Awesome AI Models and Projects

Please star ⭐ this repo if you find it useful! Help me reach 1K stars. Thank you very much for your support!

A curated list of awesome AI models, projects, and tools. Inspired by the awesome initiative.

Contents

• AI Repositories
• Contributing

AI Repositories

This section includes cool AI repositories, grouped by category.

Learning and Education

• microsoft/generative-ai-for-beginners - A structured 21-lesson course by Microsoft Cloud Advocates for building generative AI applications.

• rasbt/LLMs-from-scratch - Build a Large Language Model (From Scratch) in pure PyTorch.

• DataTalksClub/llm-zoomcamp - Free hands-on course for building real-world LLM applications.

• Shubhamsaboo/awesome-llm-apps - Curated showcase of runnable LLM applications.

• panaversity/learn-agentic-ai - Learn Agentic AI using Dapr Agentic Cloud Ascent.

• dair-ai/Mathematics-for-ML - Curated collection of math resources for ML.

• ashishpatel26/500-AI-Machine-learning-Deep-learning-Computer-vision-NLP-Projects-with-code - 500+ AI project ideas with code.

• armankhondker/awesome-ai-ml-resources - Machine Learning & AI Roadmap (2025).

• spmallick/learnopencv - Comprehensive tutorials for computer vision and AI.

• x1xhlol/system-prompts-and-models-of-ai-tools - System prompts and models of AI tools.

• karpathy/nanoGPT - The simplest, fastest repository for training/finetuning medium-sized GPTs.

• karpathy/makemore - An autoregressive character-level language model for making more things.

• fastai/fastai - A PyTorch-based library for deep learning from scratch.

• google-research/bert - TensorFlow code and pre-trained models for BERT.

• openai/gpt-2 - Code for the paper "Language Models are Unsupervised Multitask Learners".

• cs231n/cs231n.github.io - Convolutional Neural Networks for Visual Recognition course materials.

• karpathy/minGPT - A minimal PyTorch re-implementation of the OpenAI GPT training.

• fastai/courses - fast.ai course materials and notebooks.

• microsoft/ML-For-Beginners - 12 weeks, 26 lessons, 52 quizzes, classic Machine Learning for all.

• dair-ai/Prompt-Engineering-Guide - Guide and resources for prompt engineering.

• yandexdataschool/nlp_course - YSDA Natural Language Processing course.

• fastai/imagenette - A subset of ImageNet with 10 classes.

• d2l-ai/d2l-en - Interactive deep learning book.

• google-research/t5x - Framework for sequence-to-sequence models.

• openai/evals - Framework for evaluating LLMs.

• openai/cookbook - Examples and guides for using the OpenAI API.

• huggingface/course - The Hugging Face course on Transformers.

• fastai/book - The fast.ai book.

• mit-deep-learning/6.036 - Introduction to Machine Learning.

• stanfordnlp/cs224n-winter17-lectures - CS224n: Natural Language Processing with Deep Learning.

• karpathy/recurrentjs - Deep Learning in Javascript.

• tensorflow/probability - Probabilistic reasoning and statistical analysis in TensorFlow.

• pytorch/examples - A set of examples around pytorch in Vision, Text, Reinforcement Learning.

• keras-team/keras-io - Keras documentation.

• microsoft/LightGBM - A fast, distributed, high performance gradient boosting framework.

• catboost/catboost - A fast, scalable, high performance Gradient Boosting on Decision Trees library.

• dmlc/xgboost - Scalable, Portable and Distributed Gradient Boosting.

• yandexdataschool/Practical_RL - A course on practical reinforcement learning.

• openai/openai-cookbook - Examples and guides for using the OpenAI API.

• openai/chatgpt-retrieval-plugin - ChatGPT Retrieval Plugin.

• huggingface/diffusion-models-class - Hugging Face diffusion models class.

• fastai/fastbook - The fastai book.

• mit-llm/llm-course - MIT LLM course.

