{"id":102740,"url":"https://github.com/nickvasdev/awesome-ai","name":"awesome-ai","description":"A curated list of AI tools, courses, books, and resources for anyone interested in exploring artificial intelligence, machine learning, and deep learning.","projects_count":81,"last_synced_at":"2026-06-26T06:00:36.132Z","repository":{"id":306390450,"uuid":"869346286","full_name":"nickvasdev/awesome-ai","owner":"nickvasdev","description":"A curated list of AI tools, courses, books, and resources for anyone interested in exploring artificial intelligence, machine learning, and deep learning.","archived":false,"fork":false,"pushed_at":"2024-10-27T09:12:47.000Z","size":1025,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2026-06-09T07:04:29.728Z","etag":null,"topics":["ai","awesome","awesome-list","courses","learning","resources"],"latest_commit_sha":null,"homepage":"","language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/nickvasdev.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2024-10-08T06:30:19.000Z","updated_at":"2024-12-20T16:34:22.000Z","dependencies_parsed_at":"2025-07-25T12:39:26.765Z","dependency_job_id":"9e0cc997-9664-4891-9fe0-f448e3219365","html_url":"https://github.com/nickvasdev/awesome-ai","commit_stats":null,"previous_names":["hisk/awesome-ai","nickvasdev/awesome-ai"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/nickvasdev/awesome-ai","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/nickvasdev%2Fawesome-ai","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/nickvasdev%2Fawesome-ai/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/nickvasdev%2Fawesome-ai/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/nickvasdev%2Fawesome-ai/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/nickvasdev","download_url":"https://codeload.github.com/nickvasdev/awesome-ai/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/nickvasdev%2Fawesome-ai/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":34805072,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-06-26T02:00:06.560Z","response_time":106,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"created_at":"2026-01-02T00:00:40.211Z","updated_at":"2026-06-26T06:00:36.133Z","primary_language":null,"list_of_lists":false,"displayable":true,"categories":["Learning Resources","Tools","Courses","On-Device AI","Videos","Newsletters","Books"],"sub_categories":["Online Resources","Video","Advanced AI and Machine Learning Courses","Deep Learning and Reinforcement Learning","Introductory Courses","Images","LLM Architecture Foundations","Limitations of Cloud-Based LLM Inference and Advantages of On-Device Inference","Evolution of On-Device LLMs","Efficient Architectures for On-Device LLMs","The Performance Indicator of On-Device LLMs","Awesome GitHub Resources","Chat","On-Device LLMs Training","Memory and Computational Efficiency","General Efficiency and Performance Improvements","Commercial Tools"],"readme":"![](./banner.jpg)\n\n# Awesome AI Resources\n\nA curated list of AI tools, courses, books, and resources for anyone interested in exploring artificial intelligence, machine learning, and deep learning.\n\n[![Awesome](https://awesome.re/badge.svg)](https://awesome.re)\n# Table of Contents\n\n- [Tools](#tools)\n   * [Chat](#chat)\n   * [Images](#images)\n   * [Video](#video)\n   * [Commercial Tools](#commercial-tools)\n- [Courses](#courses)\n   * [Introductory Courses](#introductory-courses)\n   * [Deep Learning and Reinforcement Learning](#deep-learning-and-reinforcement-learning)\n   * [Advanced AI and Machine Learning Courses](#advanced-ai-and-machine-learning-courses)\n- [Books](#books)\n- [Videos](#videos)\n- [Learning Resources](#learning-resources)\n   * [Online Resources](#online-resources)\n   * [Awesome GitHub Resources](#awesome-github-resources)\n- [Newsletters](#newsletters)\n- [On-Device AI](#on-device-ai)\n   * [Evolution of On-Device LLMs](#evolution-of-on-device-llms)\n   * [LLM Architecture Foundations](#llm-architecture-foundations)\n   * [On-Device LLMs Training](#on-device-llms-training)\n   * [Limitations of Cloud-Based LLM Inference and Advantages of On-Device