NLP: open-source projects on GitHub
84 repositories on NLP, picked by the REDDYX AI agent. Each has a summary, key features and a breakdown. Sorted by stars.
// RELATED TOPICS
🤗 Transformers
A framework for defining machine learning models in text, vision, audio, and multimodal models, for inference and training.
★ 160,482 · PythonLlamaFactory: Unified LLM Tuning
LlamaFactory offers a unified library for efficient fine‑tuning of 100+ LLMs and VLMs, with support for LoRA, QLoRA and distributed multi‑GPU training.
★ 71,186 · PythonLangExtract Data Extraction
Python library for extracting structured data from text using LLM: precise source grounding and interactive visualization.
★ 36,452 · PythonAdvanced RAG Techniques
The repository demonstrates various advanced methods for Retrieval-Augmented Generation (RAG) systems with detailed tutorials in Jupyter Notebook format.
★ 27,523 · Jupyter NotebookHaystack: AI Framework for LLM
An open framework for building production-ready LLM applications with modular control over search, routing, memory, and generation.
★ 25,289 · MDXUNILM POWERFUL PRETRAINED MODEL
UniLM is a large-scale self-supervised pretrained model covering tasks, languages, and modalities. It supports BEiT, BEiT-3, BitNet, DeepNet, and Document AI, written in
★ 22,242 · PythonOPEN-SOURCE FINANCIAL LLMS FOR DATA ANALYSIS
FinGPT is a suite of open-source financial large language models from AI4Finance Foundation. The project offers lightweight fine-tuning (under $300) instead of full train
★ 21,591 · Jupyter NotebookDATASETS - HUGE DATABASE FOR AI
The largest platform with ready-made datasets for training AI models, offering fast and convenient tools for working with data.
★ 21,583 · PythonAI Agent Memory File
Replaces complex RAG pipelines with a serverless memory layer for AI agents, enabling instant search.
★ 15,579 · RustDocument Structuring
An open ETL solution for converting complex documents into clean structured data formats for language models.
★ 14,764 · HTMLGPT Agents Without Pain
Open platform for creating and deploying LLM agents with visual builder support and integration with popular models.
★ 14,711 · TypeScriptTXTAI — AI All-in-One
An algorithmic framework for semantic search, LLM orchestration, and language-model workflows. All in one!
★ 12,620 · PythonOPTIMIZATION AND DEPLOYMENT OF AI MODELS
Toolkit for optimizing and deploying deep learning models. Supports conversion from PyTorch, TensorFlow, ONNX and inference on CPU, GPU, and Intel NPU.
★ 11,656 · C++AI engineering from scratch
Learn, build it, and deliver it to others.
★ 7,884 · PythonAI Humanizer for Korean
A Python project that turns machine‑generated Korean text into natural human‑like prose, fixing translationese and 71 AI indicators.
★ 6,547 · PythonSMILE - AI ENGINE ON JAVA
SMILE — Statistical Machine Intelligence & Learning Engine, a powerful framework for building machine learning models in Java.
★ 6,438 · JavaTRAFILATURA - FAST WEB PARSE
Trafilatura extracts clean text and metadata from pages, supporting CSV, JSON, HTML and other formats.
★ 6,055 · PythonEASYR1: MULTIMODAL RL TRAINING
EasyR1 is a scalable framework for multimodal reinforcement learning training on veRL, delivering high efficiency and ease of use.
★ 5,215 · PythonARGILLA - CREATE DATASETS FASTER
Argilla helps AI engineers and domain experts collaboratively create high-quality datasets for training models.
★ 5,203 · PythonSPARK-NLP - REVOLUTION IN NLP
Spark NLP provides state-of-the-art NLP models and ready-to-use pipelines for scalable text processing in Scala.
★ 4,163 · ScalaGIGATOKEN — GB/s Tokenization
gigatoken — fast tokenization of language models in Rust, achieving gigabyte-per-second speeds.