• stanford-cs221/autumn2019 - CS221: Artificial Intelligence: Principles and Techniques.

• berkeleydeeprlcourse/homework - Berkeley Deep RL Course.

• deeplearning-ai/machine-learning-specialization - Machine Learning Specialization.

• andrewng/machine-learning-coursera - Machine Learning Coursera.

• mit-llm/llm-book - LLM book.

• google-research/pegasus - PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization.

• facebookresearch/ParlAI - A framework for dialogue research.

• allenai/allennlp - An open-source NLP research library.

• spacy/spaCy - Industrial-strength Natural Language Processing.

• nltk/nltk - NLTK Source.

• keras-team/keras-tuner - Hyperparameter tuning for humans.

• optuna/optuna - A hyperparameter optimization framework.

• tensorflow/agents - TF-Agents: A reliable, scalable and easy to use TensorFlow library for Contextual Bandits and Reinforcement Learning.

• dmlc/dgl - Python package built to ease deep learning on graph, on top of existing DL frameworks.

• pyg-team/pytorch_geometric - Graph Neural Network Library for PyTorch.

Frameworks and Libraries

• huggingface/transformers - State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

• pytorch/pytorch - Tensors and Dynamic neural networks in Python with strong GPU acceleration.

• tensorflow/tensorflow - An open source machine learning framework for everyone.

• keras-team/keras - Deep Learning for humans.

• CompVis/stable-diffusion - A latent text-to-image diffusion model.

• huggingface/diffusers - State-of-the-art diffusion models for image and audio generation in PyTorch.

• openai/whisper - Robust Speech Recognition via Large-Scale Weak Supervision.

• langchain-ai/langchain - Framework for building reliable AI agents with modular components.

• ollama/ollama - Framework for running LLMs locally on your hardware.

• vllm-project/vllm - A high-throughput and memory-efficient inference and serving engine for LLMs.

• scikit-learn/scikit-learn - Machine learning in Python.

• PaddlePaddle/Paddle - PArallel Distributed Deep LEarning.

• microsoft/onnxruntime - ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator.

• apache/tvm - Open deep learning compiler stack for cpu, gpu and specialized accelerators.

• ray-project/ray - Ray is a unified framework for scaling AI and Python applications.

• google/jax - JAX is Autograd and XLA, brought together for high-performance ML research.

• facebookresearch/fairseq - Facebook AI Research Sequence-to-Sequence Toolkit.

• deepmind/jraph - Jraph: A library for graph neural networks in JAX.

• lucidrains/vit-pytorch - Implementation of Vision Transformer in PyTorch.

• openai/spinningup - An educational resource to help anyone learn deep reinforcement learning.

• google/flax - Neural network library for JAX.

• deepmind/haiku - Simple neural network library for JAX.

• microsoft/DialoGPT - Large-scale pretraining for dialogue.

• huggingface/accelerate - Library for training PyTorch models on multiple devices.

• pytorch/text - Data loading utilities for text.

• tensorflow/models - Models and examples built with TensorFlow.

• pytorch/vision - Datasets, Transforms and Models specific to Computer Vision.

• pytorch/audio - Data manipulation and transformation for audio signal processing.

• huggingface/tokenizers - Fast tokenizers for NLP.

• openai/tiktoken - tiktoken is a fast BPE tokeniser for use with OpenAI's models.

• google/sentencepiece - Unsupervised text tokenizer.

• facebookresearch/detectron2 - Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.

• google-research/albert - ALBERT: A Lite BERT for Self-supervised Learning of Language Representations.

• google-research/electra - ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators.

• openai/jukebox - Code for the paper "Jukebox: A Generative Model for Music".

• stability-ai/stable-audio-tools - Generative models for conditional audio generation.

• CompVis/latent-diffusion - High-Resolution Image Synthesis with Latent Diffusion Models.

