Open-source nlp software
1574 open-source libraries, tools and applications tagged nlp, ranked by how closely nlp is their primary purpose, then by adoption and maintenance health. Each entry links to a page with sources, use cases and when to choose or avoid it.
1574 products, primary matches first, then adoption-weighted; health v2 shown.
| Product | Health v2 | Stars | Maturity |
|---|---|---|---|
| WikiExtractor/wikiextractor WikiExtractor is a Python command-line tool that extracts and cleans plain text from Wikipedia database backup dumps (XML). It supports tem… | 95 | 4005 | stable |
| urchade/GLiNER GLiNER is a Python framework for training and deploying lightweight, zero-shot Named Entity Recognition models that can extract arbitrary e… | 87 | 3997 | active |
| Speakr Speakr is a self-hosted web application that transcribes audio recordings and turns them into organized, searchable notes. It supports mult… | 84 | 3987 | 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… | 95 | 3959 | active |
| OpenHealthForAll/open-health OpenHealth is a self-hostable AI health assistant that consolidates personal health data (blood tests, checkups, wearables, symptoms) into … | 47 | 3954 | 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… | 72 | 3951 | 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 | 3946 | stable |
| gnekt/My-Brain-Is-Full-Crew A crew of 8+ AI agents with 14 specialized skills that manages an Obsidian vault through conversational chat, handling knowledge organizati… | 52 | 3874 | active |
| JioNLP JioNLP is a Python library for Chinese NLP preprocessing and parsing, offering utilities like time semantic parsing, license plate parsing,… | 77 | 3873 | active |
| piskvorky/gensim Gensim is a Python library for topic modelling, document indexing, and similarity retrieval over large text corpora. It provides memory-ind… | 43 | 16492 | 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 | 16323 | maintenance |
| kingname/GeneralNewsExtractor GNE (GeneralNewsExtractor) is a Python library that extracts article title, author, publish time, body text, and images from news page HTML… | 75 | 3802 | active |
| fqscfqj/Y2A-Auto Y2A-Auto is a self-hosted Python application that automates re-uploading YouTube videos to AcFun and bilibili. It handles the full pipeline… | 81 | 3787 | active |
| Hunyuan-PromptEnhancer/PromptEnhancer PromptEnhancer is a prompt-rewriting framework from Tencent Hunyuan that uses a Chain-of-Thought rewriter trained via reinforcement learnin… | 59 | 3785 | 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 | 3774 | active |
| SakiRinn/LiveCaptions-Translator A lightweight Windows application that combines the built-in Windows 11 LiveCaptions speech-to-text feature with translation APIs (includin… | 72 | 3769 | active |
| 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… | 53 | 3765 | stable |
| shobrook/adrenaline Adrenaline is an AI-powered assistant that answers technical questions about programming concepts, GitHub repositories, documentation, and … | 32 | 3741 | active |
| MTG/essentia Essentia is an open-source C++ library for audio analysis and music information retrieval, offering a large collection of reusable DSP algo… | 66 | 3733 | stable |
| 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 | 3728 | active |
| 语燕输入法 (YuyanIme) YuyanIme is a Chinese input method app for Android built on the Rime engine, supporting full pinyin, T9 nine-key, double pinyin, handwritin… | 83 | 3701 | active |
| miso-belica/sumy Sumy is a Python library and command-line utility for automatic extractive summarization of plain text documents and HTML pages. It impleme… | 85 | 3697 | active |
| wdcpclover/ai4paper AI4Paper is an AI research workbench delivered primarily as a Zotero 7-10 plugin, with a web app, browser extension, and WeChat mini-progra… | 78 | 3684 | active |
| PAIR-code/lit The Learning Interpretability Tool (LIT) is a visual, interactive web-based tool for understanding and debugging ML model behavior across t… | 72 | 3667 | active |
| TheFuzz TheFuzz (formerly FuzzyWuzzy) is a Python library for fuzzy string matching that uses Levenshtein distance to compute similarity ratios bet… | 33 | 3654 | active |
| menzi11/BullshitGenerator A JavaScript-based generator of nonsensical Chinese filler text ('BullshitGenerator') intended for testing GUI text rendering. It assembles… | 32 | 15502 | maintenance |
| unicode-org/icu ICU (International Components for Unicode) is the Unicode Consortium's mature C/C++ and Java library providing Unicode and globalization su… | 79 | 3611 | stable |
