Deep Learning: open-source projects on GitHub
105 repositories on Deep Learning, 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 · PythonBuilding LLM from Scratch
Step-by-step implementation of a ChatGPT-like model in PyTorch: tokenizer, architecture, training, and text generation.
★ 93,387 · Jupyter NotebookYOLOV5: OBJECT DETECTION ON PYTORCH
Computer vision model for object detection, instance segmentation, and image classification. Runs on PyTorch, supports export to CoreML and ONNX.
★ 58,278 · PythonDeepSpeed: optimization library for training
DeepSpeed is an optimization deep learning library ensuring efficient distributed training and inference. Supports ZeRO, MoE and parallelism for training models with hund
★ 43,332 · PythonRay: AI Compute Engine
Ray is a distributed engine for AI computing, combining a runtime core and a set of libraries to accelerate ML workloads.
★ 42,516 · PythonFRAMEWORK FOR CHEAPER LARGE MODEL TRAINING
Library for distributed training and inference of large language models. Supports Zero, tensor, and pipeline parallelism strategies to reduce GPU costs.
★ 41,422 · PythonCROSS-PLATFORM ON-DEVICE ML FRAMEWORK
MediaPipe is Google's framework for running ML on-device. Supports mobile platforms, web, desktop, and IoT without sending data to the cloud.
★ 37,717 · C++DIFFUSION MODELS LIBRARY FOR GENERATION
Library for inference and training of diffusion models generating images, audio, and 3D structures. Provides ready-to-use pipelines, noise schedulers, and pretrained mode
★ 34,917 · PythonOPEN TEXTBOOK ON ML SYSTEMS
Open textbook series on machine learning systems (MLSys) with practical tools. Teaches AI engineering: building efficient, reliable, and safe AI systems in real-world con
★ 30,249 · PythonFAST SPEECH TRANSCRIPTION
Faster Whisper — an accelerated version of the Whisper model for speech recognition, built on CTranslate2. It supports quantized models and provides real‑time transcripti
★ 26,758 · PythonHIGH-PERFORMANCE NEURAL NETWORK INFERENCE FRAMEWORK FOR MOBILE
ncnn is a neural network inference framework with no third-party dependencies for mobile, embedded, and desktop platforms. Supports CPU and Vulkan GPU backends, includes
★ 24,068 · C++BEST AI ENGINEERING RESOURCES
Collection with 22k+ stars: roadmaps, tools, and projects for LLMs, RAG, agents, and production. Everything to start and grow as an AI engineer in one place.
★ 22,566AI Resources and Guide
A comprehensive collection of AI resources and step‑by‑step guides for working with models such as DeepSeek, GPT, Claude, Cursor, and others.
★ 22,111 · JavaScriptDATASETS - 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 · PythonWEB‑LLM: Browser LLM Engine
High-performance engine for running LLM directly in the browser, written in TypeScript.
★ 18,069 · TypeScriptMNN: FAST AI ON DEVICE
Lightweight and lightning-fast inference engine from Alibaba for on-device LLM and Edge AI.
★ 15,386 · C++Document Structuring
An open ETL solution for converting complex documents into clean structured data formats for language models.
★ 14,764 · HTMLlitgpt: Powerful LLMs
High-performance language models with ready-to-use recipes for pretraining, fine-tuning, and scaling. 13K+ stars!
★ 13,387 · PythonKIMI K3: 2.78 Trillion Parameters
Running the Kimi K3 model with 2.78 trillion parameters on a single CPU, using only 8.24 GB of RAM without BLAS, frameworks, or GPU.
★ 12,109 · CLUDWIG - LOW-CODE AI FRAMEWORK
Build LLMs and neural networks without code. Simplicity for custom AI models included!
★ 11,791 · 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++TensorZero: LLMOps Platform
An open LLMOps platform that unifies LLM gateway, observability, evaluation, optimization, and experiments.
★ 11,366 · RustPYOD: Anomaly Detector for AI
The pyod library offers 60+ anomaly detectors for tables, time series, graphs, text, and images with ADEngine orchestration.
★ 9,867 · PythonAutonomous ML research in sleep
Markdown skills for LLM agents: cross-model reviews, idea search, and experiment automation.
★ 8,895 · PythonBENTOML PATH TO AI API
Serve models and AI applications in minutes: API, queues, multi‑model pipelines, and LLM services.
★ 8,663 · PythonAI engineering from scratch
Learn, build it, and deliver it to others.
★ 7,884 · PythonVISUAL GUIDE TO TRANSFORMERS
An interactive visualization that reveals how Transformer models work. Easy to understand even for beginners.
★ 7,761 · JavaScriptOPENSQUILLA: EFFECTIVE AI AGENT
OpenSquilla — a token‑efficient AI agent that, with the same budget, provides greater intelligence density. Implemented in Python and compatible with popular LLMs for bui
★ 7,150 · PythonSMILE - AI ENGINE ON JAVA
SMILE — Statistical Machine Intelligence & Learning Engine, a powerful framework for building machine learning models in Java.
★ 6,438 · JavaPROMPT ENGINEERING MAX
A collection of the best resources on prompt engineering for GPT, ChatGPT, PaLM, and other LLM models.