• lucidrains/DALLE2-pytorch - Implementation of DALL-E 2 in Pytorch.

• openai/baselines - OpenAI Baselines: high-quality implementations of reinforcement learning algorithms.

• hill-a/stable-baselines - A fork of OpenAI Baselines, implementations of reinforcement learning algorithms.

• snap-stanford/ogb - Benchmark datasets, data loaders, and evaluators for graph machine learning.

• openai/gym - A toolkit for developing and comparing reinforcement learning algorithms.

• hill-a/stable-baselines3 - PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.

• openai/mujoco-py - MuJoCo is a physics engine for detailed, efficient rigid body simulations.

• facebookresearch/habitat-sim - A flexible, high-performance 3D simulator for embodied AI research.

• carla-simulator/carla - Open-source simulator for autonomous driving research.

• unity-technologies/ml-agents - The Unity Machine Learning Agents Toolkit (ML-Agents) is an open-source project that enables games and simulations to serve as environments for training intelligent agents.

• nvidia/warp - A Python framework for high performance GPU simulation and graphics.

• nvidia/modulus - Open-source deep-learning framework for building, training, and fine-tuning deep learning models using state-of-the-art Physics-ML methods.

• huggingface/safetensors - Simple, safe way to store and distribute tensors.

• openai/triton - Triton is a language and compiler for writing highly efficient custom Deep Learning primitives.

• pytorch/torchdynamo - A Python-level JIT compiler designed to make unmodified PyTorch programs faster.

• pytorch/torchscript - TorchScript is a way to create serializable and optimizable models from PyTorch code.

• tensorflow/tfx - TFX is an end-to-end platform for deploying production ML pipelines.

• apache/beam - Apache Beam is a unified programming model for Batch and Streaming data processing.

• apache/flink - Apache Flink is an open source stream processing framework with powerful capabilities to handle both batch and stream processing.

• huggingface/huggingface_hub - Client library to download and publish models, datasets and other repos on the huggingface.co hub.

• replicate/replicate-python - Python client for Replicate.

• togethercomputer/Together - The Together Python Library.

Tools and Platforms

• OpenClaw/OpenClaw - Personal AI assistant that runs locally and extends its own capabilities.

• n8n-io/n8n - Open-source workflow automation platform with AI capabilities.

• langflow-ai/langflow - Low-code platform for designing AI workflows.

• langgenius/dify - Production-ready platform for building AI applications.

• open-webui/open-webui - Self-hosted web interface for AI models.

• infiniflow/ragflow - Retrieval-augmented generation engine.

• anthropics/claude-code - Anthropic's agentic coding tool.

• google/gemini-cli - Command-line tool for Google's Gemini model.

• streamlit/streamlit - The fastest way to build data apps.

• gradio-app/gradio - Create UIs for your ML model in Python in 3 minutes.

• jupyterlab/jupyterlab - JupyterLab computational environment.

• milvus-io/milvus - A cloud-native vector database, storage for next generation AI applications.

• weaviate/weaviate - Weaviate is an open-source vector database that stores both objects and vectors.

• chroma-core/chroma - the AI-native open-source embedding database.

• langfuse/langfuse - Open source LLM engineering platform: LLM observability, metrics, evaluations, prompt management.

• stanfordnlp/dspy - DSPy: The framework for programming foundation models.

• modal-labs/modal-client - Modal is the fastest way to run code in the cloud.

• huggingface/datasets - The largest hub of ready-to-use datasets for ML models.

• wandb/wandb - Track and visualize all the pieces of your machine learning pipeline.

• bentoml/BentoML - The easiest way to serve AI apps in production.

• comet-ml/comet-ml - Supercharge your machine learning workflow.

• cortexlabs/cortex - Deploy machine learning models to production.

• paperclipai/paperclip - Open-source orchestration for zero-human companies with AI agents.

• qdrant/qdrant - Vector Database for the next generation of AI applications.