| apache/lucene Apache Lucene is a high-performance, full-featured text search engine library written in Java, providing indexing, search, spellchecking, h… | 95 | 3586 | stable |
| codelucas/newspaper newspaper3k is a Python 3 library for discovering, downloading, and parsing news articles from websites. It extracts full text, authors, pu… | 66 | 15174 | maintenance |
| textdistance A Python library for computing distances and similarities between two or more sequences using 30+ algorithms such as Levenshtein, Hamming, … | 27 | 3544 | active |
| MNE-Python MNE-Python is an open-source Python library for exploring, visualizing, and analyzing human neurophysiological data such as MEG, EEG, sEEG,… | 94 | 3540 | stable |
| fnnx-ai/scikit-llm Scikit-LLM is a Python library that integrates large language models like GPT into scikit-learn workflows as estimators. It enables tasks s… | 72 | 3533 | active |
| matomo-org/device-detector A PHP library that parses User Agents and Client Hints to detect the device type, browser, operating system, brand, and model, as well as b… | 86 | 3529 | active |
| jinchenma94/bazi-skill A Claude Code skill for Chinese Four Pillars (BaZi) astrology charting and analysis. It collects birth details interactively, computes the … | 56 | 3508 | active |
| JusticeRage/Gepetto Gepetto is an IDA Pro plugin that queries large language models (OpenAI, Anthropic, Gemini, Ollama, and others) to explain decompiled funct… | 73 | 3487 | active |
| NLPIR NLPIR is a Chinese natural language processing platform (formerly ICTCLAS) providing an SDK with around twenty text analysis functions incl… | 71 | 3479 | active |
| Docta-ai/docta Docta is a Python library for data-centric AI that diagnoses and fixes issues in datasets such as label errors, noise, and misannotations. … | 66 | 3479 | active |
| wolfgarbe/SymSpell SymSpell is a C# library implementing the Symmetric Delete spelling correction algorithm for extremely fast spelling correction and fuzzy s… | 60 | 3474 | stable |
| TextAttack TextAttack is a Python framework for generating adversarial examples against NLP models, as well as for data augmentation and model trainin… | 80 | 3471 | active |
| wensonsmith/YoudaoTranslator An Alfred workflow for macOS that provides instant Chinese-English and multilingual translation via Youdao and Baidu translation APIs. It i… | 31 | 3457 | active |
| MTEB MTEB (Massive Text Embedding Benchmark) is a Python library and CLI for benchmarking embedding models across 1000+ tasks, languages, and mo… | 95 | 3455 | active |
| lynote-ai/humanize-text An open-source Python toolkit for making AI-generated drafts read more naturally, offering four documented humanization approaches plus a p… | 67 | 3453 | active |
| bbepis/XUnity.AutoTranslator A Unity game translation plugin that automatically translates game text via online translation services and supports manual translation wor… | 91 | 3450 | active |
| jsvine/markovify Markovify is a simple, extensible Python library for building Markov chain models from text corpora and generating random semi-plausible se… | 32 | 3409 | stable |
| huggingface/datatrove DataTrove is a Python library from Hugging Face for processing, filtering, and deduplicating large-scale text data through customizable pip… | 87 | 3390 | active |
| AnySoftKeyboard AnySoftKeyboard is a free, open-source on-screen keyboard application for Android supporting 50+ languages via external language packs. It … | 87 | 3387 | active |
| InkTimeRecord/TTime TTime is a cross-platform desktop application for Windows and macOS that provides translation via input, screenshot, word selection, floati… | 23 | 3380 | active |
| libAudioFlux/audioFlux audioFlux is a C-based library with Python bindings for audio and music analysis and feature extraction. It supports dozens of time-frequen… | 50 | 3372 | active |
| futo-org/android-keyboard FUTO Keyboard is a privacy-focused Android keyboard app forked from AOSP's LatinIME, offering offline voice input, swipe typing, autocorrec… | 83 | 3347 | active |
| QiuYannnn/Local-File-Organizer A privacy-focused desktop application that uses on-device AI models (Llama3.2 3B and Llava v1.6 via Nexa SDK) to scan, understand, and reor… | 14 | 3340 | active |
| wendy7756/AI-Video-Transcriber An open-source AI tool that transcribes, summarizes, and archives videos and podcasts from 30+ platforms (YouTube, TikTok, Bilibili, etc.) … | 61 | 3314 | active |
