function: nlp
1557 products, primary matches first, then adoption-weighted; health v2 shown.
| Product | Health v2 | Stars | Maturity |
|---|---|---|---|
| ymcui/Chinese-LLaMA-Alpaca-2 A project releasing Chinese-adapted LLaMA-2 base models and Alpaca-2 instruction-tuned chat models with an extended Chinese vocabulary, inc… | 54 | 7120 | stable |
| interviewstreet/hiring-agent An open-source AI agent pipeline from HackerRank that extracts structured data from resume PDFs, enriches it with GitHub signals, and produ… | 60 | 7007 | active |
| deeppavlov/DeepPavlov DeepPavlov is an open-source Python NLP library built on PyTorch and Hugging Face transformers for developing, training, and deploying stat… | 39 | 6989 | active |
| interpretml/interpret InterpretML is a Python library that unifies machine learning interpretability techniques, letting users train inherently interpretable gla… | 91 | 6928 | active |
| TalAter/annyang annyang is a tiny (2 KB), dependency-free JavaScript library that adds speech recognition and voice commands to websites using the Web Spee… | 78 | 6816 | stable |
| adbar/trafilatura Trafilatura is a Python package and command-line tool for crawling the web and extracting main text, metadata, and comments from raw HTML w… | 93 | 6709 | active |
| goldendict/goldendict GoldenDict is a feature-rich desktop dictionary lookup program that supports many dictionary formats (StarDict, Babylon, Lingvo DSL, Dictd,… | 44 | 6649 | active |
| microsoft/LLMLingua LLMLingua is a Microsoft library for prompt compression that removes non-essential tokens from prompts and KV caches to speed up LLM infere… | 53 | 6609 | active |
| axa-group/nlp.js NLP.js is a natural language processing library for Node.js that provides intent classification, named entity recognition, sentiment analys… | 23 | 6585 | active |
| steipete/summarize Summarize is a Node.js CLI and Chrome/Firefox extension that extracts clean text from web pages, PDFs, YouTube videos, podcasts, and audio/… | 82 | 6577 | active |
| shibing624/pycorrector pycorrector is a Python toolkit for Chinese text error correction, supporting phonetic, visual, and grammar error types with models includi… | 84 | 6515 | active |
| argosopentech/argos-translate Argos Translate is an open-source offline neural machine translation library written in Python, built on OpenNMT. It can be used as a Pytho… | 66 | 6403 | active |
| zarazhangrui/follow-builders An AI agent skill that tracks top AI builders on X/Twitter, YouTube podcasts, and AI company blogs, then remixes their content into digesti… | 59 | 6396 | active |
| itorr/nbnhhsh A userscript and web tool that translates Chinese pinyin initialism abbreviations (like 'yyds' or 'xswl') used on social platforms into rea… | 53 | 6273 | active |
| tyiannak/pyAudioAnalysis pyAudioAnalysis is a Python library for audio analysis covering feature extraction (MFCCs, spectrograms, chromagrams), supervised and unsup… | 48 | 6254 | active |
| PrefectHQ/marvin Marvin is a Python framework for building AI applications with LLMs, offering structured-output utilities (extract, cast, classify, generat… | 88 | 6192 | active |
| NEKOparapa/AiNiee AiNiee is an AI-powered translation tool focused on automatically translating complex long-form content such as RPG/SLG game text, Epub/TXT… | 94 | 6174 | active |
| petergyang/no-ai-slop An AI agent skill/plugin that removes 20+ patterns of AI-generated writing clichés ('slop') from text while preserving the author's persona… | 77 | 6124 | active |
| Beingpax/VoiceInk VoiceInk is a native macOS voice-to-text dictation app that transcribes speech to text almost instantly using local AI models (Parakeet, Wh… | 84 | 6115 | active |
| zenstory-ai/oh-story-claudecode A skill pack for Claude Code and compatible AI coding agents that provides an end-to-end workflow for writing Chinese web fiction, covering… | 80 | 6112 | active |
| harfbuzz/harfbuzz HarfBuzz is a text shaping engine that converts Unicode text into properly positioned glyph output for any writing system, supporting OpenT… | 99 | 6039 | stable |
| houbb/sensitive-word A high-performance Java library for sensitive/prohibited word detection and filtering based on the DFA algorithm, with a built-in 60k+ word… | 56 | 6026 | active |
| YILING0013/AI_NovelGenerator A Python GUI application that uses large language models to generate multi-chapter long-form novels with automatic context continuity, fore… | 65 | 5960 | active |
| FilipePS/Traduzir-paginas-web TWP - Translate Web Pages is a browser extension (WebExtension) that translates web pages in real time using Google, Bing, or Yandex transl… | 98 | 5955 | active |
