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 |
|---|---|---|---|
| varunshenoy/GraphGPT GraphGPT is a web application that converts unstructured natural language text into a knowledge graph using GPT-3, visualizing entities and… | 32 | 4423 | experimental |
| LeeSureman/Flat-Lattice-Transformer Reference implementation of the ACL 2020 paper FLAT: Chinese NER Using Flat-Lattice Transformer, built on PyTorch and FastNLP. It trains fl… | 32 | 1002 | maintenance |
| baidu/DDParser DDParser is Baidu's open-source Chinese dependency parsing tool built on PaddlePaddle and large-scale annotated data. It provides one-comma… | 23 | 1001 | maintenance |
| gsh199449/spider Gather Platform is a Java-based configurable web crawler built on the WebMagic kernel, with a web console for configuring and managing scra… | 57 | 997 | maintenance |
| UdaraJay/Pile Pile is an open-source desktop app for reflective journaling that keeps entries stored locally. It optionally integrates AI (OpenAI GPT-4 o… | 18 | 3121 | experimental |
| Priler/jarvis JARVIS is an offline, privacy-respecting voice assistant built in Rust with Tauri, using neural networks for speech-to-text, text-to-speech… | 50 | 2952 | experimental |
| gvzdv/claudish-to-english A Claude Code plugin that rewrites assistant messages into plain English using a local LLM via ollama, or alternatively the codex CLI, Anth… | 78 | 2728 | experimental |
| b-nnett/goose Goose is a local-first iOS companion app for WHOOP 5.0 fitness bands, built with SwiftUI and a Rust core that parses Bluetooth packet data … | 10 | 2722 | experimental |
| Nutlope/llama-ocr An npm library that performs OCR by sending images to Llama 3.2 Vision models via Together AI and returns structured Markdown. It supports … | 60 | 2437 | experimental |
| facebookresearch/large_concept_model Official PyTorch implementation of Meta's Large Concept Models (LCM), which perform language modeling by autoregressively predicting senten… | 22 | 2381 | experimental |
| mshumer/gpt-investor An experimental AI agent notebook that uses Claude 3 models to analyze stocks in a given industry, gathering financial data, news, and anal… | 26 | 2264 | experimental |
| deepklarity/jupyter-text2code A proof-of-concept Jupyter Notebook extension that converts English queries into relevant Python code using sentence embedding models. It s… | 50 | 2077 | experimental |
| Klotzkette/claude-fuer-deutsches-recht An experimental collection of Claude skills, sub-agents, and workflows adapted for German legal practice, covering areas like employment, c… | 78 | 1719 | experimental |
| obsei/obsei Obsei is an open-source, low-code, AI-powered automation framework for text analysis workflows. It collects unstructured data from sources … | 100 | 1437 | experimental |
| osama-fawad/Pekingman Pekingman is a multimodal AGI-oriented agent system that connects environmental perception, long-term memory, human-like reasoning, emotion… | 51 | 1419 | experimental |
| anc95/writely Writely is an open-source browser extension for Chrome, Firefox, and Edge that brings GPT-powered AI writing assistance to any editable web… | 33 | 1296 | experimental |
| nethical6/conversation-steganography A Go CLI tool that hides encrypted secret messages inside natural-looking chat text generated by a local LLM (GPT-2), enabling covert commu… | 52 | 1250 | experimental |
| google-deepmind/synthid-text A reference Python implementation of Google DeepMind's SynthID Text watermarking and detection technology for identifying AI-generated text… | 68 | 1173 | experimental |
| model-zoo/shift-ctrl-f A Chrome extension that lets users search a webpage using natural language questions instead of exact string matching. It runs a MobileBERT… | 10 | 1100 | experimental |