| facebookresearch/tribev2 TRIBE v2 is a multimodal deep learning model from Meta AI that predicts fMRI brain responses to naturalistic video, audio, and text stimuli… | 52 | 3293 | active |
| jehna/humanify A Rust CLI tool that unminifies and deobfuscates JavaScript by using LLMs (OpenAI, Anthropic, Gemini, OpenRouter, or local Ollama) to sugge… | 83 | 3288 | active |
| Pix2Text Pix2Text is an open-source Python tool that recognizes layouts, tables, math formulas (LaTeX), and text in images and converts them into Ma… | 93 | 3270 | active |
| MAIF/shapash Shapash is a Python library that makes machine learning models interpretable and understandable through clear visualizations, a webapp, and… | 95 | 3267 | active |
| Graphic Walker PyGWalker is a Python library that turns pandas (or Polars/Arrow) dataframes into an interactive drag-and-drop visual analysis UI inside Ju… | 78 | 3267 | active |
| oxylabs/ai-crawler-py A Python client library for Oxylabs AI Studio's AI-Crawler, a commercial service that crawls websites from a starting URL, uses natural lan… | 10 | 3264 | active |
| sd-webui-prompt-all-in-one A Stable Diffusion WebUI extension that enhances the prompt and negative prompt input boxes with a more intuitive interface. It adds automa… | 73 | 3237 | active |
| echohive42/AI-reads-books-page-by-page A Python script that reads PDF books page by page, using AI to extract knowledge points and generate progressive summaries at configurable … | 58 | 3217 | active |
| textlint textlint is a pluggable linting tool for natural language text, similar to ESLint but for prose instead of code. It supports Markdown and p… | 96 | 3201 | active |
| TNTSearch TNTSearch is a full-text search engine written entirely in PHP that builds inverted indexes stored in SQLite, MySQL, or Redis. It returns r… | 84 | 3199 | active |
| matthartman/ghost-pepper A free, open-source macOS menu bar app providing fully on-device speech-to-text dictation and meeting transcription using local Whisper, Pa… | 72 | 3186 | active |
| FB208/OpenBidKit_Yibiao OpenBidKit Yibiao (易标) is an open-source Electron desktop application that uses LLMs and RAG to generate bid/tender proposal documents from… | 82 | 3149 | active |
| chenyme/Chenyme-AAVT Chenyme-AAVT is a fully automated audio/video translation application that uses Whisper (faster-whisper) for speech recognition, large lang… | 10 | 3129 | active |
| Top2Vec Top2Vec is a Python library that learns jointly embedded topic, document, and word vectors for topic modeling and semantic search. It suppo… | 23 | 3111 | stable |
| theajack/cnchar cnchar is a comprehensive TypeScript library for Chinese character processing, offering pinyin conversion, stroke counts, stroke order draw… | 62 | 3100 | active |
| LLMQuant/quant-mind QuantMind is an agent-native Python framework that refines raw financial information such as papers, news, and SEC filings into typed, time… | 61 | 3100 | active |
| infinilabs/analysis-pinyin A Pinyin analysis plugin for Elasticsearch, OpenSearch, and Easysearch that converts between Chinese characters and Pinyin. It provides a p… | 56 | 3094 | active |
| jdkato/prose prose is a pure-Go natural language processing library offering tokenization, sentence segmentation, part-of-speech tagging, named-entity e… | 62 | 3091 | active |
| xnx3/translate translate.js is a JavaScript library that adds automatic HTML page translation with just two lines of code, scanning the DOM and translatin… | 80 | 3090 | active |
| robert-mcdermott/ai-knowledge-graph A Python CLI tool that uses an LLM to extract Subject-Predicate-Object triplets from unstructured text documents and renders them as an int… | 84 | 3088 | active |
| guillaume-be/rust-bert A Rust-native library providing ready-to-use NLP pipelines and transformer-based models (BERT, DistilBERT, GPT-2, RoBERTa, BART, etc.), por… | 57 | 3084 | active |
| google/mozc Mozc is an open-source Japanese Input Method Editor (IME) originating from Google Japanese Input, released under a BSD license. It supports… | 77 | 3015 | active |
| Dicklesworthstone/llm_aided_ocr A Python tool that converts scanned PDFs to text via Tesseract OCR, then uses LLMs (local or API-based like OpenAI/Anthropic) to correct OC… | 68 | 3001 | active |
| LIME Lime (Local Interpretable Model-agnostic Explanations) is a Python library that explains the predictions of any machine learning classifier… | 23 | 12170 | maintenance |
