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 |
|---|---|---|---|
| toss/es-hangul A modern, tree-shakable TypeScript/JavaScript library for manipulating Korean Hangul characters. It provides APIs for initial consonant (ch… | 84 | 1880 | active |
| thunlp/WantWords WantWords is an open-source online reverse dictionary developed by Tsinghua University's THUNLP lab, returning words that semantically matc… | 32 | 7095 | maintenance |
| 425776024/nlpcda nlpcda is a Python library for one-click Chinese NLP data augmentation. It provides techniques like random entity replacement, synonym subs… | 25 | 1875 | active |
| xyTom/snippai Snippai is an AI-powered snipping tool that captures screenshots and uses AI to extract structured content such as LaTeX formulas, text, ta… | 89 | 1871 | active |
| bmabey/pyLDAvis pyLDAvis is a Python library for interactive visualization of fitted LDA topic models, ported from the R LDAvis package. It renders web-bas… | 44 | 1851 | active |
| RHVoice/RHVoice RHVoice is a free and open-source statistical parametric speech synthesizer (TTS) built on HTS technology, originally for Russian and now s… | 88 | 1844 | active |
| sxzxs/Real-time-translation-typing A Windows AutoHotkey-based tool that provides real-time typing translation and real-time speech-to-text translation, with special support f… | 93 | 1837 | active |
| ssnangua/ColorTxt ColorTxt is a local desktop novel reader for TXT and common ebook formats (epub, mobi, pdf, etc.) that colorizes content with custom highli… | 80 | 1837 | active |
| google-research/language A shared repository collecting open-sourced NLP research projects from the Google AI Language team, written in Python. It serves as a home … | 67 | 1816 | active |
| google/budoux BudouX is a small, standalone, machine-learning-powered line break organizer that segments sentences into phrases for languages without wor… | 100 | 1808 | active |
| kmonkeyhead/MORT MORT is a Windows desktop application that extracts on-screen text in real time using OCR and translates it via databases or machine transl… | 96 | 1807 | active |
| undertheseanlp/underthesea Underthesea is an open-source Python toolkit for Vietnamese natural language processing that has evolved into an agentic AI toolkit with mu… | 91 | 1806 | active |
| xhluca/bm25s BM25S is a pure Python library implementing BM25 lexical ranking using Numpy/Scipy sparse matrices with an optional Numba backend, achievin… | 91 | 1800 | active |
| microsoft/Recognizers-Text Microsoft.Recognizers-Text is a multilingual library for recognizing and resolving entities such as numbers, units, and date/time expressio… | 61 | 1795 | stable |
| lancopku/pkuseg-python pkuseg is a Python toolkit for multi-domain Chinese word segmentation based on the paper by Luo et al. (2019). It provides pre-trained mode… | 23 | 6710 | maintenance |
| symfony/string A PHP library from the Symfony ecosystem providing an object-oriented API for string manipulation that uniformly handles bytes, UTF-8 code … | 97 | 1785 | stable |
| AIScientists-Dev/academic-humanizer A skill/plugin for AI coding agents (Claude Code, Codex, MorphMind) that edits AI-assisted academic drafts to remove generic AI-writing tel… | 51 | 1785 | active |
| Moonvy/OpenPromptStudio Open Prompt Studio (OPS) is a web-based visual editor for AIGC prompts, primarily targeting Midjourney. It provides Chinese-English prompt … | 31 | 6685 | maintenance |
| Feather-2/Burner-X Paper Burner X is a browser-based AI workstation for processing, translating, and analyzing academic documents like PDFs, DOCX, PPTX, and E… | 63 | 1783 | active |
| arianneorpilla/jidoujisho jidoujisho is a full-featured immersion language learning suite for mobile, built with Flutter for Android. It combines media viewing (vide… | 43 | 1777 | active |
| x007xyz/flycut-caption FlyCut Caption is an AI-powered video subtitle editing tool built as a React component and web/desktop app, offering speech recognition wit… | 73 | 1773 | active |
| isnowfy/snownlp SnowNLP is a Python library for processing Simplified Chinese text, offering word segmentation, part-of-speech tagging, sentiment analysis,… | 32 | 6635 | maintenance |
| zubair-trabzada/ai-legal-claude A Claude Code skill pack providing an AI legal assistant with 14 slash commands and 5 parallel agents for contract review, risk analysis, N… | 45 | 1768 | active |
| parthsarthi03/raptor The official Python implementation of RAPTOR (Recursive Abstractive Processing for Tree-Organized Retrieval), a retrieval-augmented generat… | 26 | 1761 | active |
| AnswerDotAI/ModernBERT ModernBERT is the research repository for a modernized BERT-family bidirectional encoder trained on 2 trillion tokens with an 8192-token co… | 53 | 1758 | active |
