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 |
|---|---|---|---|
| GauravSingh9356/J.A.R.V.I.S A Python-based voice-controlled personal assistant inspired by Iron Man's J.A.R.V.I.S. It combines speech recognition, text-to-speech, OCR,… | 44 | 1415 | active |
| VideoSrt VideoSrt is an open-source Windows GUI tool written in Go that recognizes speech in video/audio files and automatically generates SRT subti… | 23 | 5042 | maintenance |
| thalesgroup-cert/Watcher Watcher is an open-source, self-hosted cyber threat intelligence and hunting platform built with Django and React JS. It uses AI to analyze… | 96 | 1387 | active |
| QwenLM/Qwen3-VL-Embedding Qwen3-VL-Embedding and Qwen3-VL-Reranker are state-of-the-art multimodal embedding and reranking models built on the Qwen3-VL foundation mo… | 52 | 1387 | active |
| zjunlp/KnowLM KnowLM is an open-source framework for building knowledgeable large language models, covering data processing, pre-training, fine-tuning, k… | 31 | 1386 | active |
| jordanrendric/claude-video-vision A Claude Code plugin with an MCP server that gives Claude the ability to watch and understand videos by extracting frames via ffmpeg and tr… | 70 | 1381 | active |
| K-Dense-AI/k-dense-byok K-Dense BYOK is a free, open-source desktop application providing 'Kady', an AI research assistant (co-scientist) that runs locally and use… | 78 | 1376 | active |
| Meituan-AutoML/MobileVLM MobileVLM is a family of compact vision language models (1.4B-3B parameters) designed to run efficiently on mobile devices, combining small… | 17 | 1371 | active |
| Kuingsmile/word-GPT-Plus Word GPT Plus is a Microsoft Word add-in that integrates LLMs and AI agents directly into Word for generating, translating, summarizing, an… | 83 | 1368 | active |
| HG-ha/MTools MTools is a cross-platform desktop application built with Python and Flet that bundles image processing, audio/video editing, text operatio… | 83 | 1361 | active |
| jhc13/taggui TagGUI is a cross-platform desktop application for quickly adding and editing image tags and captions, aimed at creators of image datasets … | 47 | 1357 | active |
| lxtGH/OMG-Seg Official research codebase for OMG-Seg (CVPR 2024) and OMG-LLaVA (NeurIPS 2024), unified models for image-level, object-level, and pixel-le… | 68 | 1353 | active |
| xtreme1-io/xtreme1 Xtreme1 is an open-source, self-hosted data labeling and annotation platform for multimodal training data, supporting images, 3D LiDAR poin… | 98 | 1345 | active |
| Intuition-Lab/personal-model Personal Model (Persome) is a local-first macOS runtime that captures focused cross-app activity and builds an evidence-linked personal mem… | 76 | 1337 | active |
| modelscope/sirchmunk Sirchmunk is an agentic, embedding-free search engine that turns raw files into a self-evolving knowledge base in real time, without vector… | 81 | 1333 | active |
| deanmalmgren/textract A Python library that extracts text from virtually any document format (PDF, DOCX, PPTX, HTML, images, and more) through a simple unified i… | 93 | 4727 | maintenance |
| Tongjilibo/bert4torch bert4torch is a PyTorch library providing an elegant reimplementation of transformer models (BERT, RoBERTa, T5, GPT, ChatGLM, LLaMA, etc.) … | 76 | 1326 | active |
| apecloud/ApeRAG ApeRAG is a production-ready RAG platform combining Graph RAG, vector search, and full-text search with AI agents and MCP support. It offer… | 62 | 1322 | active |
| deepseek-ai/DeepSeek-Prover-V2 DeepSeek-Prover-V2 is an open-source large language model for formal theorem proving in Lean 4, trained via reinforcement learning with sub… | 31 | 1311 | active |
| DimiMikadze/orca Orca is an AI agent application for deep LinkedIn profile analysis that scrapes posts, comments, reactions, and interaction networks, then … | 76 | 1306 | active |
