Nirant

financial-agent-india. AI-powered financial analysis agent for Indian stock markets using AngelOne SmartAPI + Claude

mcp-server-chart. 🤖 A visualization mcp & skills contains 25+ visual charts using @antvis. Using for chart generation and data analysis.

kura. Kura is a simple reproduction of the CLIO paper which uses language models to label user behaviour before clustering them based on embeddings recursively. This helps us understand user behaviour on a higher level without sacrificing PII.

massive-serve. Python package for serving a local search engine. One command to download and serve a datastore---that's it 😎.

langgraph-whatsapp-agent. A template for building WhatsApp agents using LangGraph and Twilio. This project enables you to deploy AI agents that interact with users via WhatsApp, process messages and images, and invoke custom graph-based agents. It integrates with MCP and runs on the LangGraph Platform.

browserable. Open source and self-hostable browser automation library for AI agents

cucom.

shell_sage. ShellSage saves sysadmins’ sanity by solving shell script snafus super swiftly

docetl. A system for agentic LLM-powered data processing and ETL

EmbedAnything. Highly Performant, Modular, Memory Safe and Production-ready Inference, Ingestion and Indexing built in Rust 🦀

flex-mining. code for turning data sets into trading strategies

vector-io. Comprehensive Vector Data Tooling. The universal interface for all vector database, datasets and RAG platforms. Easily export, import, backup, re-embed (using any model) or access your vector data from any vector databases or repository.

neural-cherche. Neural Search

quantstats. Portfolio analytics for quants, written in Python

qdrant-spark. Qdrant's Apache Spark connector

CompanionLLM. CompanionLLM - A framework to finetune LLMs to be your own sentient conversational companion

onprem. A toolkit for applying LLMs to sensitive, non-public data in offline or restricted environments

ragas. Supercharge Your LLM Application Evaluations 🚀

fastembed. Fast, Accurate, Lightweight Python library to make State of the Art Embedding

airoboros. Customizable implementation of the self-instruct paper.

llama2.rs. A mimimal Rust implementation of Llama.c

LLaMA2-Accessory. An Open-source Toolkit for LLM Development

nanoT5. Fast & Simple repository for pre-training and fine-tuning T5-style models

app. Prem App it's your personal AI in your pocket

mpt-30B-inference. Run inference on MPT-30B using CPU

mem0. Universal memory layer for AI Agents

datacomp. DataComp: In search of the next generation of multimodal datasets

qdrant. Qdrant - High-performance, massive-scale Vector Database and Vector Search Engine for the next generation of AI. Also available in the cloud https://cloud.qdrant.io/

langchain. The agent engineering platform.

chatgpt-memory. Allows to scale the ChatGPT API to multiple simultaneous sessions with infinite contextual and adaptive memory powered by GPT and Redis datastore.

llama-dl. High-speed download of LLaMA, Facebook's 65B parameter GPT model

tortoise-tts. A multi-voice TTS system trained with an emphasis on quality

lance. Open Lakehouse Format for Multimodal AI. Convert from Parquet in 2 lines of code for 100x faster random access, vector index, and data versioning. Compatible with Pandas, DuckDB, Polars, Pyarrow, and PyTorch with more integrations coming..

summ. GPT-based Conversation Summarizer

backend-GPT. JavaScript

langchain-hub. Python

whisper. Robust Speech Recognition via Large-Scale Weak Supervision

whisper.cpp. Port of OpenAI's Whisper model in C/C++

tiktoken. tiktoken is a fast BPE tokeniser for use with OpenAI's models.

howdoi.ai. howdoi.ai

scanpix. Jupyter Notebook

voiceliner. Braindump better.

latus. Nearest neighbor search with integrated filtering

goose. A powerful background job processing library for Clojure

label-sleuth. Open source no-code system for text annotation and building of text classifiers

chalk. A declarative drawing API in Python

course22. The fast.ai course notebooks

malloy. Malloy is a modern open source language for describing data relationships and transformations.

classy. classy is a simple-to-use library for building high-performance Machine Learning models in NLP.

concise-concepts. This repository contains an easy and intuitive approach to few-shot NER using most similar expansion over spaCy embeddings. Now with entity scoring.