★ 5,984 · TypeScriptLLM FROM SCRATCH IN PYTORCH
The reasoning-from-scratch project shows how to build a Reasoning LLM from scratch in PyTorch, step by step. Implemented in Jupyter notebooks: architecture, training with
★ 5,831 · Jupyter NotebookZENML: AI PLATFORM FROM PIPELINE
ZenML is a Python framework for creating AI pipelines and agents, unifying data, models, and orchestration in a single platform.
★ 5,636 · PythonMMF: Modular Multimodal Framework
Modular framework from FAIR for vision and language research, combining the flexibility of Python and the power of multimodal models.
★ 5,633 · PythonTREE OF THOUGHTS: SMART SOLUTION SEARCH
Tree of Thoughts implementation for LLMs: model builds reasoning tree, evaluates branches, picks best path. Boosts solution quality by 70%+ without fine-tuning.
★ 4,592 · 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 · PythonONE DNN: ACCELERATING AI ON CPU
oneDNN provides high-performance AI kernel implementations for x64, AArch64, RISC‑V, and Intel GPUs. It accelerates PyTorch, TensorFlow, OpenVINO, and ONNX Runtime using
★ 4,092 · C++NIKSTLA - TIME AI FORECAST
TimeGPT‑1 is a pretrained time‑series model trained on 100 billion points, delivering accurate forecasts and anomaly detection for retail, energy, finance, and IoT.
★ 4,050 · Jupyter NotebookUniversal FedML Platform
A universal library for distributed training, model serving, and federated learning with a cross-cloud scheduler.
★ 4,046 · PythonSYNAPSA COMMONS: FREE AI COURSES
Free practical AI courses in Colab, Kaggle, Binder, Codespaces and Jupyter. They include evidence of EU AI Act compliance, model validation, document extraction, search a
★ 4,026 · PythonSWANLAB: TRACKING AND VISUALIZATION
SwanLab is an open-source tool for tracking and visualizing AI model training, compatible with PyTorch, Transformers, and other frameworks.
★ 3,981 · PythonLAZYLLM - THE LAZIEST WAY
LazyLLM lets you quickly create multi-agent LLM applications with minimal code and maximum simplicity.
★ 3,833 · PythonAI‑ENGINEER HQ: SCIENCE CORE
The project contains Jupyter notebooks with methods for training models, RAG pipelines on LangChain and data structure algorithms for AI agents. It allows quickly creatin
★ 3,780 · Jupyter NotebookVIETNAMESE TTS WITH ON-DEVICE INSTANT VOICE CLONING
On-device Vietnamese TTS with instant voice cloning from 3-8s audio. Runs in real-time on CPU and GPU at 48 kHz quality.
★ 3,432 · PythonAUTODISTILL: TRAINING WITHOUT LABELING
Automatically turns raw images into ready-to-use inference models, using foundation models to generate pseudo‑labels and train supervised models. No manual labeling requi
★ 2,798 · PythonXTRUING: PERSONALIZE YOUR LLM
xTuring simplifies creating and personalizing your own LLMs: from data preparation to fine‑tuning. The tool supports adapters, ready‑made pipelines and model export. Join
★ 2,681 · PythonBOOTCAMP: 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 Notebook2350+ Stars: Ready AI Models
A collection of pretrained state-of-the-art models for ailia SDK. Over 2300 stars on GitHub — run AI out of the box in Python.
★ 2,405 · PythonSUPERLINKED INFERENCE ENGINE
Open-source server for embedding inference, reranking, and data extraction. 2000+ stars on GitHub.
★ 2,029 · PythonGRAPHS VS FRAUD
Curated list of articles on fraud detection using graphs and transformers.
★ 1,907CURATOR — DATA FOR POST-TRAINING
Synthetic data curation for LLM fine-tuning and structured information extraction. 1686 stars ⭐
★ 1,767 · PythonTOOLKIT FOR CLINICAL AI
PyHealth is a library for healthcare AI supporting EHR (MIMIC, eICU, OMOP), clinical texts, signals, and imaging. 30+ models and reproducible pipelines for research.
★ 1,699 · 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 · PythonPRUNA - ACCELERATING MODELS
Pruna — a Python framework for model optimization that speeds up inference and reduces resource usage without losing accuracy.
★ 1,391 · PythonAIRUNNER OFFLINE AI FOR ALL
Offline inference engine for arts, real-time voice dialogues, LLM chatbots, and automated workflows.
★ 1,315 · PythonRECOMMENDATIONS ON STEROIDS
A framework for recommendation models on PyTorch. Easy to use and easily extensible.
★ 1,242 · Jupyter NotebookNNCFF - 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.
★ 1,195KNOWNOTE: LOCAL AI KNOWLEDGE BASE...
KnowNote — local AI knowledge base on Electron, replacing NotebookLM... Indexes files, answers questions and builds chains of thought without sending data to the cloud.
★ 1,170 · TypeScriptASREVIEW - ACTIVE LEARNING FOR REVIEWS
Asreview uses active learning to speed up systematic literature reviews, reducing the number of required readings.
★ 1,074 · PythonAI Agent 24/7
An autonomous AI agent runs your deep experiments 24/7, saving resources and memory. The Leader‑Worker architecture ensures stable operation at zero cost.
★ 1,035 · PythonNew projects on this topic in Telegram
Telegram →