Inference](#limitations-of-cloud-based-llm-inference-and-advantages-of-on-device-inference)\n   * [The Performance Indicator of On-Device LLMs](#the-performance-indicator-of-on-device-llms)\n   * [Efficient Architectures for On-Device LLMs](#efficient-architectures-for-on-device-llms)\n   * [Model Compression and Parameter Sharing](#model-compression-and-parameter-sharing)\n   * [Collaborative and Hierarchical Model Approaches](#collaborative-and-hierarchical-model-approaches)\n   * [Memory and Computational Efficiency](#memory-and-computational-efficiency)\n   * [Mixture-of-Experts (MoE) Architectures](#mixture-of-experts-moe-architectures)\n   * [Hybrid Architectures](#hybrid-architectures)\n   * [General Efficiency and Performance Improvements](#general-efficiency-and-performance-improvements)\n\n\n\n\u003c!-- TOC --\u003e\u003ca name=\"tools\"\u003e\u003c/a\u003e\n## Tools\n\n\u003c!-- TOC --\u003e\u003ca name=\"chat\"\u003e\u003c/a\u003e\n### Chat\n  - [Chat GPT](https://chat.openai.com/) - A free-to-use AI system that allows users to engage in conversations, gain insights, automate tasks, and witness the future of AI all in one place.\n  - [Gemini](https://gemini.google.com/) - Direct access to Google AI for writing, planning, learning, and more.\n  - [Claude](https://www.anthropic.com/claude) - Foundational AI models for brainstorming ideas, analyzing images, and processing long documents.\n\n\u003c!-- TOC --\u003e\u003ca name=\"images\"\u003e\u003c/a\u003e\n### Images\n  - [Midjourney](https://www.midjourney.com/) - AI image generation.\n  - [DALL·E 3](https://openai.com/dall-e-3) - AI system that creates realistic images and art from a natural-language description.\n\n\u003c!-- TOC --\u003e\u003ca name=\"video\"\u003e\u003c/a\u003e\n### Video\n  - [Sora](https://openai.com/sora) - Text-to-video AI model that creates imaginative scenes from text.\n  - [Runway](https://runwayml.com/) - AI video generation.\n\n\u003c!-- TOC --\u003e\u003ca name=\"commercial-tools\"\u003e\u003c/a\u003e\n### Commercial Tools\n  - [Taskade](https://www.taskade.com) - Build, train, and deploy AI agents to automate tasks, research, and collaborate in real-time.\n\n\u003c!-- TOC --\u003e\u003ca name=\"courses\"\u003e\u003c/a\u003e\n## Courses\n\n\u003c!-- TOC --\u003e\u003ca name=\"introductory-courses\"\u003e\u003c/a\u003e\n### Introductory Courses\n  - [Introduction to Artificial Intelligence (AI)](https://www.notion.so/owainlewis/Introduction-to-Artificial-Intelligence-AI-ef59b363654542e597ba46a19d129882?pvs=4) - High-level introduction to AI from IBM on Coursera.\n  - [Introduction to Generative AI](https://www.coursera.org/learn/introduction-to-generative-ai) - Beginner-level introduction to Generative AI from Google on Coursera.\n  - [CS50’s Intro to Artificial Intelligence](https://cs50.harvard.edu/ai/2020) - Concepts and algorithms at the foundation of modern AI.\n  - [MIT: Intro to Deep Learning](https://introtodeeplearning.com) - Seven-day bootcamp to introduce deep learning methods.\n\n\u003c!-- TOC --\u003e\u003ca name=\"deep-learning-and-reinforcement-learning\"\u003e\u003c/a\u003e\n### Deep Learning and Reinforcement Learning\n  - [Deep Blueberry: Deep Learning book](https://mithi.github.io/deep-blueberry) - Basics of deep-learning architectures like CNNs, LSTMs, GANs, and more.\n  - [Spinning Up in Deep Reinforcement Learning](https://spinningup.openai.com/) - A free deep reinforcement learning course by OpenAI.\n  - [Deep Learning](https://www.udacity.com/course/intro-to-tensorflow-for-deep-learning--ud187) - Introductory course to deep learning using TensorFlow.\n  - [Stanford Statistical Learning](http://online.stanford.edu/course/statistical-learning-winter-2014) - Introductory course on machine learning.\n\n\u003c!-- TOC --\u003e\u003ca name=\"advanced-ai-and-machine-learning-courses\"\u003e\u003c/a\u003e\n### Advanced AI and Machine Learning Courses\n  - [Knowledge Based Artificial Intelligence](https://www.udacity.com/course/knowledge-based-ai-cognitive-systems--ud409) - Georgia Tech's course focusing on Symbolic AI.\n  - [Machine Learning Crash Course by Google](https://developers.google.com/machine-learning/crash-course/ml-intro) - A series of lessons with video lectures, real-world case studies, and hands-on practice.