| DAMO-NLP-SG/VideoLLaMA2 VideoLLaMA 2 is an open-source video large language model that adds spatial-temporal modeling and audio understanding to video-LLMs. It pro… | 25 | 1306 | active |
| minsight-ai-info/AI-Search-Hub AI Search Hub is an open-source Skill that aggregates native AI search capabilities from platforms like Gemini, Grok, Doubao, and Yuanbao i… | 47 | 1304 | active |
| neo4j/neo4j-graphrag-python The official Neo4j first-party Python library for building graph retrieval-augmented generation (GraphRAG) applications. It provides retrie… | 92 | 1303 | active |
| codefuse-ai/codefuse-chatbot CodeFuse-ChatBot is an open-source AI assistant for the software development lifecycle, combining a multi-agent scheduling framework with D… | 28 | 1295 | active |
| SWI-Prolog SWI-Prolog is a comprehensive, open-source (BSD-2) implementation of the Prolog logic programming language, implemented in C and Prolog wit… | 97 | 1288 | stable |
| Muesli-HQ/muesli Muesli is an open-source native macOS app that combines hotkey-driven AI dictation with local meeting transcription, running speech-to-text… | 79 | 1285 | active |
| flutter-ml/google_ml_kit_flutter A set of Flutter plugins wrapping Google's ML Kit on-device machine learning APIs for Android and iOS. It provides vision APIs (barcode, fa… | 75 | 1285 | active |
| Renumics/spotlight Renumics Spotlight is an open-source tool for interactively exploring unstructured datasets (images, audio, text, video, time-series, meshe… | 89 | 1275 | active |
| jonexaiorg/jonex Jonex is an end-to-end, self-hosted AI knowledge platform combining a multimodal parsing engine (documents, video, images) with an ontology… | 56 | 1267 | active |
| TencentCloudADP/youtu-graphrag Youtu-GraphRAG is a Python framework for graph-based retrieval-augmented generation that unifies graph schema construction, community detec… | 52 | 1266 | active |
| myreader-io/myGPTReader myGPTReader is a Slack bot powered by ChatGPT that reads and summarizes webpages, documents (eBooks, PDF, DOCX), and YouTube videos, and su… | 10 | 4414 | maintenance |
| GML-MMGroup/GMTalker GMTalker is an interactive 3D digital human system rendered with Unreal Engine, integrating speech recognition, speech synthesis, natural l… | 42 | 1239 | active |
| InternScience/GraphGen GraphGen is a Python framework for knowledge-graph-guided synthetic data generation for LLM training. It builds fine-grained knowledge grap… | 53 | 1232 | active |
| OpenTSLM/OpenTSLM OpenTSLM is a family of Time-Series Language Models that integrate time series as a native modality into pretrained LLMs (Llama, Gemma), en… | 58 | 1230 | active |
| MoonshotAI/Kimi-VL Kimi-VL is an open-source Mixture-of-Experts vision-language model (VLM) with a 2.8B activated parameter language decoder, offering multimo… | 31 | 1227 | active |
| aTrainTranscription/aTrain aTrain is a desktop GUI application for offline transcription of speech recordings using Whisper-based machine learning models, with speake… | 77 | 1220 | active |
| EvolvingLMMs-Lab/LLaVA-OneVision-2 A fully open framework for training multimodal large language models, releasing models, datasets, and training recipes for the LLaVA-OneVis… | 70 | 1220 | active |
| superlinear-ai/raglite RAGLite is a Python toolkit for building Retrieval-Augmented Generation (RAG) pipelines backed by DuckDB or PostgreSQL, with hybrid keyword… | 80 | 1207 | active |
| ddlBoJack/emotion2vec Official PyTorch implementation of emotion2vec, a self-supervised pre-trained model for speech emotion representation. It provides code for… | 27 | 1197 | active |
| NVIDIA/audio-flamingo NVIDIA's PyTorch implementation of the Audio Flamingo series of large audio-language models (AF1, AF2, AF3, and Music Flamingo) for audio u… | 47 | 1195 | active |
