1.rohitg00 / ai-engineering-from-scratch
Learn AI Engineering! Learn it. Build it. Ship it for others.
Ranked by Attention Score: stars gained over the last 180 complete days
1–100 of 212 by Attention Score · May 7, 2026 – Nov 2, 2026 (UTC)
Learn AI Engineering! Learn it. Build it. Ship it for others.
We write your reusable computer vision tools. 💜
ARIS ⚔️ (Auto-Research-In-Sleep) — Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation. No framework, no lock-in — works with Claude Code, Codex, OpenClaw, or any LLM agent.
🤗 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.
Qlib is an AI-oriented Quant investment platform that aims to use AI tech to empower Quant Research, from exploring ideas to implementing productions. Qlib supports diverse ML modeling paradigms, including supervised learning, market dynamics modeling, and RL, and is now equipped with https://github.com/microsoft/RD-Agent to automate R&D process.
Ultralytics YOLO27, YOLO26, YOLO11, YOLOv8 — object detection, instance segmentation, semantic segmentation, image classification, pose estimation, object tracking
Tensors and Dynamic neural networks in Python with strong GPU acceleration
Machine Learning Systems: Foundations, Scaling, Agentic AI, and Physical AI (Vols I–IV) • Harvard CS249r | https://mlsysbook.ai
《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。
Stable Diffusion web UI
Faster Whisper transcription with CTranslate2
A curated list of Artificial Intelligence (AI) courses, books, video lectures and papers.
Nano vLLM
Deepfakes Software For All
Streamlit — A faster way to build and share data apps.
Machine Learning From Scratch. Bare bones NumPy implementations of machine learning models and algorithms with a focus on accessibility. Aims to cover everything from linear regression to deep learning.
Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.
Build and share delightful machine learning apps, all in Python. 🌟 Star to support our work!
🧑🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), gans(cyclegan, stylegan2, ...), 🎮 reinforcement learning (ppo, dqn), capsnet, distillation, ... 🧠
🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.
Interactive deep learning book with multi-framework code, math, and discussions. Adopted at 500 universities from 70 countries including Stanford, MIT, Harvard, and Cambridge.
Ultralytics YOLOv5 in PyTorch for object detection, instance segmentation, classification, training, and export.
🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
🐫 CAMEL: The first and the best multi-agent framework. Finding the Scaling Law of Agents. https://www.camel-ai.org
A Lightweight Face Recognition and Facial Attribute Analysis (Age, Gender, Emotion and Race) Library for Python
JARVIS, a system to connect LLMs with ML community. Paper: https://arxiv.org/pdf/2303.17580.pdf
High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)
Open standard for machine learning interoperability
A Library for Advanced Deep Time Series Models for General Time Series Analysis.
The AI Compute Platform for frontier teams. SkyPilot turns fragmented AI compute into one AI supercomputer, so frontier AI teams build custom intelligence faster.
Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.
Clone a voice in 5 seconds to generate arbitrary speech in real-time
Translate manga/image 一键翻译各类图片内文字 https://cotrans.touhou.ai/ (no longer working)
AI Toolkit for Healthcare Imaging
🤗 The largest hub of ready-to-use datasets for AI models with fast, easy-to-use and efficient data manipulation tools
Deep Learning for humans
A collaboration friendly studio for NeRFs
💫 Industrial-strength Natural Language Processing (NLP) in Python
🌸 Run LLMs at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading
🐍 Geometric Computer Vision Library for Spatial AI
Open Machine Learning Compiler Framework
Fast and Accurate ML in 3 Lines of Code
Python 开源项目之「自学编程之路」,保姆级教程:AI实验室、宝藏视频、数据结构、学习指南、机器学习实战、深度学习实战、网络爬虫、大厂面经、程序人生、资源分享。
An open source implementation of CLIP.
Image annotation with Python. Supports polygon, rectangle, circle, line, point, and AI-assisted annotation.
The Triton Inference Server provides an optimized cloud and edge inferencing solution.