| kijai/ComfyUI-Florence2 A ComfyUI custom node plugin that runs Microsoft's Florence-2 vision-language model for image captioning, object detection, segmentation, a… | 57 | 1756 | active |
| T5 The official T5 library from Google Research, implementing the text-to-text transfer transformer for NLP tasks like summarization, question… | 67 | 6562 | maintenance |
| maxbbraun/trump2cash A Python stock trading bot that watches Donald Trump's tweets, detects mentions of publicly traded companies, and uses sentiment analysis t… | 10 | 6541 | maintenance |
| codertimo/BERT-pytorch A PyTorch implementation of Google AI's 2018 BERT model with simple, readable code. It provides CLI tools for building vocabulary and pre-t… | 23 | 6529 | maintenance |
| Auto Synced Translated Dubs A Python CLI tool that automatically translates video subtitles into multiple languages and generates AI voice dubbed audio tracks synced t… | 56 | 1744 | active |
| Ansj Chinese Segmentation A Java library for Chinese word segmentation based on n-Gram+CRF+HMM, achieving ~2 million characters/second with 96%+ accuracy. It also pr… | 23 | 6506 | maintenance |
| egoist/sitefetch A Node.js CLI tool that crawls an entire website and saves its pages as a single text file, using Mozilla Readability to extract clean cont… | 21 | 1739 | active |
| jesselau76/ebook-GPT-translator A Python CLI and GUI tool that translates ebooks (TXT, EPUB, DOCX, PDF, optional MOBI) using LLM providers like OpenAI, Azure, Codex, Claud… | 60 | 1735 | active |
| juliye2025/evil-read-arxiv A collection of Claude Code / OpenAI Codex skills plus a Next.js web app that automates research paper discovery, analysis, and note-taking… | 58 | 1735 | active |
| lifan0127/ai-research-assistant Aria is a Zotero plugin that brings GPT-powered AI assistance to reference management, letting researchers chat with their library items, P… | 24 | 1729 | active |
| NuPIC NuPIC is Numenta's open-source machine intelligence platform implementing Hierarchical Temporal Memory (HTM), a computational theory of the… | 23 | 6352 | maintenance |
| Python3Spiders/WeiboSuperSpider A Weibo (Chinese microblog) scraping toolbox in Python covering users, topics, and comments, with extras like image downloading, sentiment … | 71 | 1706 | active |
| dqbd/tiktokenizer Tiktokenizer is a web-based playground for OpenAI's tiktoken tokenizers that calculates the exact number of tokens in a given prompt. It is… | 36 | 1701 | stable |
| leochlon/hallbayes Berry is a local MCP server that detects hallucinations by measuring whether an LLM's claims are actually supported by the cited evidence, … | 54 | 1699 | active |
| espressif/esp-csi Espressif's official examples and tools for Wi-Fi Channel State Information (CSI) on ESP32-series chips, enabling non-contact wireless sens… | 64 | 1691 | active |
| Subtitle Translator A cross-platform Electron desktop app that translates subtitle files (.ass, .srt, .ssa, .vtt) using LLMs like ChatGPT. It preserves context… | 88 | 1689 | active |
| ckiplab/ckiptagger CkipTagger is a Python library implementing neural CKIP-style Chinese NLP tools for word segmentation, part-of-speech tagging, and named en… | 33 | 1686 | stable |
| explosion/sense2vec A Python library implementing sense2vec, contextually-keyed word vectors that learn embeddings for multi-word phrases and part-of-speech-di… | 52 | 1681 | stable |
| streetsidesoftware/vscode-spell-checker Code Spell Checker is a VS Code extension that spell checks source code and documents as you type, underlining unknown words and offering s… | 97 | 1680 | active |
| elixir-nx/bumblebee Bumblebee is an Elixir library providing pre-trained neural network models built on Axon, with integration for downloading models from Hugg… | 94 | 1674 | active |
| chrismattmann/tika-python Tika-Python is a Python client library for Apache Tika's REST services, enabling document parsing, text extraction, and MIME detection nati… | 83 | 1673 | active |
| zihangdai/xlnet XLNet is a generalized autoregressive pretraining method for language representation learning, built on Transformer-XL. This repo provides … | 32 | 6189 | maintenance |
| mkiol/dsnote Speech Note is a Linux desktop and Sailfish OS application for note taking, reading, and translating text using offline Speech to Text, Tex… | 92 | 1664 | active |
| coduo/php-humanizer A PHP library that converts developer-oriented values like snake_case identifiers, byte sizes, numbers, and dates into human-readable text.… | 52 | 1657 | active |
| vigorX777/ai-daily-digest A zero-dependency TypeScript CLI tool (runnable as an OpenCode skill) that fetches the latest posts from 90 top tech blogs recommended by A… | 42 | 1643 | active |