| ALwrity/ALwrity ALwrity is an open-source, AI-first digital marketing platform built in Python that combines content strategy planning, multimodal AI conte… | 77 | 1186 | active |
| DAMO-NLP-SG/VideoLLaMA3 VideoLLaMA 3 is a frontier multimodal foundation model for image and video understanding, released with checkpoints, inference code, and de… | 34 | 1186 | active |
| mlomb/chat-analytics A web app and CLI that takes chat exports from platforms like Telegram, Discord, and WhatsApp and generates a single interactive HTML repor… | 40 | 1177 | active |
| baichuan-inc/Baichuan2 Baichuan 2 is a family of open large language models (7B and 13B, Base and Chat variants with 4-bit quantized versions) trained by Baichuan… | 28 | 4082 | maintenance |
| FlagOpen/RoboBrain2.5 RoboBrain 2.5 is an open-source embodied AI foundation model from BAAI that combines multimodal large language model capabilities with 3D s… | 47 | 1150 | active |
| amazon-science/mm-cot Official PyTorch implementation of the paper 'Multimodal Chain-of-Thought Reasoning in Language Models', which adds vision features to a tw… | 31 | 3978 | maintenance |
| microsoft/onnxruntime-genai ONNX Runtime GenAI is a C++ library with Python, C#, C/C++, and Java APIs for running generative AI models (LLMs, Whisper, vision-language … | 94 | 1142 | active |
| InternRobotics/InternNav InternNav is an open-source PyTorch-based toolbox for building embodied navigation foundation models, supporting vision-language navigation… | 52 | 1135 | active |
| NovaSearch-Team/RAG-Retrieval A Python library and toolkit for unified fine-tuning, inference, and distillation of RAG retrieval models, including embedding models, ColB… | 57 | 1131 | active |
| FutureUniant/Tailor Tailor is an AI-powered desktop video editing application offering intelligent video cutting, generation, and optimization. It provides fea… | 22 | 1128 | active |
| amazon-science/RAGChecker RAGChecker is an automatic evaluation framework for diagnosing Retrieval-Augmented Generation (RAG) systems. It provides holistic and diagn… | 15 | 1126 | active |
| FlagAI-Open/FlagAI FlagAI is a Python toolkit for training, fine-tuning, and deploying large-scale AI models across NLP, CV, and vision-language tasks. It int… | 61 | 3870 | maintenance |
| easydoc-ai/easydoc EasyDoc is a multimodal document processing API that converts unstructured documents like PDFs into hierarchical, machine-readable JSON. It… | 32 | 1114 | active |
| ycccccccy/echotrace EchoTrace is a fully local, privacy-focused desktop application for exporting, decrypting, and analyzing WeChat chat records. It generates … | 55 | 3834 | maintenance |
| minghanqin/LangSplat Official implementation of LangSplat, a CVPR 2024 Highlight paper that constructs a 3D language field using 3D Gaussian Splatting with CLIP… | 44 | 1096 | active |
| spider-ios/autox-release AutoX is a desktop social media operations tool that automates one-click publishing of videos to multiple platforms such as Douyin, TikTok,… | 60 | 1090 | active |
| rhymes-ai/Aria Aria is an open multimodal native Mixture-of-Experts (MoE) model with 25.3B total parameters (3.9B activated per token) and a 64K multimoda… | 23 | 1088 | active |
| titanwings/ex-skill A Python tool that generates Claude Code / OpenClaw agent 'skills' capturing a specific person's texting persona from chat history (WeChat,… | 56 | 1087 | active |
| kagisearch/kite-public Kite is the open-source front-end for Kagi News, a web news application that delivers daily curated, LLM-summarized news stories from diver… | 67 | 1086 | active |
| agenmod/immortal-skill An open-source 'digital immortality' framework that distills a person's persona from chat logs and documents across 12+ platforms (WeChat, … | 46 | 1074 | active |