| oxylabs/ai-scraper-py AI-Scraper is a Python library and scrape agent from Oxylabs AI Studio that extracts data from webpages using natural language prompts inst… | 10 | 1090 | experimental |
| erelsgl/limdu Limdu is a machine-learning framework for Node.js supporting binary, multi-class, and multi-label classification with online and batch lear… | 53 | 1046 | experimental |
| Magenta Magenta is a Google Brain research project and Python TensorFlow library for generating music, images, and drawings with machine learning. … | 10 | 19787 | abandoned |
| sfyc23/EverydayWechat A Python 3 / ItChat-based WeChat assistant that sends scheduled daily messages (weather, quotes, custom text) to friends and group chats, a… | 32 | 10336 | abandoned |
| clips/pattern Pattern is a Python web mining module bundling tools for scraping (Google, Twitter, Wikipedia APIs, crawler, HTML DOM parser), NLP (POS tag… | 62 | 8856 | abandoned |
| Mycroft AI Mycroft Core is the core software of the Mycroft open-source voice assistant platform, providing wake-word listening, speech recognition, n… | 10 | 6616 | abandoned |
| facebookresearch/pytext PyText is a deep-learning-based NLP modeling framework built on PyTorch, providing extensible abstractions for text classifiers, sequence t… | 10 | 6291 | abandoned |
| salesforce/BLIP PyTorch implementation of BLIP, a vision-language pre-training model for unified image understanding and text generation tasks. The reposit… | 10 | 5708 | abandoned |
| google/seq2seq A general-purpose encoder-decoder (seq2seq) framework built on TensorFlow, supporting tasks like machine translation, text summarization, c… | 10 | 5619 | abandoned |
| karpathy/neuraltalk NeuralTalk is a Python+numpy implementation of Multimodal Recurrent Neural Networks that generate natural-language descriptions of images. … | 32 | 5508 | abandoned |
| euske/pdfminer PDFMiner is a pure-Python library and CLI tool for parsing PDF documents and extracting text along with layout information such as fonts, p… | 10 | 5269 | abandoned |
| huggingface/autotrain-advanced AutoTrain Advanced is Hugging Face's no-code tool for training and deploying state-of-the-art machine learning models, covering LLM finetun… | 76 | 4612 | abandoned |
| qq547276542/Agriculture_KnowledgeGraph AgriKG is an agricultural domain knowledge graph system built on Neo4j with a Django web interface, including crawled encyclopedia data, na… | 32 | 4395 | abandoned |
| pytorch/text TorchText is a PyTorch companion library providing datasets, data loaders, vocabularies, text transforms, and pre-trained models for natura… | 10 | 3553 | abandoned |
| mortenjust/cleartext-mac Cleartext is a macOS text editor that restricts writing to the 1,000 most common English words, inspired by Randall Munroe's Thing Explaine… | 23 | 3251 | abandoned |
| protectai/llm-guard LLM Guard is a Python library providing input and output scanners to secure LLM interactions, including sanitization, harmful language dete… | 10 | 3208 | abandoned |
| ryankiros/neural-storyteller A recurrent neural network research project that generates short stories about images by combining skip-thought vectors, visual-semantic em… | 32 | 2959 | abandoned |
| IntelLabs/nlp-architect NLP Architect is an open-source Python library from Intel AI Lab for exploring state-of-the-art deep learning topologies and optimization t… | 10 | 2931 | abandoned |
| FudanNLP/fnlp FNLP (FudanNLP) is a Java toolkit for Chinese natural language processing, including word segmentation, POS tagging, NER, keyword extractio… | 23 | 2682 | abandoned |
| sherjilozair/char-rnn-tensorflow A Python/TensorFlow implementation of multi-layer recurrent neural networks (LSTM) for character-level language modeling, inspired by Andre… | 32 | 2658 | abandoned |
| medcl/elasticsearch-rtf Elasticsearch-RTF is a ready-to-fly Chinese distribution of Elasticsearch bundling pre-tested plugins such as the IK Chinese analyzer, so b… | 10 | 2645 | abandoned |
