 4.03
+51 stars
from 5,056 · score 3.95
31.JohnSnowLabs / spark-nlp
State of the Art Natural Language Processing
- nlp
- natural-language-processing
- spark
- pyspark
- named-entity-recognition
- sentiment-analysis
- +14 more
+48 stars
from 4,112 · score 3.89
32.capitalone / DataProfiler
What's in your data? Extract schema, statistics and entities from datasets
- python
- privacy
- pii
- npi
- nlp
- data-science
- +14 more
+48 stars
from 1,547 · score 3.89
33.axa-group / nlp.js
An NLP library for building bots, with entity extraction, sentiment analysis, automatic language identify, and so more
- nlp
- nlu
- nodejs
- sentiment-analysis
- natural-language-processing
- bot
- +7 more
+46 stars
from 6,531 · score 3.85
34.wooorm / franc
Natural language detection
+40 stars
from 4,379 · score 3.71
+39 stars
from 10,843 · score 3.69
36.bootphon / phonemizer
Simple text to phones converter for multiple languages
+39 stars
from 1,538 · score 3.69
37.pemistahl / lingua-go
The most accurate natural language detection library for Go, suitable for short text and mixed-language text
- natural-language-processing
- language-detection
- language-recognition
- language-classification
- language-identification
- language-processing
- +6 more
+38 stars
from 1,331 · score 3.66
38.allenai / allennlpArchived
An open-source NLP research library, built on PyTorch.
+37 stars
from 11,848 · score 3.64
39.miso-belica / sumy
Module for automatic summarization of text documents and HTML pages.
- python
- lsa
- textteaser
- html-page
- summarizer
- pagerank-algorithm
- +8 more
+36 stars
from 3,664 · score 3.61
40.clips / pattern
Web mining module for Python, with tools for scraping, natural language processing, machine learning, network analysis and visualization.
- python
- machine-learning
- natural-language-processing
- web-mining
- wordnet
- sentiment-analysis
- +1 more
+35 stars
from 8,821 · score 3.58
41.life4 / textdistance
📐 Compute distance between sequences. 30+ algorithms, pure python implementation, common interface, optional external libs usage.
- distance
- algorithm
- python
- textdistance
- hamming-distance
- levenshtein-distance
- +7 more
+34 stars
from 3,512 · score 3.56
42.mozillazg / go-pinyin
TranslatedConvert Chinese characters to pinyin
- go
- pinyin
- golang
- hanzi
- hanzi-pinyin
- chinese
+32 stars
from 1,764 · score 3.50
43.kbastani / graphifyArchived
Graphify is a Neo4j unmanaged extension used for document and text classification using graph-based hierarchical pattern recognition.
+32 stars
from 419 · score 3.50
44.dmis-lab / biobert
Bioinformatics'2020: BioBERT: a pre-trained biomedical language representation model for biomedical text mining
+28 stars
from 2,187 · score 3.37
45.keras-team / keras-hub
Pretrained model hub for Keras 3.
+28 stars
from 968 · score 3.37
46.cltk / cltk
The Classical Language Toolkit
+26 stars
from 903 · score 3.30
47.ikawaha / kagome
Self-contained Japanese Morphological Analyzer written in pure Go
- japanese
- tokenizer
- nlp-library
- japanese-language
- pos-tagging
- segmentation
- +3 more
+24 stars
from 963 · score 3.22
48.facebookresearch / ParlAIArchived
A framework for training and evaluating AI models on a variety of openly available dialogue datasets.
+21 stars
from 10,595 · score 3.09
49.quanteda / quanteda
An R package for the Quantitative Analysis of Textual Data
- r
- text-analytics
- natural-language-processing
- corpus
- quanteda
+18 stars
from 877 · score 2.94
50.curiosity-ai / catalyst
🚀 Catalyst is a C# Natural Language Processing library built for speed. Inspired by spaCy's design, it brings pre-trained models, out-of-the box support for training word and document embeddings, and flexible entity recognition models.
+18 stars
from 843 · score 2.94
51.jpmckinney / tf-idf-similarity
Ruby gem to calculate the similarity between texts using tf*idf
+18 stars
from 774 · score 2.94
52.derek73 / python-nameparser
Parse human names into title, given, middle, family, suffix, nickname and maiden name. Typed, zero-dependency, CJK-aware.