| 0xemmkty/QuantMuse A Python-based quantitative trading system combining factor analysis, ML models, and LLM-powered market analysis with real-time market data… | 33 | 2964 | active |
| mit-nlp/MITIE MITIE is a C++ library and toolset for information extraction, providing named entity recognition and binary relation detection built on dl… | 39 | 2960 | active |
| openrecall/openrecall OpenRecall is an open-source, privacy-first digital memory tool that periodically takes screenshots of your screen, extracts text via local… | 40 | 2946 | active |
| state-spaces/s4 Official implementations of Structured State Space (S4) sequence models and related variants like S4D, HiPPO, and SaShiMi, built in PyTorch… | 32 | 2927 | active |
| starcwang/easy_javadoc Easy Javadoc is an IntelliJ IDEA plugin that automatically generates Javadoc and KDoc documentation comments for Java and Kotlin classes, m… | 72 | 2914 | active |
| AllenNLP AllenNLP is an open-source NLP research library built on PyTorch for developing state-of-the-art deep learning models on linguistic tasks. … | 10 | 11886 | maintenance |
| xiao-zaiyi/illa-helper A browser extension that helps users learn languages naturally while browsing the web, based on the comprehensible input theory. It provide… | 73 | 2899 | active |
| hotcoffeeshake/tong-jincheng-skill A Claude Code skill that makes the AI respond as 'Tong Jincheng' (童锦程), a Chinese internet personality known for blunt relationship advice,… | 51 | 2898 | active |
| jhj0517/Whisper-WebUI A Gradio-based web interface for OpenAI's Whisper models that generates subtitles from files, YouTube videos, or microphone input. It suppo… | 58 | 2897 | active |
| explosion/thinc Thinc is a lightweight deep learning library from the makers of spaCy offering a type-checked, functional-programming API for composing neu… | 74 | 2891 | active |
| Jieba (CppJieba) NodeJieba is the Node.js binding of the Jieba Chinese word segmentation library, with the core segmentation algorithms implemented in C++ v… | 82 | 2878 | active |
| Amurex Amurex is an open-source Chrome extension that acts as an AI meeting copilot for Google Meet and MS Teams. It provides real-time suggestion… | 31 | 2873 | active |
| goniszewski/grimoire Grimoire is a local-first, self-hosted bookmark manager for saving, extracting, and searching web content, with optional AI-powered summari… | 95 | 2866 | active |
| scrapinghub/dateparser A Python library that parses human-readable dates in almost any format, including relative expressions like 'two weeks ago', timestamps, an… | 92 | 2861 | stable |
| go-ego/gse gse is a Go library for efficient multilingual text segmentation and NLP, implementing jieba-style word segmentation with HMM/Viterbi suppo… | 91 | 2844 | active |
| huggingface/setfit SetFit is a Python library for efficient, prompt-free few-shot fine-tuning of Sentence Transformers for text classification. It achieves hi… | 88 | 2842 | active |
| AdapterHub Adapters is a Python add-on library for HuggingFace Transformers that integrates 10+ parameter-efficient fine-tuning methods (bottleneck ad… | 74 | 2831 | active |
| kpu/kenlm KenLM is a C++ toolkit for estimating, filtering, and querying n-gram language models with modified Kneser-Ney smoothing. It is designed fo… | 35 | 2812 | stable |
| zachlatta/freeflow FreeFlow is a free, open-source macOS dictation app that transcribes speech via Groq's fast API and pastes cleaned text into any focused te… | 74 | 2794 | active |
| rhasspy/rhasspy Rhasspy is a fully offline, privacy-focused set of voice assistant services supporting many human languages. It converts spoken voice comma… | 10 | 2746 | active |
| microlinkhq/metascraper Metascraper is a Node.js library that extracts unified metadata from any URL by combining Open Graph, JSON-LD, Microdata, RDFa, Twitter Car… | 92 | 2738 | active |
| BigDawnGhost/wenyi Wenyi is a Python CLI tool that translates EPUB books into Chinese using LLMs, with whole-book context analysis, real-time glossary extract… | 80 | 2733 | active |
| MindForger MindForger is a desktop personal knowledge management tool that combines a thinking notebook with a full-featured Markdown editor/IDE. It m… | 98 | 2723 | active |
| freedmand/semantra-python Semantra is a command-line tool that semantically indexes text and PDF documents and launches a local web application for querying them by … | 31 | 2713 | active |
| openai/privacy-filter OpenAI Privacy Filter is a small bidirectional token-classification model (1.5B total, 50M active parameters) for detecting and masking per… | 46 | 2711 | active |