investpy. Financial Data Extraction from Investing.com with Python

outputformat. Python library to decorate and beautify strings

obsei. Obsei is a low code AI powered automation tool. It can be used in various business flows like social listening, AI based alerting, brand image analysis, comparative study and more .

mindmeld. An Open Source Conversational AI Platform for Deep-Domain Voice Interfaces and Chatbots.

gradio. Build and share delightful machine learning apps, all in Python. 🌟 Star to support our work!

template. This is the repository for the distill web framework

fastai-nbstripout. much faster nbstripout and autotrust notebooks local git configuration

bootleg. Self-Supervision for Named Entity Disambiguation at the Tail

adapters. A Unified Library for Parameter-Efficient and Modular Transfer Learning

indicnlp_catalog. A collaborative catalog of NLP resources for Indic languages

my-cs-degree. A CS degree with a focus on full-stack ML engineering, 2020

camphr. Camphr - NLP libary for creating pipeline components

Pluto.jl. 🎈 Simple reactive notebooks for Julia

nlp-roadmap. ROADMAP(Mind Map) and KEYWORD for students those who have interest in learning NLP

seirsplus. Models of SEIRS epidemic dynamics with extensions, including network-structured populations, testing, contact tracing, and social distancing.

covid-19-data. A repository of data on coronavirus cases and deaths in the U.S.

noisystudent. Code for Noisy Student Training. https://arxiv.org/abs/1911.04252

ARBML. Implementation of many Arabic NLP and CV projects. Providing real time experience using many interfaces like web, command line and notebooks.

hello_nbdev. A tutorial example for nbdev

awesome-danish. A curated list of awesome resources for Danish language technology

nbdev. Create delightful software with Jupyter Notebooks

sha-rnn. Single Headed Attention RNN - "Stop thinking with your head"

machine-learning-systems-design. A booklet on machine learning systems design with exercises. NOT the repo for the book "Designing Machine Learning Systems", which is `dmls-book`

projects. 🪐 End-to-end NLP workflows from prototype to production

bulldog. State management framework for Data Science & Analytics

CodeSearchNet. Datasets, tools, and benchmarks for representation learning of code.

transformer. A collection of resources to study Transformers in depth.

Mongoku. 🔥The Web-scale GUI for MongoDB

unlikelihood_training. Neural Text Generation with Unlikelihood Training

rankqa. This is the PyTorch implementation of the ACL 2019 paper RankQA: Neural Question Answering with Answer Re-Ranking.

nlpaug. Data augmentation for NLP

sentence-transformers. State-of-the-Art Embeddings, Retrieval, and Reranking

moe. Misspelling Oblivious Word Embeddings

pyforest. pyforest - feel the bliss of automated imports

vampire. Variational Methods for Pretraining in Resource-limited Environments

personal-website. Repository hosting code of Deven Bansod's personal website

spacy-transformers. 🛸 Use pretrained transformers like BERT, XLNet and GPT-2 in spaCy

transfer-learning-conv-ai. 🦄 State-of-the-Art Conversational AI with Transfer Learning

rank_bm25. A Collection of BM25 Algorithms in Python

conv-emotion. This repo contains implementation of different architectures for emotion recognition in conversations.

danlp. DaNLP is a repository for Natural Language Processing resources for the Danish Language.

MELD. MELD: A Multimodal Multi-Party Dataset for Emotion Recognition in Conversation

recommenders. Best Practices on Recommendation Systems

grover. Code for Defending Against Neural Fake News, https://rowanzellers.com/grover/

mt-dnn. Multi-Task Deep Neural Networks for Natural Language Understanding

langrank. A program to choose transfer languages for cross-lingual learning

fastai-vision-app. Starter Pack for creating fast responsive Web App for Fast.AI Vision models

transfer-nlp. NLP library designed for reproducible experimentation management

Deep-Learning-in-Production. In this repository, I will share some useful notes and references about deploying deep learning-based models in production.