| danielfrg/word2vec A Python wrapper around Google's original word2vec C code, providing training and similarity/analogy tools via Python APIs and command-line… | 10 | 2614 | abandoned |
| aceakash/string-similarity A JavaScript library that computes the degree of similarity between two strings using Dice's Coefficient, offering compareTwoStrings and fi… | 10 | 2530 | abandoned |
| kkos/oniguruma Oniguruma is a flexible C regular expression library supporting many regex syntaxes and a wide range of character encodings, historically u… | 10 | 2523 | abandoned |
| opencog/opencog OpenCog is a framework for integrated artificial intelligence and artificial general intelligence (AGI) research, combining natural languag… | 36 | 2478 | abandoned |
| aress31/burpgpt burpgpt is a Burp Suite extension that sends HTTP traffic to OpenAI GPT models for AI-driven passive vulnerability scanning and traffic ana… | 31 | 2394 | abandoned |
| achillesrasquinha/bulbea A Python library for stock market prediction and modelling using deep learning, built on TensorFlow with RNN models for price forecasting a… | 32 | 2334 | abandoned |
| openai/finetune-transformer-lm Reference code and model for OpenAI's paper 'Improving Language Understanding by Generative Pre-Training' (the original GPT-1), implemented… | 10 | 2307 | abandoned |
| chiphuyen/lazynlp A Python library for crawling, cleaning, and deduplicating web pages to build massive monolingual text datasets, suitable for training lang… | 23 | 2298 | abandoned |
| facebookresearch/InferSent InferSent is a sentence embedding method from Facebook AI Research that produces semantic representations for English sentences using a mod… | 10 | 2281 | abandoned |
| PetrochukM/PyTorch-NLP PyTorch-NLP (torchnlp) is a Python library of basic utilities for natural language processing built on PyTorch, providing text data loading… | 10 | 2220 | abandoned |
| Pointer-Generator Networks (Get To The Point) Reference implementation of the pointer-generator network from the ACL 2017 paper 'Get To The Point: Summarization with Pointer-Generator N… | 32 | 2191 | abandoned |
| itsabot/itsabot Abot is an open-source Go framework for building digital assistants similar to Siri, Cortana, or Alexa, with an extensible plugin system an… | 23 | 2142 | abandoned |
| joshnewlan/say_what A Python script that listens to conference call audio via speech-to-text (IBM Watson) and alerts the user on HipChat when their name is men… | 32 | 2086 | abandoned |
| ryankiros/skip-thoughts A Python implementation of the Skip-Thought Vectors paper, providing a sent2vec encoder that maps sentences to fixed 4800-dimensional vecto… | 32 | 2048 | abandoned |
| tobie/ua-parser A multi-language port of Browserscope's user agent string parser that extracts browser, device, and OS information from user agent strings.… | 10 | 1961 | abandoned |
| crockpotveggies/tinderbox Tinderbox is a self-hosted desktop web application that automates Tinder swiping and introductions using Eigenfaces for face-based attracti… | 10 | 1937 | abandoned |
| rowanmanning/joblint Joblint is a Node.js CLI tool and JavaScript library that lints tech job posts for issues with sexism, culture, unrealistic expectations, a… | 10 | 1855 | abandoned |
| jiesutd/LatticeLSTM A PyTorch implementation of Lattice LSTM for Chinese Named Entity Recognition, accompanying an ACL 2018 paper. It combines character-based … | 32 | 1832 | abandoned |
| zjy-ucas/ChineseNER A TensorFlow demo implementing a bidirectional LSTM-CRF model for Chinese named entity recognition. It includes training and evaluation scr… | 32 | 1823 | abandoned |
| facebookarchive/MemNN Facebook AI Research's reference implementations of memory-augmented neural networks (MemN2N, Key-Value Memory Networks, Entity Networks) w… | 10 | 1753 | abandoned |