\n  - [Deep RL Bootcamp Lectures](https://sites.google.com/view/deep-rl-bootcamp/lectures) - Deep Reinforcement Bootcamp Lectures - August 2017.\n  - [Elements of AI](https://www.elementsofai.com/) - An introduction to AI for everyone interested in learning what AI is and how it affects our lives.\n\n\u003c!-- TOC --\u003e\u003ca name=\"books\"\u003e\u003c/a\u003e\n## Books\n\n- [Deep Learning](http://www.deeplearningbook.org/) - Introduction by Goodfellow, Bengio, and Courville covering deep learning techniques and perspectives.\n- [The Hundred-Page Machine Learning Book](http://themlbook.com/) - A comprehensive guide to machine learning in just 100 pages.\n- [Generative AI in Action](https://www.manning.com/books/generative-ai-in-action) - Learn how to add generative AI tools for text, images, and code into projects.\n\n\u003c!-- TOC --\u003e\u003ca name=\"videos\"\u003e\u003c/a\u003e\n## Videos\n\n- [The Unreasonable Effectiveness Of Deep Learning](https://www.youtube.com/watch?v=sc-KbuZqGkI) - Yann LeCun gives a talk on deep convolutional neural networks.\n- [AWS Machine Learning in Motion](https://www.manning.com/livevideo/aws-machine-learning-in-motion) - Learn how to build a predictive algorithm using AWS.\n- [Reinforcement Learning in Motion](https://www.manning.com/livevideo/reinforcement-learning-in-motion) - Concepts like how RL systems learn and how to train AI agents.\n\n\u003c!-- TOC --\u003e\u003ca name=\"learning-resources\"\u003e\u003c/a\u003e\n## Learning Resources\n\n\u003c!-- TOC --\u003e\u003ca name=\"online-resources\"\u003e\u003c/a\u003e\n### Online Resources\n  - [Neural Networks And Deep Learning](http://neuralnetworksanddeeplearning.com) - Learn the core concepts behind neural networks and deep learning.\n  - [Awesome Machine Learning](https://github.com/josephmisiti/awesome-machine-learning) - Curated list of machine learning resources.\n  - [Awesome Deep Learning Resources](https://github.com/guillaume-chevalier/awesome-deep-learning-resources) - Rough list of deep learning resources.\n  - [Professional and In-Depth AI Video Courses](https://freecoursesite.com/?s=Artificial+Intelligence) - Free professional AI tutorials and courses.\n  - [MIT: TinyML and Efficient Deep Learning Computing](https://efficientml.ai)\n  - [Harvard: Machine Learning Systems](https://mlsysbook.ai/)\n  - [Deep Learning AI: Introduction to On-Device AI](https://www.deeplearning.ai/short-courses/introduction-to-on-device-ai/)\n\n\u003c!-- TOC --\u003e\u003ca name=\"awesome-github-resources\"\u003e\u003c/a\u003e\n### Awesome GitHub Resources\n  - [Awesome Graph Classification](https://github.com/benedekrozemberczki/awesome-graph-classification) - Learning from graph-structured data.\n  - [Awesome Fraud Detection Papers](https://github.com/benedekrozemberczki/awesome-fraud-detection-papers) - Fraud detection papers from machine learning conferences.\n\n\u003c!-- TOC --\u003e\u003ca name=\"newsletters\"\u003e\u003c/a\u003e\n## Newsletters\n\n- [Superhuman.ai](https://www.superhuman.ai/) - A daily AI newsletter.\n\n\u003c!-- TOC --\u003e\u003ca name=\"on-device-ai\"\u003e\u003c/a\u003e\n## On-Device AI\n\n\u003c!-- TOC --\u003e\u003ca name=\"evolution-of-on-device-llms\"\u003e\u003c/a\u003e\n### Evolution of On-Device LLMs\n  - [Tinyllama](https://arxiv.org/abs/2401.02385) - Open-source small language model.\n  - [MobileVLM V2](https://arxiv.org/abs/2402.03766) - Faster and stronger baseline for Vision Language Model.\n  - [MobileAIBench](https://arxiv.org/abs/2406.10290) - Benchmarking LLMs and LMMs for on-device use cases.\n  - [Octopus series papers](https://arxiv.org/abs/2404.01549) - On-device language models for different applications. [[Octopus v2]](https://arxiv.org/abs/2404.01744) [[Octopus v3]](https://arxiv.org/abs/2404.11459) [[Octopus v4]](https://arxiv.org/abs/2404.19296) [[Github]](https://github.com/NexaAI).\n  - [The Era of 1-bit LLMs](https://arxiv.org/abs/2402.17764) - All large language models are in 1.58 bits.