★ 4,155 · RustAdalFlow - Boost LLM Efficiency
A library for building and auto-optimizing LLM-based applications in Python. Simplifies working with prompts and model configuration.
★ 4,153 · PythonLightLLM - Fast LLM Inference
A lightweight and fast framework for inference and serving of large language models in Python. Simple scaling and high performance.
★ 4,092 · PythonHUMANIZE-TEXT AI INTO HUMAN TEXT
Open-source AI‑humanizer converts AI‑generated text into natural human style. Uses SFT + KTO pipeline and a translation chain via DeepSeek, OpenRouter and n8n. Transparen
★ 3,512 · PythonNatural Japanese Rewriting Skill
A Python agent skill that rewrites AI-generated text into natural, human-like Japanese.
★ 3,267 · PythonLLM Agents: Best Works
A curated list of essential papers on agents based on large language models.
★ 3,030DIY-LLM: FULL LLM COURSE WITH CODE
The diy-llm project offers six step‑by‑step Jupyter notebooks covering data pre‑training, tokenization, Transformer, MoE, distributed training, scaling laws, inference an
★ 2,960 · Jupyter NotebookBOOTCAMP: MULTIMODAL DATA
The bootcamp project brings together tools for working with unstructured data: reverse image, audio, video, molecular search, and NLP tasks.
★ 2,453 · Jupyter NotebookSelf-Coding System for Web
Alan AI SDK for web adds a self-coding AI agent to any application, accelerating development and automating routine tasks.
★ 2,421EXCELLENT LIST OF CHATGPT RESOURCES
A curated list of the best libraries, SDKs, and APIs for working with ChatGPT. Support the project by starring it!
★ 2,419POWERFUL CHATGPT LIBRARY
Open source JavaScript library for working with ChatGPT. 2000+ stars on GitHub!
★ 2,037 · JavaScriptSUPERLINKED INFERENCE ENGINE
Open-source server for embedding inference, reranking, and data extraction. 2000+ stars on GitHub.
★ 2,029 · PythonRAGHUB: Resources and RAG Frameworks
The community gathers the best RAG frameworks, projects, and materials for AI developers. Contribute and discover new solutions.
★ 2,019CONTEXTGEM: LLM DOCUMENT EXTRACTION
ContextGem lets you extract structured data from any document using LLMs without complex code.
★ 1,844 · PythonPaper Figure Gallery
A gallery of 3,516 Figure 1 teasers from ICLR, ICML, NeurIPS, CVPR, ACL, AAAI papers (2023-2026) with tier badges and FigureForge-powered retrieval-augmented drafting.
★ 1,616 · PythonEXTRACTTHINKER DOCUMENT INTELLIGENCE
ExtractThinker — an ORM‑style library for LLM integration, including LangChain and LlamaIndex, that streamlines parsing of PDF, DOCX and images, performs layout and analy
★ 1,605 · PythonLLM IN SPACY PIPELINE PAINLESSLY
spacy-llm connects GPT, Claude, Cohere and open models to spaCy pipeline. Configure via config, get structured Doc with entities and relations. No wrapper code — pure NLP
★ 1,399 · PythonMAKE MONEY WITH AI PROJECTS
A collection of open AI projects in Python that will help you quickly monetize ideas and automate earnings.
★ 1,221 · PythonNNCFF - ACCELERATING MODEL INFERENCE
NNCFF is a neural network compression framework for accelerated inference in OpenVINO™. It reduces model size while preserving accuracy.
★ 1,221 · PythonAI LEARNING: ROADMAPS
Complete set of roadmaps and resources for AI, ML, DL, and Data Science — from beginner to expert.
★ 1,195RAG-RETRIEVAL UNIFY SEARCH
The project unifies efficient fine-tuning of RAG search methods: embeddings, ColBERT, and reranker.