| AnswerDotAI/rerankers A lightweight, dependency-free Python library providing a unified API for using all common reranking and cross-encoder models. It lets deve… | 39 | 1640 | active |
| go-ego/riot Riot is a distributed full-text search engine library written in Go, featuring efficient indexing, Chinese word segmentation via gse, BM25 … | 97 | 6051 | maintenance |
| datamade/usaddress usaddress is a Python library that parses unstructured United States address strings into labeled address components using a conditional ra… | 44 | 1638 | active |
| un33k/python-slugify A Python library that generates URL-safe slugs from text, with best-effort handling of Unicode strings via transliteration. It offers optio… | 98 | 1625 | stable |
| difyz9/ytb2bili ytb2bili is a self-hosted video workflow application that automates downloading videos from YouTube, generating and translating subtitles, … | 73 | 1622 | active |
| royshil/obs-localvocal LocalVocal is an OBS Studio plugin that performs real-time, fully local speech recognition and translation using Whisper models running on … | 84 | 1618 | active |
| Online Dictionary Helper Online Dictionary Helper is a Chrome/Firefox browser extension that shows definitions of selected words and phrases from online or built-in… | 76 | 1617 | active |
| stanford-oval/WikiChat WikiChat is a retrieval-augmented generation (RAG) framework that grounds LLM chatbot responses in a corpus (Wikipedia by default) to reduc… | 44 | 1617 | active |
| AlibabaResearch/DAMO-ConvAI The official codebase for Alibaba DAMO Academy's Conversational AI research, containing implementations of models from their published pape… | 75 | 1605 | active |
| Apache OpenNLP Apache OpenNLP is a machine learning based Java toolkit for processing natural language text, supporting tasks like tokenization, sentence … | 97 | 1604 | stable |
| enoch3712/ExtractThinker ExtractThinker is a Python document intelligence library that uses LLMs to extract and classify structured data from documents like PDFs, i… | 71 | 1601 | active |
| sea-team/gofound GoFound is a lightweight full-text search engine written in Go, featuring inverted/forward indexes, built-in Chinese word segmentation (jie… | 23 | 1597 | active |
| LuteOrg/lute-v3 Lute (Learning Using Texts) is a self-hosted Python/Flask web application for learning foreign languages through reading. It lets users imp… | 87 | 1594 | active |
| capitalone/DataProfiler DataProfiler is a Python library that loads CSV, AVRO, Parquet, JSON, text, or URL data into a pandas-compatible DataFrame and profiles it … | 91 | 1591 | active |
| stanfordnlp/pyreft pyreft is Stanford NLP's Python library for Representation Finetuning (ReFT), which adapts frozen language models by learning task-specific… | 52 | 1587 | active |
| shibing624/similarity A Java toolkit for computing text similarity at word, phrase, sentence, and paragraph levels, offering algorithms like Cilin-based similari… | 61 | 1583 | active |
| antvis/AVA AVA is an AI-native visual analytics framework from AntV that lets users load data (CSV, JSON, URL), query it in natural language, and get … | 80 | 1581 | active |
| karpathy/arxiv-sanity-preserver A self-hostable web application for browsing, searching, and filtering recent arXiv submissions, with personalized paper recommendations ba… | 32 | 5799 | maintenance |
| Postlight Parser Postlight Parser is a JavaScript library that extracts meaningful content—article text, titles, authors, dates, lead images, and excerpts—f… | 23 | 5791 | maintenance |
| hanmin0822/MisakaTranslator MisakaTranslator is a Windows desktop application that provides real-time machine translation for Galgames, text-based games, and manga. It… | 23 | 5777 | maintenance |
| santinic/how2 how2 is a command-line tool that suggests Unix shell commands from natural-language queries, using AI models retrained on Bash/Zsh plus Sta… | 23 | 5771 | maintenance |
| bootphon/phonemizer A Python library and command-line tool that converts words and texts into phonemes across many languages. It wraps multiple backends (espea… | 83 | 1573 | stable |
| cookiy-ai/user-research-skill An open-source AI agent skill (installed as a CLI) that lets AI coding agents like Claude Code, Codex, Cursor, and OpenClaw plan, run, and … | 57 | 1567 | active |
| Chinese-Text-Classification-Pytorch A PyTorch-based collection of ready-to-run Chinese text classification models including TextCNN, TextRNN, FastText, TextRCNN, BiLSTM with a… | 32 | 5728 | maintenance |
| vi3k6i5/flashtext FlashText is a Python library for fast keyword extraction and replacement in sentences, based on the FlashText algorithm. It uses a trie-li… | 36 | 5706 | maintenance |