\n  - [AWQ](https://arxiv.org/abs/2306.00978) - Activation-aware weight quantization for LLM compression and acceleration. [[Github]](https://github.com/mit-han-lab/llm-awq).\n  - [Small Language Models](https://arxiv.org/pdf/2409.15790) - Survey, measurements, and insights.\n\n\u003c!-- TOC --\u003e\u003ca name=\"llm-architecture-foundations\"\u003e\u003c/a\u003e\n### LLM Architecture Foundations\n  - [The case for 4-bit precision](https://arxiv.org/abs/2212.09720) - k-bit inference scaling laws.\n  - [Challenges and applications of large language models](https://arxiv.org/abs/2307.10169).\n  - [MiniLLM](https://arxiv.org/abs/2306.08543) - Knowledge distillation of large language models. [[Github]](https://github.com/Tebmer/Awesome-Knowledge-Distillation-of-LLMs).\n  - [Gptq](https://arxiv.org/abs/2210.17323) - Accurate post-training quantization for generative pre-trained transformers. [[Github]](https://github.com/IST-DASLab/gptq).\n  - [Gpt3.int8()](https://arxiv.org/abs/2208.07339) - 8-bit matrix multiplication for transformers at scale.\n\n\u003c!-- TOC --\u003e\u003ca name=\"on-device-llms-training\"\u003e\u003c/a\u003e\n### On-Device LLMs Training\n  - [OpenELM](https://arxiv.org/abs/2404.14619) - An efficient language model family with open training and inference framework. [[Github]](https://github.com/apple/corenet).\n\n\u003c!-- TOC --\u003e\u003ca name=\"limitations-of-cloud-based-llm-inference-and-advantages-of-on-device-inference\"\u003e\u003c/a\u003e\n### Limitations of Cloud-Based LLM Inference and Advantages of On-Device Inference\n  - [Ferret-v2](https://arxiv.org/abs/2404.07973) - An improved baseline for referring and grounding with large language models.\n  - [Phi-3 Technical Report](https://arxiv.org/abs/2404.14219) - A highly capable language model locally on your phone.\n  - [Exploring post-training quantization](https://arxiv.org/abs/2303.08302) - Comprehensive study to low rank compensation.\n  - [Matrix compression](https://arxiv.org/abs/2310.11028) - Randomized low rank and low precision factorization. [[Github]](https://github.com/pilancilab/matrix-compressor).\n\n\u003c!-- TOC --\u003e\u003ca name=\"the-performance-indicator-of-on-device-llms\"\u003e\u003c/a\u003e\n### The Performance Indicator of On-Device LLMs\n  - [MNN](https://github.com/alibaba/MNN) - A lightweight deep neural network inference engine.\n  - [PowerInfer-2](https://arxiv.org/abs/2406.06282) - Fast large language model inference on a smartphone. [[Github]](https://github.com/SJTU-IPADS/PowerInfer).\n  - [llama.cpp](https://github.com/ggerganov/llama.cpp) - Lightweight library for approximate nearest neighbors and maximum inner product search.\n  - [Powerinfer](https://arxiv.org/abs/2312.12456) - Fast large language model serving with a consumer-grade GPU. [[Github]](https://github.com/SJTU-IPADS/PowerInfer).\n\n\u003c!-- TOC --\u003e\u003ca name=\"efficient-architectures-for-on-device-llms\"\u003e\u003c/a\u003e\n### Efficient Architectures for On-Device LLMs\n  - [MobileLLM](https://arxiv.org/abs/2402.14905) - High accuracy, optimized for sub-billion parameter models, embedding sharing, grouped-query attention, reduced model size.\n  - [EdgeShard](https://arxiv.org/abs/2405.14371) - Up to 50% latency reduction, collaborative edge-cloud computing, optimal shard placement, distributed model components reduce individual device load.\n  - [LLMCad](https://arxiv.org/abs/2309.04255) - Up to 9.3× speedup in token generation, generate-then-verify, token tree generation, smaller LLM for token generation, larger LLM for verification.\n  - [Any-Precision LLM](https://arxiv.org/abs/2402.10517) - Supports multiple precisions efficiently, post-training quantization, memory-efficient design, substantial memory savings with versatile model precisions.\n  - [Breakthrough Memory](https://ieeexplore.ieee.org/abstract/document/10477465) - Up to 4.5× performance improvement, PIM and PNM technologies enhance memory processing, enhanced memory bandwidth and capacity.\n  - [MELTing Point](https://arxiv.org/abs/2403.12844) - Provides systematic performance evaluation, analyzes impacts of quantization, efficient model evaluation, evaluates memory and computational efficiency trade-offs.