| AILab-CVC/UniRepLKNet UniRepLKNet is a large-kernel ConvNet architecture (CVPR 2024, TPAMI 2025) that provides universal perception across image, audio, video, p… | 40 | 1074 | stable |
| mittagessen/kraken kraken is a turn-key OCR/HTR engine built on neural networks, optimized for historical and non-Latin script material. It provides trainable… | 94 | 1073 | active |
| GanymedeNil/document.ai A universal local knowledge base solution that stores documents as vectors in a vector database and uses GPT3.5 to generate answers from re… | 31 | 3666 | maintenance |
| shang-zhu/violin Violin is an open-source video translation tool that transcribes speech, translates it into 33 languages, synthesizes a native-sounding voi… | 56 | 1070 | active |
| X-LANCE/SLAM-LLM SLAM-LLM is a deep learning toolkit for training custom multimodal large language models focused on speech, language, audio, and music proc… | 52 | 1066 | active |
| CRui5in/paper-ppt-agent A self-hosted web application that uses a multi-agent AI pipeline (Strategist, Executor, Critic) to convert academic papers from PDF or LaT… | 73 | 1065 | active |
| sb-ai-lab/EmotiEffLib EmotiEffLib (formerly HSEmotion) is a lightweight library for facial emotion and engagement recognition in photos and videos, available in … | 59 | 1063 | active |
| alibaba/Alink Alink is a machine learning algorithm platform built on Apache Flink, developed by Alibaba's PAI team. It provides a large library of batch… | 23 | 3612 | maintenance |
| braintrustdata/autoevals Autoevals is a Python and TypeScript library for automatically evaluating AI model outputs using LLM-as-a-judge, heuristic, and statistical… | 91 | 1053 | active |
| wu-yc/LabClaw LabClaw is a modular library of 240 SKILL.md agent skills for biomedical AI research, covering biology, drug discovery, medicine, data scie… | 44 | 1053 | active |
| ml-tooling/ml-workspace ML Workspace is an all-in-one web-based IDE Docker image specialized for machine learning and data science. It bundles Jupyter, JupyterLab,… | 23 | 3546 | maintenance |
| agents-flex/agents-flex Agents-Flex is a lightweight, modular Java framework for building AI applications and agents, positioned as a Java counterpart to Spring AI… | 91 | 1032 | active |
| ocropus-archive/DUP-ocropy OCRopy is a collection of Python-based tools for document analysis and OCR, covering binarization, page layout analysis, and text line reco… | 10 | 3464 | maintenance |
| Towhee Towhee is a Python framework for building ETL pipelines that process unstructured data (images, video, text, audio) into embeddings using s… | 23 | 3451 | maintenance |
| octimot/StoryToolkitAI StoryToolkitAI is a desktop film editing tool that transcribes, indexes, and semantically searches video footage locally, using speech reco… | 62 | 1016 | active |
| EvolvingLMMs-Lab/Otter Otter is a multi-modal vision-language model built on OpenFlamingo, instruction-tuned on the MIMIC-IT dataset with image and video understa… | 21 | 3445 | maintenance |
| ZJUI-AI4H/Hulu-Med Hulu-Med is a family of open-source transparent generalist medical vision-language models ranging from 4B to 235B parameters, covering text… | 59 | 1006 | active |
| PrithivirajDamodaran/FlashRank FlashRank is an ultra-light, fast Python library for re-ranking search and retrieval results using SoTA cross-encoders and listwise LLM-bas… | 55 | 1006 | active |
| siyuanchen0214/Scam-AI-Multi-modal-Evaluation-System A Python-based multi-modal AI system for detecting fraudulent content across text, image, audio, and video, with provenance tracing and cro… | 36 | 1002 | active |
| catalyst-team/catalyst Catalyst is a high-level PyTorch framework for deep learning research and development, focused on reproducibility, rapid experimentation, a… | 60 | 3386 | maintenance |