• kubeflow/kubeflow - Machine Learning Toolkit for Kubernetes.

• seldon-core/seldon-core - MLOps framework.

• labmlai/annotated_deep_learning_paper_implementations - Implementation of deep learning papers.

• replicate/cog - Containers for machine learning.

• modal-labs/modal-examples - Examples for Modal.

• streamlit/demo-self-driving - Demo of self-driving car with Streamlit.

• gradio-app/hub - Hub for Gradio apps.

• jupyter-widgets/ipywidgets - Interactive widgets for Jupyter.

• plotly/plotly.py - Interactive graphing library.

• huggingface/hub - Client library for the Hugging Face Hub.

• plotly/dash - Analytical Web Apps for Python & R.

• bokeh/bokeh - Interactive Data Visualization in the browser, from Python.

• apache/superset - Apache Superset is a Data Visualization and Data Exploration Platform.

• d3/d3 - Bring data to life with SVG, Canvas and HTML.

• matplotlib/matplotlib - matplotlib: plotting with Python.

• seaborn/seaborn - Statistical data visualization in Python.

• altair-viz/altair - Declarative statistical visualization library for Python.

• vega/vega - A visualization grammar.

• jupyter/notebook - Jupyter Interactive Notebook.

• googlecolab/colabtools - Python notebook for Colab.

• fastapi/fastapi - FastAPI framework, high performance, easy to learn, fast to code.

• tiangolo/uvicorn - The lightning-fast ASGI server.

• encode/httpx - A next generation HTTP client for Python.

• psf/requests - Python HTTP for Humans.

• pallets/flask - The Python micro framework for building web applications.

• django/django - The Web framework for perfectionists with deadlines.

• apache/kafka - Mirror of Apache Kafka.

• anyscale/ray - Ray is an open-source unified compute framework.

• prefecthq/prefect - Prefect is a workflow orchestration tool for building resilient data pipelines in Python.

• apache/airflow - Apache Airflow - A platform to programmatically author, schedule, and monitor workflows.

• luigi/luigi - Luigi is a Python module that helps you build complex pipelines of batch jobs.

• celery/celery - Distributed Task Queue.

• redis/redis - Redis is an in-memory database that persists on disk.

• mongodb/mongo - The MongoDB Database.

• apache/cassandra - Mirror of Apache Cassandra.

• elasticsearch/elasticsearch - Free and Open, Distributed, RESTful Search Engine.

• opensearch-project/OpenSearch - Open source distributed and RESTful search engine.

• influxdata/influxdb - Scalable datastore for metrics, events, and real-time analytics.

• prometheus/prometheus - The Prometheus monitoring system and time series database.

• grafana/grafana - The open and composable observability and data visualization platform.

• apache/zookeeper - Apache ZooKeeper.

• etcd-io/etcd - Distributed reliable key-value store for the most critical data of a distributed system.

• consul/consul - Consul is a distributed, highly available, and data center aware solution to connect and configure applications across dynamic, distributed infrastructure.

• traefik/traefik - The Cloud Native Application Proxy.

• nginx/nginx - An official read-only mirror of the NGINX Open Source repository.

• envoyproxy/envoy - Cloud-native high-performance edge/middle/service proxy.

• istio/istio - Connect, secure, control, and observe services.

• kubernetes/kubernetes - Production-Grade Container Scheduling and Management.

• docker/docker - Docker - the open-source application container engine.

• minio/minio - The Object Store for AI Data Infrastructure.

• apache/hadoop - Apache Hadoop.

• apache/spark - Apache Spark - A unified analytics engine for large-scale data processing.

• apache/hive - Apache Hive.

• apache/pig - Apache Pig.

Contributing

Contributions are welcome! Please read the contributing guidelines before submitting a pull request.

To add a new item, please ensure it meets the following criteria:

• It is actively maintained.
• It has a clear use case or purpose.
• It includes a link to the official repository or documentation.

License

This list is licensed under the MIT License.