1.huggingface / transformers
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
+5,624 stars
from 162,796 · score 8.63
Trending repositories
Ranked by Attention Score: stars gained over the last 90 complete days
38 repositories by Attention Score · Aug 5, 2026 – Nov 2, 2026 (UTC)
2.d2l-ai / d2l-zh
《动手学深度学习》：面向中文读者、能运行、可讨论。中英文版被70多个国家的500多所大学用于教学。
+3,079 stars
from 79,117 · score 8.03
3.srbhr / Resume-Matcher
The #1 AI Harness for Building Resumes, PDFs, Cover Letters & more, locally with 100+ LLMs support.
+1,217 stars
from 27,819 · score 7.10
4.d2l-ai / d2l-en
Interactive deep learning book with multi-framework code, math, and discussions. Adopted at 500 universities from 70 countries including Stanford, MIT, Harvard, and Cambridge.
+781 stars
from 29,201 · score 6.66
5.camel-ai / camel
🐫 CAMEL: The first and the best multi-agent framework. Finding the Scaling Law of Agents. https://www.camel-ai.org
+551 stars
from 17,456 · score 6.31
6.QwenLM / Qwen
The official repo of Qwen (通义千问) chat & pretrained large language model proposed by Alibaba Cloud.
+543 stars
from 21,440 · score 6.30
7.huggingface / datasets
🤗 The largest hub of ready-to-use datasets for AI models with fast, easy-to-use and efficient data manipulation tools
+348 stars
from 21,754 · score 5.86
8.explosion / spaCy
💫 Industrial-strength Natural Language Processing (NLP) in Python
+289 stars
from 33,721 · score 5.67
9.autogluon / autogluon
Fast and Accurate ML in 3 Lines of Code
+261 stars
from 10,546 · score 5.57
10.arc53 / DocsGPT
Private AI platform for agents, assistants and enterprise search. Built-in Agent Builder, Deep research, Document analysis, Multi-model support, and API connectivity for agents.
+225 stars
from 18,127 · score 5.42
11.hankcs / HanLP
中文分词 词性标注 命名实体识别 依存句法分析 成分句法分析 语义依存分析 语义角色标注 指代消解 风格转换 语义相似度 新词发现 关键词短语提取 自动摘要 文本分类聚类 拼音简繁转换 自然语言处理
+154 stars
from 36,378 · score 5.04
12.OpenMOSS / MOSS
An open-source, tool-augmented conversational language model from Fudan University
+142 stars
from 12,185 · score 4.96
13.RasaHQ / rasa
💬 Open source machine learning framework to automate text- and voice-based conversations: NLU, dialogue management, connect to Slack, Facebook, and more - Create chatbots and voice assistants
+136 stars
from 21,228 · score 4.92
14.nltk / nltk
NLTK Source
+113 stars
from 14,650 · score 4.74
15.doccano / doccano
Open source annotation tool for machine learning practitioners.
+95 stars
from 10,713 · score 4.56
16.ludwig-ai / ludwig
Low-code framework for building custom LLMs, neural networks, and other AI models
+69 stars
from 11,723 · score 4.25
17.RUCAIBox / LLMSurvey
The official GitHub page for the survey paper "A Survey of Large Language Models".
+67 stars
from 12,162 · score 4.22
18.stanfordnlp / stanza
Stanford NLP Python library for tokenization, sentence segmentation, NER, and parsing of many human languages
+65 stars
from 7,840 · score 4.19
19.piskvorky / gensim
Topic Modelling for Humans
+62 stars
from 16,446 · score 4.14
20.google-research / bertArchived
TensorFlow code and pre-trained models for BERT
+52 stars
from 39,985 · score 3.97
21.sebastianruder / NLP-progress
Repository to track the progress in Natural Language Processing (NLP), including the datasets and the current state-of-the-art for the most common NLP tasks.
+41 stars
from 22,913 · score 3.74
22.flairNLP / flair
A very simple framework for state-of-the-art Natural Language Processing (NLP)
+29 stars
from 14,366 · score 3.40
23.clips / pattern
Web mining module for Python, with tools for scraping, natural language processing, machine learning, network analysis and visualization.
+22 stars
from 8,835 · score 3.14
24.MycroftAI / mycroft-coreArchived
Mycroft Core, the Mycroft Artificial Intelligence platform.
+15 stars
from 6,602 · score 2.77
25.keras-team / keras-hub
Pretrained model hub for Keras 3.
+15 stars
from 982 · score 2.77
26.allenai / allennlpArchived
An open-source NLP research library, built on PyTorch.
+13 stars
from 11,870 · score 2.64
27.chiphuyen / stanford-tensorflow-tutorialsArchived
This repository contains code examples for the Stanford's course: TensorFlow for Deep Learning Research.
+13 stars
from 10,359 · score 2.64
28.jerryji1993 / DNABERT
DNABERT: pre-trained Bidirectional Encoder Representations from Transformers model for DNA-language in genome
+13 stars
from 770 · score 2.64
29.catalyst-team / catalyst
Accelerated deep learning R&D
+10 stars
from 3,378 · score 2.40
30.asyml / texar
Toolkit for Machine Learning, Natural Language Processing, and Text Generation, in TensorFlow. This is part of the CASL project: http://casl-project.ai/
+5 stars
from 2,388 · score 1.79
31.ncbi-nlp / bluebert
BlueBERT, pre-trained on PubMed abstracts and clinical notes (MIMIC-III).
+4 stars
from 596 · score 1.61
32.harmonydata / harmony
The Harmony Python library: a research tool for psychologists to harmonise data and questionnaire items. Open source.
+4 stars
from 63 · score 1.61
33.turtlesoupy / this-word-does-not-exist
This Word Does Not Exist
+3 stars
from 1,021 · score 1.39
34.NLPatVCU / medaCy
:hospital: Medical Text Mining and Information Extraction with spaCy
+3 stars
from 439 · score 1.39
35.Maluuba / nlg-eval
Evaluation code for various unsupervised automated metrics for Natural Language Generation.
+2 stars
from 1,390 · score 1.10
36.uber-research / PPLM
Plug and Play Language Model implementation. Allows to steer topic and attributes of GPT-2 models.
+1 stars
from 1,152 · score 0.69
37.shawnwun / RNNLG
RNNLG is an open source benchmark toolkit for Natural Language Generation (NLG) in spoken dialogue system application domains. It is released by Tsung-Hsien (Shawn) Wen from Cambridge Dialogue Systems Group under Apache License 2.0.
+1 stars
from 490 · score 0.69
38.geeks-of-data / knowledge-gpt
Extract knowledge from all information sources using gpt and other language models. Index and make Q&A session with information sources.
+1 stars
from 291 · score 0.69