| facebookresearch/TransCoder TransCoder is a PyTorch implementation of an unsupervised neural model that translates source code between Java, C++, and Python 3. It is a… | 10 | 1729 | abandoned |
| lukalabs/cakechat CakeChat is a Python backend for building emotional generative chatbots using a hierarchical recurrent encoder-decoder (seq2seq) architectu… | 10 | 1708 | abandoned |
| Ayanaminn/N46Whisper A Google Colab notebook application that generates Japanese subtitle files from video using the faster-whisper speech recognition model. It… | 32 | 1705 | abandoned |
| huggingface/swift-coreml-transformers A Swift library with Core ML implementations of GPT-2, DistilGPT-2, BERT, and DistilBERT, including tokenizers and demo apps for on-device … | 10 | 1683 | abandoned |
| nyu-mll/jiant jiant is a PyTorch-based NLP research toolkit for multitask and transfer learning, supporting 50+ natural language understanding tasks and … | 23 | 1674 | abandoned |
| terrifyzhao/bert-utils A Python library that simplifies Google's BERT to generate sentence vectors with one line of code and perform text classification and text … | 32 | 1669 | abandoned |
| Jovo Framework Jovo is an open-source TypeScript/JavaScript framework for building cross-platform voice and chat applications from a single codebase, targ… | 10 | 1669 | abandoned |
| waynecz/dadda-translate-crx Dadda is a Chrome word-selection translation extension with a built-in vocabulary notebook and toast-based word memorization reminders. It … | 23 | 1640 | abandoned |
| superscriptjs/superscript SuperScript is a dialogue engine and bot framework for building human-like conversation chat bots in JavaScript on Node.js. It provides an … | 23 | 1636 | abandoned |
| caesarHQ/textSQL textSQL is an open-source project that converts natural language questions into SQL queries using GPT-3.5, letting users query databases wi… | 31 | 1581 | abandoned |
| Glance Glance (formerly OpenSpritz) is a speed-reading bookmarklet that displays web page text word-by-word using RSVP (Rapid Serial Visual Presen… | 32 | 1565 | abandoned |
| allenai/bi-att-flow Original implementation of the Bi-directional Attention Flow (BiDAF) network for machine comprehension on the SQuAD dataset. It is a multi-… | 23 | 1545 | abandoned |
| huggingface/pytorch-openai-transformer-lm A PyTorch reimplementation of OpenAI's finetuned transformer language model (GPT-1) from the paper 'Improving Language Understanding by Gen… | 10 | 1525 | abandoned |
| GravityLabs/goose Goose is a Scala library (originally Java) that extracts the main body text, metadata, publish date, embedded videos, and top image from ne… | 10 | 1524 | abandoned |
| openai/generating-reviews-discovering-sentiment Research code accompanying the OpenAI paper 'Learning to Generate Reviews and Discovering Sentiment', providing a byte-level multiplicative… | 10 | 1520 | abandoned |
| fossasia/asksusi AskSUSI is the web frontend for SUSI.AI, an open-source personal assistant combining pattern matching, internet data, and inference to answ… | 10 | 1484 | abandoned |
| fossasia/susi_hangoutbot A bot that connects the SUSI AI assistant to Google Hangouts, allowing users to chat with SUSI from their Hangouts conversations. It is a J… | 32 | 1460 | abandoned |
| dhwajraj/deep-siamese-text-similarity A TensorFlow implementation of a deep siamese LSTM network that learns phrase and sentence similarity using character-level and word-level … | 32 | 1414 | abandoned |
| regenrek/deepwiki-mcp An unofficial MCP server that fetches deepwiki.com documentation, crawls its pages, converts them to Markdown, and serves them to MCP-compa… | 49 | 1386 | abandoned |
| leonardocardoso/SwiftLinkPreview A Swift library that generates link previews from URLs by extracting titles, relevant text, and images. It supports iOS, macOS, watchOS, an… | 10 | 1385 | abandoned |