\n  - [LLMaaS on device](https://arxiv.org/abs/2403.11805) - Reduces context switching latency significantly, stateful execution, fine-grained KV cache compression, efficient memory management with tolerance-aware compression and swapping.\n  - [LocMoE](https://arxiv.org/abs/2401.13920) - Reduces training time per epoch by up to 22.24%, orthogonal gating weights, locality-based expert regularization, minimizes communication overhead with group-wise All-to-All and recompute pipeline.\n  - [EdgeMoE](https://arxiv.org/abs/2308.14352) - Significant performance improvements on edge devices, expert-wise bitwidth adaptation, preloading experts, efficient memory management through expert-by-expert computation reordering.\n  - [JetMoE](https://arxiv.org/abs/2404.07413) - Outperforms Llama27B and 13B-Chat with fewer parameters, reduces inference computation by 70% using sparse activation, 8B total parameters, only 2B activated per input token.\n  - [Pangu-$\\pi$ Pro](https://arxiv.org/abs/2402.02791) - Neural architecture, parameter initialization, and optimization strategy for billion-level parameter models, embedding sharing, tokenizer compression, reduced model size via architecture tweaking.\n  - [Zamba2](https://www.zyphra.com/post/zamba2-small) - 2x faster time-to-first-token, a 27% reduction in memory overhead, and a 1.29x lower generation latency compared to Phi3-3.8B, hybrid Mamba2/Attention architecture and shared transformer block, 2.7B parameters, fewer KV-states due to reduced attention.\n\n\u003c!-- TOC --\u003e\u003ca name=\"model-compression-and-parameter-sharing\"\u003e\u003c/a\u003e\n### Model Compression and Parameter Sharing\n  - [AWQ](https://arxiv.org/abs/2306.00978) - Activation-aware weight quantization for LLM compression and acceleration. [[Github]](https://github.com/mit-han-lab/llm-awq).\n  - [MobileLLM](https://arxiv.org/abs/2402.14905) - Optimizing sub-billion parameter language models for on-device use cases. [[Github]](https://github.com/facebookresearch/MobileLLM).\n\n\u003c!-- TOC --\u003e\u003ca name=\"collaborative-and-hierarchical-model-approaches\"\u003e\u003c/a\u003e\n### Collaborative and Hierarchical Model Approaches\n  - [EdgeShard](https://arxiv.org/abs/2405.14371) - Efficient LLM inference via collaborative edge computing.\n  - [Llmcad](https://arxiv.org/abs/2309.04255) - Fast and scalable on-device large language model inference.\n\n\u003c!-- TOC --\u003e\u003ca name=\"memory-and-computational-efficiency\"\u003e\u003c/a\u003e\n### Memory and Computational Efficiency\n  - [Breakthrough Memory Solutions](https://ieeexplore.ieee.org/document/10477465) - Improved performance on LLM inference.\n  - [MELTing Point](https://arxiv.org/abs/2403.12844) - Mobile evaluation of language transformers. [[Github]](https://github.com/brave-experiments/MELT-public).\n\n\u003c!-- TOC --\u003e\u003ca name=\"mixture-of-experts-moe-architectures\"\u003e\u003c/a\u003e\n### Mixture-of-Experts (MoE) Architectures\n  - [LLM as a System Service](https://arxiv.org/abs/2403.11805) - On mobile devices.\n  - [Locmoe](https://arxiv.org/abs/2401.13920) - Low-overhead MoE for large language model training.\n  - [Edgemoe](https://arxiv.org/abs/2308.14352) - Fast on-device inference of MoE-based large language models.\n\n\u003c!-- TOC --\u003e\u003ca name=\"hybrid-architectures\"\u003e\u003c/a\u003e\n### Hybrid Architectures\n  - [Zamba2](https://www.zyphra.com/post/zamba2-small) - Hybrid Mamba2 and attention models for on-device. [[Zamba2-2.7B]](https://www.zyphra.com/post/zamba2-small) [[Zamba2-1.2B]](https://www.zyphra.com/post/zamba2-mini).\n\n\u003c!-- TOC --\u003e\u003ca name=\"general-efficiency-and-performance-improvements\"\u003e\u003c/a\u003e\n### General Efficiency and Performance Improvements\n  - [Any-Precision LLM](https://www.arxiv.org/pdf/2402.10517) - Low-cost deployment of multiple, different-sized LLMs. [[Github]](https://github.com/SNU-ARC/any-precision-llm).\n  - [On the Viability of Using LLMs for SW/HW Co-design](https://arxiv.org/abs/2306.06923) - An example in designing CIM DNN accelerators.\n\n","projects_url":"https://awesome.ecosyste.ms/api/v1/lists/nickvasdev%2Fawesome-ai/projects"}