Genomic-ULMFiT. ULMFiT for Genomic Sequence Data

course-starter-python. 👩‍🏫🐍 Starter repo for building interactive Python courses

conversational-datasets. Large datasets for conversational AI

LAMA. LAnguage Model Analysis

wheelwright. 🎡 Automated build repo for Python wheels and source packages

scibert. A BERT model for scientific text.

textpipe. Textpipe: clean and extract metadata from text

code-server. VS Code in the browser

ludwig. Low-code framework for building custom LLMs, neural networks, and other AI models

pytorch-semseg. Semantic Segmentation Architectures Implemented in PyTorch

insuranceQA. A question answering corpus in insurance domain

multifit. The code to reproduce results from paper "MultiFiT: Efficient Multi-lingual Language Model Fine-tuning" https://arxiv.org/abs/1909.04761

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.

bert. TensorFlow code and pre-trained models for BERT

nlp_course. YSDA course in Natural Language Processing

ml-interview. Preparing for machine learning interviews

PyMuPDF. PyMuPDF is a high performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.

prodigy-recipes. 🍳 Recipes for the Prodigy, our fully scriptable annotation tool

nvtop. GPU & Accelerator process monitoring for AMD, Apple, Huawei, Intel, NVIDIA and Qualcomm

flair. A very simple framework for state-of-the-art Natural Language Processing (NLP)

Know-Your-Intent. State of the Art results in Intent Classification using Sematic Hashing for three datasets: AskUbuntu, Chatbot and WebApplication.

Intent-Classification-Benchmark. Intent classification benchmarks on Chatbot, AskUbuntu and WebApplication corpus

fastai_playground. Notebooks of experiences with the fastai library

MNIST_Pytorch_python_and_capi. This is an example of how to train a MNIST network in Python and run it in c++ with pytorch 1.0

tf-fit. Fit your tensorflow model using fastai and PyTorch

pytorch-web-deploy. Simple, fast web deployment for your PyTorch models

RESIDE. EMNLP 2018: RESIDE: Improving Distantly-Supervised Neural Relation Extraction using Side Information

OCR-CRNN-CTC. ocr, cnn+lstm+ctc, crnn, recognition model, tensorflow

cnn_lstm_ctc_ocr. Tensorflow-based CNN+LSTM trained with CTC-loss for OCR

crnn-pytorch. Pytorch implementation of OCR system using CRNN + CTCLoss

python-machine-learning-book-2nd-edition. The "Python Machine Learning (2nd edition)" book code repository and info resource

style_transfer. Style Transfer as Optimal Transport

SiameseULMFiT. ULMFiT + Siamese Network for Sentence Vectors

loss-landscape. Code for visualizing the loss landscape of neural nets

jiant. jiant is an nlp toolkit

Food-Recipe-CNN. food image to recipe with deep convolutional neural networks.

gpu-hog. Run many jobs on multiple GPUs programatically

fastai_old. OLD REPO - PLEASE USE fastai/fastai

Semantic-Segmentation-Suite. Semantic Segmentation Suite in TensorFlow. Implement, train, and test new Semantic Segmentation models easily!

mtp. Multi-lingual Text Processing

ReadToMe. QML

zalo_landmark. Zalo landmark identification challenge, 103 classes, > 100k images (PyTorch)

Neural_Arithmetic_Logic_Units. This is the code for "Neural Arithmetic Logic Units" By Siraj Raval on Youtube

rasa-demo. :tiger: Sara - the Rasa Demo Bot: An example of a contextual AI assistant built with the open source Rasa Stack

cloud-gpus. This repository contains information about Cloud GPU offerings for Machine Learning practitioners.

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.

GetCards. Notebook to download machine learning flashcards

Grokking-Deep-Learning. this repository accompanies the book "Grokking Deep Learning"

albumentations. Fast and flexible image augmentation library. Paper about the library: https://www.mdpi.com/2078-2489/11/2/125

Adam-experiments. Experiments with Adam/AdamW/amsgrad

semi-auto-image-annotation-tool. Anno-Mage: A Semi Automatic Image Annotation Tool which helps you in annotating images by suggesting you annotations using user-defined labels

LASER. Language-Agnostic SEntence Representations

InferSent. InferSent sentence embeddings

pytorch-openai-transformer-lm. 🐥A PyTorch implementation of OpenAI's finetuned transformer language model with a script to import the weights pre-trained by OpenAI