| louismullie/treat Treat is a natural language processing and computational linguistics toolkit for Ruby, offering tokenization, parsing, POS tagging, NER, ke… | 38 | 1367 | abandoned |
| wangfreexx/wangfreexx-tianruoocr-cl-paddle A local (offline) Windows OCR application based on the open-source Tianruo OCR, using ChineseOCR Lite and PaddleOCR models for text recogni… | 23 | 1356 | abandoned |
| dmotz/thing-translator Thing Translator is a web app that lets users point their phone or laptop camera at objects to hear how to say their names in a different l… | 32 | 1328 | abandoned |
| facebookarchive/duckling_old Duckling (old) is a Clojure library that parses natural language text into structured data, such as extracting dates, times, and durations … | 10 | 1321 | abandoned |
| hunkim/word-rnn-tensorflow A TensorFlow implementation of multi-layer recurrent neural networks (LSTM/RNN) for training word-level language models, adapted from char-… | 32 | 1294 | abandoned |
| YeYzheng/KGQA-Based-On-medicine A knowledge graph question answering (KGQA) system for medicine that parses natural language questions into SPARQL queries against an Apach… | 32 | 1279 | abandoned |
| chaoming0625/SentimentPolarityAnalysis A Python library for Chinese sentiment polarity analysis offering both lexicon-based scoring and classic ML classifiers (k-NN, Bayes, maxim… | 32 | 1268 | abandoned |
| atpaino/deep-text-corrector A TensorFlow research project that trains sequence-to-sequence deep learning models to correct small grammatical errors in short conversati… | 32 | 1235 | abandoned |
| twitter-archive/twitter-text-js A JavaScript implementation of Twitter's text processing library for parsing tweets, extracting entities like hashtags, mentions, URLs, and… | 10 | 1205 | abandoned |
| glample/tagger A Named Entity Recognition (NER) tool implementing a state-of-the-art LSTM-CRF model that works across languages without gazetteers. It shi… | 32 | 1176 | abandoned |
| xiaoxu193/PyTeaser PyTeaser is a Python library that summarizes news articles by ranking sentences for relevance to the title, keywords, position, and length,… | 76 | 1170 | abandoned |
| FooSoft/yomichan Yomichan is a browser extension for Chrome and Firefox that turns the browser into a Japanese pop-up dictionary, showing interactive defini… | 10 | 1142 | abandoned |
| NVIDIA/sentiment-discovery A deprecated PyTorch codebase from NVIDIA for large-scale unsupervised language model pretraining and transfer to sentiment and emotion cla… | 23 | 1065 | abandoned |
| shiyybua/NER A Chinese named entity recognition (NER) system built with TensorFlow, using a bidirectional RNN combined with a CRF layer for sequence lab… | 32 | 1054 | abandoned |
| graykode/gpt-2-Pytorch A compact PyTorch reimplementation of OpenAI's GPT-2 for text generation, loading Hugging Face's converted pre-trained weights. It provides… | 32 | 1012 | abandoned |
| Transformers Hugging Face Transformers is a Python library that serves as the model-definition framework for state-of-the-art machine learning models ac… | 95 | 167798 | stable |
| ComfyUI ComfyUI is a modular, node‑based visual interface and inference engine for generative AI. It lets users chain multiple models, adjust every… | 95 | 138077 | active |
| harry0703/MoneyPrinterTurbo MoneyPrinterTurbo is an AI-powered application that generates high-definition short videos from a topic or keyword. It automatically writes… | 92 | 131685 | active |
| openai/whisper OpenAI's Whisper is a general-purpose speech recognition model and Python library built on a Transformer sequence-to-sequence architecture.… | 64 | 109525 | stable |
| PaddlePaddle/PaddleOCR PaddleOCR is a multilingual OCR and document parsing toolkit built on PaddlePaddle that converts images and PDFs into structured data like … | 91 | 90108 | stable |