Graph Neural Network Library for PyTorch
20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.
Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"
Pretrain, finetune ANY AI model of ANY size on 1 or 10,000+ GPUs with zero code changes.
Deezer source separation library including pretrained models.
Data science Python notebooks: Deep learning (TensorFlow, Theano, Caffe, Keras), scikit-learn, Kaggle, big data (Spark, Hadoop MapReduce, HDFS), matplotlib, pandas, NumPy, SciPy, Python essentials, AWS, and various command lines.
GFPGAN aims at developing Practical Algorithms for Real-world Face Restoration.
A PyTorch-based Speech Toolkit
Democratizing Deep-Learning for Drug Discovery, Quantum Chemistry, Materials Science and Biology
Best Practices on Recommendation Systems
PyTorch Tutorial for Deep Learning Researchers
PyTorch implementation of the U-Net for image semantic segmentation with high quality images
pix2tex: Using a ViT to convert images of equations into LaTeX code.
deep learning for image processing including classification and object-detection etc.
Hierarchical Reasoning Model Official Release
PennyLane is an open-source quantum software platform for quantum computing, quantum machine learning, and quantum chemistry. Create meaningful quantum algorithms, from inspiration to implementation.
RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RNN and transformer - great performance, linear time, constant space (no kv-cache), fast training, infinite ctx_len, and free sentence embedding.
The AI developer platform. Use Weights & Biases to train and fine-tune models, and manage models from experimentation to production.
Deep Learning papers reading roadmap for anyone who are eager to learn this amazing tech!
Making large AI models cheaper, faster and more accessible
Library of deep learning models and datasets designed to make deep learning more accessible and accelerate ML research.
DeepFaceLab is the leading software for creating deepfakes.
YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. Documentation: https://yolox.readthedocs.io/
Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more.
An open-source, tool-augmented conversational language model from Fudan University
1 Line of code data quality profiling & exploratory data analysis for Pandas and Spark DataFrames.
Image-to-Image Translation in PyTorch
Minimal and clean examples of machine learning algorithms implementations
A python library for user-friendly forecasting and anomaly detection on time series.
SoftVC VITS Singing Voice Conversion
(⌐■_■) - Deep Reinforcement Learning instrumenting bettercap for WiFi pwning.
ZenML 🙏: One AI Platform from Pipelines to Agents. https://zenml.io.
BirdNET analyzer for scientific audio data processing.
Scalable and user friendly neural :brain: forecasting algorithms.
Implementation of Denoising Diffusion Probabilistic Model in Pytorch
🚀Clone a voice in 5 seconds to generate arbitrary speech in real-time
A MNIST-like fashion product database. Benchmark :point_down:
Visual localization made easy with hloc
LabelImg is now part of the Label Studio community. The popular image annotation tool created by Tzutalin is no longer actively being developed, but you can check out Label Studio, the open source data labeling tool for images, text, hypertext, audio, video and time-series data.
A unified, comprehensive and efficient recommendation library
Code and documentation to train Stanford's Alpaca models, and generate the data.
Stanford NLP Python library for tokenization, sentence segmentation, NER, and parsing of many human languages
Low-code framework for building custom LLMs, neural networks, and other AI models
100-Days-Of-ML-Code中文版
A deep learning toolkit for healthcare AI: EHR (MIMIC, eICU, OMOP), clinical text, signals and imaging. 30+ models, reproducible pipelines.
Transfer learning / domain adaptation / domain generalization / multi-task learning etc. Papers, codes, datasets, applications, tutorials.-迁移学习
PyTorch implementation of YOLOv3, YOLOv3-SPP, and YOLOv3-tiny for real-time object detection with training, validation, inference, and multi-format export.
☁️ Build multimodal AI applications with cloud-native stack
Deep probabilistic analysis of single-cell and spatial omics data
Face recognition using Tensorflow
A python library for self-supervised learning and latent world models on images.
Deep universal probabilistic programming with Python and PyTorch
Large Language Model Text Generation Inference