Deep-Learning-for-Recommendation-Systems. This repository contains Deep Learning based articles , paper and repositories for Recommender Systems

gt-nlp-class. Course materials for Georgia Tech CS 4650 and 7650, "Natural Language"

nbsvm. Naive Bayes SVM for Sentiment Analysis

nlp-architect. A model library for exploring state-of-the-art deep learning topologies and techniques for optimizing Natural Language Processing neural networks

Detectron.pytorch. A pytorch implementation of Detectron. Both training from scratch and inferring directly from pretrained Detectron weights are available.

pytorchviz. A small package to create visualizations of PyTorch execution graphs

refined-github. :octocat: Browser extension that simplifies the GitHub interface and adds useful features

FastPhotoStyle. Style transfer, deep learning, feature transform

fastai. The fastai deep learning library

fast-xnor-net. Hopefully fast implementation of XNOR-Net in C, because, why not?

Deep-Learning. A few notebooks about deep learning in pytorch

jellyfish. 🪼 a python library for doing approximate and phonetic matching of strings.

dateparser. python parser for human readable dates

PyTorch-NLP. Basic Utilities for PyTorch Natural Language Processing (NLP)

parfit. A package for parallelizing the fit and flexibly scoring of sklearn machine learning models, with visualization routines.

NLPre. Python library for Natural Language Preprocessing (NLPre)

jest-expect-codemod. CodeMods for migrating `chai.assert`, `chai.expect`, `assert` -based test assertions to jest's `expect` assertions

alta. The Art of Literary Text Analysis

cnnimageretrieval. CNN Image Retrieval in MatConvNet: Training and evaluating CNNs for Image Retrieval in MatConvNet

lore. Lore makes machine learning approachable for Software Engineers and maintainable for Machine Learning Researchers

vision. Datasets, Transforms and Models specific to Computer Vision

featuretools. An open source python library for automated feature engineering

hindi-tokenizer. This is a package in Python which implements a tokenizer, stemmer for Hindi language

thai2fit. ULMFit Language Modeling, Text Feature Extraction and Text Classification in Thai Language. Created as part of pyThaiNLP

pytorch-vqa. Strong baseline for visual question answering

Simple-Yet-Hackable-WhatsApp-api. There is no official WhatsApp API. Here is a simple python class which satisfies the need.

shap. A game theoretic approach to explain the output of any machine learning model.

pastalog. Simple, realtime visualization of neural network training performance.

fastai-docker-deprecated. Fast.AI course complete docker container for Paperspace and Gradient

courses. fast.ai Courses

lolviz. A simple Python data-structure visualization tool for lists of lists, lists, dictionaries; primarily for use in Jupyter notebooks / presentations

profile-summary-for-github. Tool for visualizing GitHub profiles

Screenshot-to-code. A neural network that transforms a design mock-up into a static website.

papers. Research papers I read

mead-baseline. Deep-Learning Model Exploration and Development for NLP

Detectron. FAIR's research platform for object detection research, implementing popular algorithms like Mask R-CNN and RetinaNet.

DUP-ocropy. Python-based tools for document analysis and OCR

SparseConvNet. Submanifold sparse convolutional networks

annoy. Approximate Nearest Neighbors in C++/Python optimized for memory usage and loading/saving to disk

ktext. Utilities for preprocessing text for deep learning with Keras

Semantic-Texual-Similarity-Toolkits. Semantic Textual Similarity (STS) measures the degree of equivalence in the underlying semantics of paired snippets of text.

R-net. R-net in PyTorch, with ELMo

SynthText. Code for generating synthetic text images as described in "Synthetic Data for Text Localisation in Natural Images", Ankush Gupta, Andrea Vedaldi, Andrew Zisserman, CVPR 2016.

pyce. Encrypted Python Execution

AspectBasedSentimentAnalysis. Aspect Based Sentiment Analysis is a special type of sentiment analysis. In an explicit aspect, opinion is expressed on a target(opinion target), this aspect-polarity extraction is known as ABSA.

LSTM-CRF-models. LSTM-CRF models for sequence labeling in text.

transfer-learning-with-gluon. Jupyter Notebook