| OpenWhispr/openwhispr OpenWhispr is an open-source, privacy-first voice-to-text dictation desktop app for macOS, Windows, and Linux. It supports fully local tran… | 81 | 5766 | active |
| facebookresearch/fastText fastText is a lightweight open-source C++ library (with Python bindings and a CLI) from Facebook Research for efficiently learning word rep… | 10 | 26534 | maintenance |
| nextai-translator/bob-plugin-openai-translator A Bob plugin for macOS that uses OpenAI, Google Gemini, MiniMax, or OpenAI-compatible APIs to translate text, polish wording, and fix gramm… | 96 | 5655 | active |
| spotify/basic-pitch Basic Pitch is a lightweight neural network library from Spotify for automatic music transcription, converting audio recordings of nearly a… | 46 | 5489 | stable |
| lingodotdev/lingo.dev Lingo.dev is an open-source localization engineering toolkit that turns LLMs into stateful translation APIs, persisting glossaries, brand v… | 87 | 5407 | active |
| pypinyin pypinyin is a Python library (with a companion CLI) that converts Chinese characters (hanzi) to pinyin, supporting polyphonic characters, m… | 67 | 5356 | stable |
| handsomestWei/patent-disclosure-skill A Python-based agent skill for Chinese patent work that mines patentable points from project materials, drafts disclosure documents (invent… | 59 | 5317 | active |
| Librum-Reader/Librum Librum is a free and open-source e-book reader and library management application built with C++, Qt6, and QML. It lets users read e-books,… | 58 | 5312 | active |
| wanasit/chrono Chrono is a natural language date parser library for JavaScript/TypeScript that extracts dates and times from arbitrary text. It handles re… | 90 | 5269 | active |
| HIT-SCIR/ltp LTP (Language Technology Platform) is an open-source neural NLP toolkit for Chinese supporting word segmentation, POS tagging, NER, depende… | 55 | 5259 | active |
| microsoft/SynapseML SynapseML (formerly MMLSpark) is an open-source machine learning library built on Apache Spark that provides simple, composable, distribute… | 88 | 5240 | active |
| katanaml/sparrow Sparrow is an open-source framework for structured data extraction from documents (PDFs, images) using ML, LLMs, and Vision LLMs, with sche… | 95 | 5202 | active |
| maziyarpanahi/openmed OpenMed is a local-first healthcare AI SDK for clinical named-entity recognition and HIPAA PII/PHI de-identification that runs entirely on-… | 83 | 5166 | active |
| chatopera/Synonyms A Python library for Chinese synonym lookup and semantic similarity computation, built on word vector models for NLP and chatbot use cases.… | 52 | 5111 | active |
| grobidOrg/grobid GROBID is a Java machine learning library that extracts, parses, and re-structures raw documents such as PDFs into structured XML/TEI, focu… | 87 | 5105 | active |
| get-alex/alex alex is a JavaScript-based linter that catches insensitive, inconsiderate writing such as gendered, ableist, or polarizing phrasing in text… | 23 | 5100 | active |
| cjhutto/vaderSentiment VADER is a lexicon and rule-based sentiment analysis library for Python, specifically tuned to sentiments expressed in social media but eff… | 54 | 5053 | stable |
| epoko77-ai/im-not-ai A Claude Code / Copilot CLI skill (with a hosted web app) that detects and rewrites AI-generated Korean text so it reads like natural human… | 81 | 5008 | active |
| shibing624/text2vec A Python library that converts text (words, sentences, paragraphs) into vector embeddings, implementing Word2Vec, RankBM25, BERT, Sentence-… | 53 | 4974 | active |
| microsoft/muzic Muzic is a Microsoft Research project providing deep learning models for music understanding and generation, including MusicBERT, SongMASS,… | 66 | 4952 | active |
| openvenues/libpostal libpostal is a C library for parsing and normalizing street addresses from around the world using statistical NLP and open geo data. It con… | 60 | 4879 | stable |
| Rasa Open Source Rasa Open Source is a Python framework for building text- and voice-based conversational AI assistants, combining NLU (intent/entity recogn… | 65 | 21306 | maintenance |
| SakuraLLM/SakuraLLM SakuraLLM is a series of fine-tuned open large language models for Japanese-to-Chinese translation specialized in light novel and Galgame (… | 61 | 4735 | active |
| WorldBrain/Memex Memex is a browser extension (Chrome/Firefox) for curating, annotating, highlighting, tagging, and full-text searching web content and PDFs… | 48 | 4715 | active |
| feyninc/chonkie Chonkie is a lightweight Python library for chunking text in RAG pipelines, offering multiple chunking algorithms, embeddings, and integrat… | 84 | 4704 | active |
| zh-lx/pinyin-pro A high-performance Chinese-to-Pinyin conversion library for JavaScript/TypeScript. It converts Chinese characters to pinyin with tones, ini… | 99 | 4689 | active |