| afc163/fanyi Fanyi is a command-line Chinese-English translation tool that aggregates results from iciba, youdao, and an LLM (with a free built-in proxy… | 79 | 1554 | active |
| you-apps/TranslateYou Translate You is a privacy-focused Android translator app built with Kotlin, Jetpack Compose, and Material Design 3. It supports multiple t… | 82 | 1549 | active |
| amicalhq/amical Amical is an open-source, local-first AI dictation app for macOS and Windows that transcribes speech with Whisper and enhances it with LLMs… | 84 | 1548 | active |
| facebookresearch/mmf MMF is a modular PyTorch framework for vision and language multimodal research from Facebook AI Research. It ships reference implementation… | 67 | 5637 | maintenance |
| video-db/call.md Call.md is an open-source Electron desktop app that records meetings locally, transcribes them in real time with speaker separation, and pr… | 56 | 1532 | active |
| interpretml/DiCE DiCE is a Python library that generates diverse counterfactual explanations for any machine learning model, showing feature-perturbed versi… | 33 | 1529 | active |
| wb14123/seq2seq-couplet A deep learning project that generates Chinese couplets (对联) using a seq2seq model built with TensorFlow. It includes training scripts, a w… | 32 | 5480 | maintenance |
| liseami/DeepRant DeepRant is a cross-platform desktop app built with Tauri that provides quick hotkey-based translation of in-game chat text for gamers on i… | 89 | 1506 | active |
| huangserva/skill-prompt-generator A Claude Code Skills-based system that generates high-quality AI image prompts by intelligently combining elements from a 1,246-item Univer… | 49 | 1506 | active |
| DicioTeam/dicio-android Dicio is a free and open source voice assistant app for Android that interprets user questions and provides speech and graphical feedback e… | 91 | 1505 | active |
| joewongjc/type4me Type4Me is a macOS voice input method that transcribes speech in real time (streaming, local or cloud ASR engines) and refines text with LL… | 83 | 1497 | active |
| gregjacobs/Autolinker.js A TypeScript utility library that automatically converts URLs, email addresses, phone numbers, @mentions, and #hashtags in plain text or HT… | 61 | 1496 | stable |
| AI4Finance-Foundation/FinNLP FinNLP is a Python library for collecting internet-scale financial data from sources like Finnhub, Yahoo Finance, Reuters, and Sina Finance… | 31 | 1491 | active |
| bert4keras A lightweight, clean reimplementation of BERT and other transformer models (RoBERTa, ALBERT, T5, GPT, ELECTRA, NEZHA) for Keras/tf.keras. I… | 23 | 5409 | maintenance |
| ModelOriented/DALEX DALEX (moDel Agnostic Language for Exploration and eXplanation) is a library for exploring, explaining, and visualizing the behavior of pre… | 61 | 1486 | active |
| ripose-jp/Memento Memento is a free, open-source video player built on mpv designed for studying Japanese. It integrates a Yomitan-compatible popup dictionar… | 90 | 1484 | active |
| McCloudS/subgen Subgen is a self-hosted service that automatically generates subtitles for media files using OpenAI's Whisper speech recognition models. It… | 71 | 1484 | active |
| honeyandme/RAGQnASystem A medical intelligent question-answering system combining knowledge-graph RAG with large language models, built on the DiseaseKG dataset wi… | 59 | 1483 | active |
| sb-ai-lab/LightAutoML LightAutoML (LAMA) is a Python framework for automatic machine learning model creation (AutoML) supporting tabular, time series, image, and… | 73 | 1479 | active |
| IBM Watson Node.js SDK The official Node.js/TypeScript client library (npm package ibm-watson) for accessing IBM Watson services such as Assistant, Speech to Text… | 80 | 1473 | active |
| refinery An open-source tool for scaling, assessing, and maintaining natural language training data, treating datasets like software artifacts. It p… | 23 | 1473 | active |
| napi-rs A collection of Node.js native addons written in Rust using napi-rs, providing packages like @node-rs/bcrypt, @node-rs/argon2, @node-rs/crc… | 96 | 1470 | active |
| FACT (Firmware Analysis and Comparison Tool) FACT (Firmware Analysis and Comparison Tool) is a self-hosted Python application that automates firmware security analysis for devices like… | 94 | 1468 | active |
| sienori/simple-translate Simple Translate is a browser extension (WebExtension) that lets users quickly translate selected text on web pages or typed text via a too… | 82 | 1464 | active |
| Turing-Project/WriteGPT WriteGPT is a generative text-creation AI framework built on GPT-2 and other models (EAST, CRNN, BERT), fine-tuned to generate Chinese exam… | 23 | 5282 | maintenance |