| Loofah Loofah is a Ruby library built on Nokogiri for manipulating and transforming HTML/XML documents and fragments, including a framework for wr… | 87 | 1000 | stable |
| Image Captioning A PyTorch research codebase for image captioning, serving as the widely used unofficial implementation of Self-critical Sequence Training (… | 23 | 999 | stable |
| resemble-ai/Resemblyzer Resemblyzer is a Python package that uses a deep learning voice encoder to convert speech audio into 256-dimensional voice embeddings. Thes… | 23 | 3304 | maintenance |
| bytedance/lightseq LightSeq is a high-performance CUDA-based library for training and inference of sequence models like Transformer, BERT, GPT, and BART, with… | 10 | 3292 | maintenance |
| huawei-noah/Pretrained-Language-Model A collection of pretrained language models and optimization techniques from Huawei Noah's Ark Lab, including PanGu-α (200B-parameter Chines… | 32 | 3166 | maintenance |
| Conchylicultor/DeepQA DeepQA is a TensorFlow implementation of Google's 'A Neural Conversational Model', a seq2seq RNN-based deep learning chatbot. It supports t… | 32 | 2906 | maintenance |
| cskefu/cskefu CSKeFu (Chunsong Customer Service) is an open-source enterprise customer service / contact center platform providing agent workbenches, con… | 66 | 2901 | maintenance |
| alisen39/TrWebOCR TrWebOCR is an open-source offline Chinese OCR service built on the Tr project, exposing both a web UI and HTTP API for text recognition. I… | 23 | 2878 | maintenance |
| readbeyond/aeneas aeneas is a Python/C library and set of CLI tools that automatically computes forced alignments, generating a synchronization map between a… | 62 | 2867 | maintenance |
| tensorflow/lingvo Lingvo is a TensorFlow-based framework for building neural networks, particularly sequence models, with a focus on speech recognition, mach… | 68 | 2864 | maintenance |
| illuin-tech/colpali ColPali Engine is the Python library for training and running inference with ColVision visual document retrieval models such as ColPali, Co… | 82 | 2836 | maintenance |
| yanqiangmiffy/Chinese-LangChain A Chinese-language local knowledge base question-answering application built on ChatGLM-6B and LangChain, with a Gradio web UI. It supports… | 30 | 2823 | maintenance |
| microsoft/NUWA Microsoft's official research repository for the NUWA family of multimodal generative models, a unified 3D transformer pipeline for visual … | 10 | 2788 | maintenance |
| InsiderX-Pro/video-translator An OpenClaw agent skill (written in Shell/Python) that translates and dubs videos by submitting jobs to a remote video-translation service … | 51 | 812 | active |
| ctripcorp/C-OCR C-OCR is Ctrip's in-house OCR project focused on recognizing travel-related documents such as ID cards, passports, train tickets, and visas… | 32 | 2477 | maintenance |
| zai-org/CogVLM2 CogVLM2 is an open-source multi-modal vision-language model family built on Meta-Llama-3-8B-Instruct, offering image and video understandin… | 25 | 2429 | maintenance |
| microsoft/DialoGPT DialoGPT is a large-scale pretrained dialogue response generation model from Microsoft, based on GPT-2 and trained on 147M multi-turn Reddi… | 10 | 2422 | maintenance |
| OpenBMB/CPM-Bee CPM-Bee is a fully open-source, commercially usable 10-billion-parameter bilingual (Chinese-English) foundation large language model traine… | 68 | 2408 | maintenance |
| allenai/RL4LMs RL4LMs is a modular Python library from AllenAI for fine-tuning language models with reinforcement learning to align with human preferences… | 32 | 2396 | maintenance |
| magicrew/doc7 doc7 is a Go CLI tool that converts PDFs, Office files, scans, screenshots, charts, formulas, and diagrams into AI-ready Markdown using any… | 72 | 721 | active |