| xxnuo/MTranServer MTranServer is an offline machine translation server with very low resource usage and millisecond response times, requiring no GPU. It supp… | 66 | 4675 | active |
| makcedward/nlpaug nlpaug is a Python library for augmenting textual, audio, and spectrogram data to improve machine learning model performance. It provides A… | 66 | 4665 | active |
| ThioJoe/YT-Spammer-Purge A Python-based desktop application that scans YouTube comment sections for spam and scam comments using 15 different filtering methods, the… | 40 | 4643 | active |
| promptslab/Promptify Promptify is a Python library that turns LLMs into task-based NLP engines, providing high-level APIs for NER, classification, QA, and custo… | 65 | 4635 | active |
| osfans/trime Trime (Tongwen Input Method) is an Android input method editor (IME) built on the open-source RIME input method framework via JNI. It suppo… | 92 | 4599 | active |
| amperser/proselint proselint is a command-line linter for English prose that scans text files for style, usage, and clarity issues based on advice from renown… | 73 | 4566 | active |
| dedupeio/dedupe Dedupe is a Python library that uses machine learning to perform fuzzy matching, deduplication, and entity resolution on structured data. I… | 48 | 4507 | stable |
| kaixindelele/ChatPaper ChatPaper is a Python tool that uses ChatGPT to summarize arXiv papers, translate full PDFs, polish academic writing, and simulate peer rev… | 62 | 19780 | maintenance |
| zjunlp/DeepKE DeepKE is an open-source PyTorch-based knowledge extraction toolkit for knowledge graph construction, supporting named entity recognition, … | 64 | 4472 | active |
| tangshimin/MuJing MuJing (幕境) is a free, open-source desktop application for learning English vocabulary through real context from movies, TV shows, and docu… | 60 | 4468 | active |
| overtrue/pinyin A PHP library that converts Chinese text to pinyin using the mozillazg/pinyin-data dictionary, with accurate handling of polyphonic charact… | 74 | 4461 | stable |
| 万象拼音 (Wanxiang Pinyin) Wanxiang Pinyin is a comprehensive Rime input method configuration ecosystem featuring an AI-optimized Chinese dictionary with tone-annotat… | 86 | 4460 | active |
| wooorm/franc franc is a JavaScript library that detects the natural language of text, supporting 82, 186, or 419 languages depending on the package vari… | 23 | 4411 | stable |
| pot-app/pot-desktop Pot is a cross-platform desktop application for hotkey-based text translation, screenshot OCR, and text-to-speech, built with Tauri. It sup… | 62 | 19343 | maintenance |
| cmusphinx/pocketsphinx PocketSphinx is Carnegie Mellon's lightweight, speaker-independent continuous speech recognition engine, available as a C library, a comman… | 84 | 4335 | active |
| whoiskatrin/sql-translator SQL Translator is a free, open-source web application that converts natural language queries into SQL code and translates SQL back into hum… | 44 | 4323 | active |
| ymcui/Chinese-LLaMA-Alpaca A project releasing Chinese-adapted LLaMA and instruction-tuned Alpaca large language models with extended Chinese vocabulary, plus pre-tra… | 56 | 18931 | maintenance |
| facebook/duckling Duckling is a Haskell library that parses natural language text into structured data, extracting entities like dates, times, amounts of mon… | 55 | 4313 | active |
| ssut/py-googletrans An unofficial free Python library that wraps Google Translate's Ajax API for text translation and language detection. It supports async usa… | 66 | 4271 | active |
| ThilinaRajapakse/simpletransformers Simple Transformers is a Python library built on Hugging Face Transformers that lets users train, fine-tune, and evaluate Transformer model… | 61 | 4254 | active |
| kevin2li/PDF-Guru PDF Guru Anki is a cross-platform desktop and mobile application that combines a comprehensive PDF toolbox with deep Anki integration, conv… | 30 | 4217 | active |
| MaartenGr/KeyBERT KeyBERT is a minimal Python library that extracts keywords and keyphrases from documents using BERT embeddings and cosine similarity. It re… | 67 | 4215 | stable |
| Spark NLP Spark NLP is an open-source natural language processing library built natively on Apache Spark, providing scalable NLP annotations and tran… | 96 | 4159 | stable |
| hcfyapp/crx-selection-translate Huaci Fanyi (Selection Translate) is a browser extension for Chrome, Edge, and Firefox that translates selected text, full web pages, scree… | 32 | 4139 | active |
| ericciarla/trendFinder A self-hosted Node.js application that monitors influencer posts on Twitter/X and website changes via Firecrawl, then uses LLMs (Together A… | 24 | 4116 | active |