★ 1,138 · PythonONTOGPT: ONTOLOGY EXTRACTION
Ontogpt — an LLM‑tool for extracting ontologies from text, including the SPIRES method. It builds hierarchical taxonomies and generates OWL/RDF schemas ready for use in d
★ 1,099 · Jupyter NotebookJapanese NLP: Top Resources
A collection of libraries, models, corpora, and datasets for Japanese language processing in Python. Includes Claude Code skills for quick resource discovery.
★ 1,031Keras Hub: Models for Keras
Platform with ready-to-use pretrained models for Keras 3, simplifying AI integration into projects.
★ 999 · PythonJEVOS: BINARY DECISIONS ON LAPTOP
Jevos is an open-source Jev alternative for yes/no decisions. Runs fully locally on CPU via FastAPI. Data never leaves your device.
★ 963 · PythonDEEPGIT: GITHUB HUNTER
DeepGit — a Python agent for finding the best GitHub repositories by topic. It uses LangChain and LangGraph to perform deep code and documentation analysis. Returns a sor
★ 929 · PythonMASCOT: Multi-Agent Assistant
MASCOT is a multi-agent socially collaborative assistant presented at EMNLP 2026. The project is implemented in Python and has already garnered 518★.
★ 804 · PythonSEARCHGPT: AI SEARCH WITH SOURCES
SearchGPT — an LLM‑based search engine that returns answers with source citations. It supports web and local file search, providing verifiable information. Works via Open
★ 711 · PythonRANKIFY: TOOL FOR RAG
Rankify — Python toolkit for search, reranking, and RAG. Includes 40 benchmark datasets, 7+ search methods and 24+ ranking models. Supports multiple RAG schemes and easy
★ 683 · PythonRepo for LLM Unlearning
A collection of papers, code, and resources on machine 'unlearning' in large language models. Helps researchers remove knowledge from LLMs.
★ 638TRUSTLLM: EVALUATION OF LLM TRUSTWORTHINESS
TrustLLM — a toolkit for assessing LLM trustworthiness, presented at ICML 2024. It includes benchmark suites, metrics, and datasets for measuring hallucinations, bias, an
★ 636 · PythonSYCAMORE: AI DATA SEARCH
Sycamore — an LLM-based platform for searching and analyzing unstructured data. Allows quick extraction of insights from texts, documents, and logs.
★ 606 · PythonOpenChatBI: AI Chat for Data
OpenChatBI — an LLM‑powered chatbot that turns natural language queries into SQL and visualizes data.
★ 571 · PythonAI PERSONALIZED EXAM SYSTEM
🧠 Adaptive system for generating exam questions based on LLM, knowledge graph, and BKT algorithm.
★ 531 · PythonAI ASSISTANT FOR SUBLIME TEXT
Integration of GPT‑5, Opus 4.6, Gemini 3 and Ollama in Sublime Text for instant code and autocompletion.
★ 467 · PythonPYTORCH REPLICATIONS OF SOTA PAPERS
429 stars. From-scratch implementations of transformers, diffusion, GAN, CLIP, LoRA, MoE in Jupyter Notebook. Includes SFT and GRPO post-training experiments.
★ 430 · Jupyter NotebookAI AGENTS BREAKTHROUGHS ARCHIVE
Key papers on agents, architecture, training, RAG, and on-device AI. Up-to-date research in one repository.
★ 426ADAPTIVE CHUNKING FOR RAG
Automatically selects the optimal chunking method for each document to improve RAG pipelines. Accepted at LREC 2026.
★ 404 · PythonPATINA: AI PATTERN REMOVAL
Patina finds and rewrites AI text patterns in four languages. Works as a skill for Claude Code, Codex CLI, Cursor, OpenCode and as a Node.js CLI.
★ 388 · JavaScriptCURATED RESOURCES FOR MLLM
Awesome_Multimodel_LLM — curated collection for multimodal LLM: datasets, fine-tuning, visual reasoning, in-context learning. 379★ on GitHub. All latest MLLM resources in
★ 379New projects on this topic in Telegram
Telegram →