- python
- text-processing
- text-parser
- python-module
- cjk
- name-parsing
- +5 more
+17 stars
from 703 · score 2.89
53.abadojack / whatlanggo
Natural language detection library for Go
+15 stars
from 682 · score 2.77
54.retextjs / retext
natural language processor powered by plugins part of the @unifiedjs collective
- natural-language
- ast
- retext
- cst
- javascript
- unified
+13 stars
from 2,420 · score 2.64
55.nlpodyssey / spago
Self-contained Machine Learning and Natural Language Processing library in Go
- deep-learning
- machine-learning
- natural-language-processing
- neural-network
- computation-graph
- automatic-differentiation
- +13 more
+12 stars
from 1,841 · score 2.56
+10 stars
from 3,244 · score 2.40
57.olebedev / when
A natural language date/time parser with pluggable rules
- natural-language
- datetime
- date
- time
- parser
- golang
+10 stars
from 1,454 · score 2.40
58.fukuball / jieba-php
Translated"Jieba" (Chinese for "to stutter") Chinese text segmentation: built to be the best PHP Chinese word segmentation module.
- nlp
- natural-language-processing
- chinese-text-segmentation
- machine-learning
+10 stars
from 1,368 · score 2.40
59.simplenlg / simplenlg
Java API for Natural Language Generation. Originally developed by Ehud Reiter at the University of Aberdeen’s Department of Computing Science and co-founder of Arria NLG. This git repo is the official SimpleNLG version.
- simplenlg
- natural-language-generation
- nlg
- realiser
- surface-realiser
- java
- +1 more
+10 stars
from 823 · score 2.40
60.MihaiValentin / lunr-languages
A collection of languages stemmers and stopwords for Lunr Javascript library
- lunr-languages
- stemmer
- stopwords
- lunr
- localization
- language-stemmer
+10 stars
from 449 · score 2.40
61.asyml / texar
Toolkit for Machine Learning, Natural Language Processing, and Text Generation, in TensorFlow. This is part of the CASL project: http://casl-project.ai/
- machine-learning
- natural-language-processing
- tensorflow
- deep-learning
- text-generation
- python
- +9 more
+9 stars
from 2,384 · score 2.30
62.meta-toolkit / meta
A Modern C++ Data Sciences Toolkit
- nlp
- nlp-parsing
- search-engine
- inverted-index
- pos-tag
- text-analysis
- +6 more
+9 stars
from 712 · score 2.30
63.pytorch / textArchived
Models, data loaders and abstractions for language processing, powered by PyTorch
- nlp
- data-loader
- deep-learning
- pytorch
- dataset
- models
+7 stars
from 3,547 · score 2.08
64.diasks2 / pragmatic_segmenter
Pragmatic Segmenter is a rule-based sentence boundary detection gem that works out-of-the-box across many languages.
+7 stars
from 590 · score 2.08
65.james-bowman / nlp
Selected Machine Learning algorithms for natural language processing and semantic analysis in Golang
- go
- golang
- natural-language-processing
- nlp
- lsa
- latent-semantic-analysis
- +14 more
+6 stars
from 471 · score 1.95
66.NLPatVCU / medaCy
:hospital: Medical Text Mining and Information Extraction with spaCy
- natural-language-processing
- medical-natural-language-processing
- machine-learning
- metamap
- clinical-text-processing
- information-extraction
- +2 more
+6 stars
from 436 · score 1.95
67.neurosnap / sentences
A multilingual command line sentence tokenizer in Golang
- sentence-tokenizer
- tokenizer
- cli
- sentences
+5 stars
from 466 · score 1.79
68.huggingface / swift-coreml-transformersArchived
Swift Core ML 3 implementations of GPT-2, DistilGPT-2, BERT, and DistilBERT for Question answering. Other Transformers coming soon!
+4 stars
from 1,678 · score 1.61
69.gagolews / stringi
Fast and Portable Character String Processing in R (with the Unicode ICU)
+4 stars
from 317 · score 1.61
70.patil-suraj / question_generation
Neural question generation using transformers
- nlp
- nlg
- deep-learning
- transformer
- t5
- question-generation
- +2 more
+3 stars
from 1,135 · score 1.39
71.dbpedia-spotlight / dbpedia-spotlightArchived
DBpedia Spotlight is a tool for automatically annotating mentions of DBpedia resources in text.
- dbpedia-spotlight
- nlp
- semantic-web
- entity-linking
- text-annotation
- content-tagging
- +2 more
+2 stars
from 759 · score 1.10
72.CogComp / cogcomp-nlp
CogComp's Natural Language Processing Libraries and Demos: Modules include lemmatizer, ner, pos, prep-srl, quantifier, question type, relation-extraction, similarity, temporal normalizer, tokenizer, transliteration, verb-sense, and more.
- natural-language-processing
- nlp
- big-data
- data-mining
- cogcomp
- lemmatizer
- +12 more
+1 stars
from 478 · score 0.69