| tmoroney/auto-subs AutoSubs is a local-first desktop application that generates AI subtitles on-device using Whisper, Moonshine, and Parakeet models, with spe… | 94 | 4091 | active |
| rapidfuzz/RapidFuzz RapidFuzz is a fast fuzzy string matching library for Python and C++ offering many string metrics such as Levenshtein, Jaro-Winkler, and Ha… | 87 | 4085 | stable |
| jitwxs/163MusicLyrics A Windows desktop GUI application for fetching and processing song lyrics from NetEase Cloud Music and QQ Music. It supports searching by s… | 74 | 4071 | active |
| marcelroed/gigatoken Gigatoken is a Rust-based tokenizer library for language modeling that tokenizes text at GB/s throughput, claiming ~1000x speedups over Hug… | 60 | 4061 | active |
| rspeer/python-ftfy ftfy is a Python library that fixes mojibake (encoding mix-ups) and other Unicode text glitches after the fact, recovering original text fr… | 34 | 4060 | stable |
| umlx5h/LLPlayer LLPlayer is a Windows media player built for language learning, featuring dual subtitles, AI-generated subtitles via Whisper ASR, real-time… | 78 | 4049 | active |
| defog-ai/sqlcoder SQLCoder is a family of fine-tuned open-weight LLMs that convert natural language questions into SQL queries, outperforming GPT-4 on text-t… | 28 | 4044 | active |
| apache/tika Apache Tika is a Java toolkit that detects file types and extracts text and metadata from over a thousand file formats (PDF, Office documen… | 77 | 4011 | stable |
| WikiExtractor/wikiextractor WikiExtractor is a Python command-line tool that extracts and cleans plain text from Wikipedia database backup dumps (XML). It supports tem… | 98 | 4001 | stable |
| ginobefun/BestBlogs BestBlogs.dev is an AI-powered personal reading assistant and content curation platform that aggregates articles, podcasts, videos, tweets,… | 67 | 3998 | active |
| promeG/TinyPinyin TinyPinyin is a fast, low-memory Java and Android library for converting Chinese characters to Pinyin without tones. It supports custom dic… | 23 | 3949 | stable |
| OpenHealthForAll/open-health OpenHealth is a self-hostable AI health assistant that consolidates personal health data (blood tests, checkups, wearables, symptoms) into … | 50 | 3942 | active |
| yuka-friends/Windrecorder Windrecorder is a local-first screen recording and memory search app for Windows, an open-source alternative to Rewind.ai and Microsoft Rec… | 47 | 3926 | active |
| dongrixinyu/JioNLP JioNLP is a Python library for Chinese NLP preprocessing and parsing, offering utilities like time semantic parsing, license plate parsing,… | 75 | 3864 | active |
| aurelio-labs/semantic-router Semantic Router is a Python library that provides a fast decision-making layer for LLMs and agents, routing requests based on semantic vect… | 94 | 3841 | active |
| piskvorky/gensim Gensim is a Python library for topic modelling, document indexing, and similarity retrieval over large text corpora. It provides memory-ind… | 50 | 16481 | maintenance |
| ddbourgin/numpy-ml numpy-ml is a collection of machine learning models and algorithms implemented exclusively in NumPy and the Python standard library, coveri… | 32 | 16330 | maintenance |
| kingname/GeneralNewsExtractor GNE (GeneralNewsExtractor) is a Python library that extracts article title, author, publish time, body text, and images from news page HTML… | 81 | 3788 | active |
| daviddrysdale/python-phonenumbers A Python port of Google's libphonenumber library for parsing, formatting, and validating international phone numbers. It converts phone num… | 76 | 3769 | active |
| Hunyuan-PromptEnhancer/PromptEnhancer PromptEnhancer is a prompt-rewriting framework from Tencent Hunyuan that uses a Chain-of-Thought rewriter trained via reinforcement learnin… | 61 | 3758 | active |
| aubio/aubio aubio is a C library (with Python bindings and CLI tools) for labeling music and sounds, detecting events such as note onsets, pitch, and t… | 57 | 3754 | stable |
| shobrook/adrenaline Adrenaline is an AI-powered assistant that answers technical questions about programming concepts, GitHub repositories, documentation, and … | 32 | 3741 | active |
| mumuy/relationship A JavaScript library and web app that computes Chinese family kinship terms and relationship chains, e.g. deriving the correct title for 'm… | 66 | 3727 | active |
| rahulnyk/knowledge_graph A Python/Jupyter Notebook project that converts any text corpus into a knowledge graph by extracting concepts with an LLM and linking co-oc… | 71 | 3713 | active |
| Renhuai123/ziwei-doushu An open-source Zi Wei Dou Shu (Purple Star Astrology) chart calculation engine based on Ni Haixia's Tianji system, written in TypeScript wi… | 60 | 3707 | active |