A repository dedicated to showcasing and exploring the fascinating world of generative artificial intelligence. 🌟 Star if you like it!
See the code
🆕 Last updated: January 2025
| Resource | Category | Description |
|---|---|---|
| LangGraph | Agent Frameworks | Stateful multi-agent orchestration |
| Inspect AI | Evaluation | UK AISI's open-source eval framework |
| DSPy | Frameworks | Programming (not prompting) LLMs |
| Pydantic AI | Agent Frameworks | Type-safe, model-agnostic agents |
| RAGAS | Evaluation | RAG pipeline evaluation |
Created by NatNew and Contributors
Awesome-Generative-AI is your go-to open source repository for exploring the dynamic and creative world of generative artificial intelligence. From AI-generated art to innovative applications in various domains, this repository offers a wealth of resources, projects, and inspiration. Project Roadmap
Generative AI is not just about technology; it's about the art of the possible. In this section, we delve into the vision, scope, and potential of generative AI. Learn about our community and how you can be a part of this exciting journey.
New to generative AI? No worries! Our step-by-step guide will help you set up your environment and start exploring the world of AI-driven creativity.
What is Generative AI?
| Link | Preview |
|---|---|
| What is generative AI? - McKinsey & Company | Generative artificial intelligence (AI) describes algorithms (such as ChatGPT) that can be used to create new content, including audio, code, images, text, simulations, and videos. Recent breakthroughs in the field have the potential to drastically change the way we approach content creation. |
| What is generative AI? - Gartner | Generative AI can learn from existing artifacts to generate new, realistic artifacts (at scale) that reflect the characteristics of the training data but don’t repeat it. It can produce a variety of novel content, such as images, video, music, speech, text, software code and product designs. |
| What is Generative AI? - Nvidia | Generative AI enables users to quickly generate new content based on a variety of inputs. Inputs and outputs to these models can include text, images, sounds, animation, 3D models, or other types of data. |
| What Is Generative AI: A Super-Simple Explanation Anyone Can Understand- Forbes | The term AI, as it's used today, refers to computer algorithms that can effectively simulate human cognitive processes - learning, decision-making, problem-solving, and even creativity. |
| The Turing Lectures: What is generative AI? | Generative AI refers to a type of artificial intelligence that involves creating new and original data or content. Unlike traditional AI models that rely on large datasets and algorithms to classify or predict outcomes, generative AI models are designed to learn the underlying patterns and structure of the data and generate novel outputs that mimic human creativity. |
Dive into our curated collection of the most innovative and inspiring generative AI projects. Each project comes with a comprehensive description, source codes, and insights.
Experience AI like never before with our interactive demos. Play around with AI models, create your art, music, or text, and see the magic unfold in real time.
Whether you're a beginner or an advanced learner, our collection of tutorials, guides, and resources will help you deepen your understanding of generative AI.
Your creativity can inspire many! Learn how you can contribute to this repository, and check out the amazing work done by our community.
Enter our virtual gallery showcasing a mesmerizing array of AI-generated art and media. Be inspired and perhaps contribute your masterpiece!
Got questions? Need help? Join our vibrant community in discussions, Q&A sessions, and get all the support you need for your generative AI journey.
Explore more! Here's a list of additional resources, tools, communities, and reading materials to fuel your curiosity and knowledge in generative AI.
Platforms for building, deploying, and managing AI agents at scale.
| Platform | Provider | Best For | Key Features |
|---|---|---|---|
| Microsoft Copilot Studio | Microsoft | Enterprise agents | Low-code, M365 integration, multi-agent orchestration |
| OpenAI Assistants API | OpenAI | Custom GPT agents | Code interpreter, retrieval, function calling |
| Google Vertex AI Agent Builder | Enterprise search & agents | Grounding, RAG, Google Cloud integration | |
| Amazon Bedrock Agents | AWS | AWS-integrated agents | Knowledge bases, action groups, guardrails |
| Azure AI Agent Service | Microsoft | Azure-native agents | Enterprise security, Azure integration |
| Salesforce Agentforce | Salesforce | CRM agents | Sales, service, marketing automation |
| LangGraph Platform | LangChain | Custom agent workflows | Stateful graphs, human-in-loop, LangSmith |
| Relevance AI | Relevance AI | No-code agents | Visual builder, tool library |
| Voiceflow | Voiceflow | Conversational agents | Visual design, multi-channel |
| Botpress | Botpress | Open-source agents | Self-hostable, visual flow builder |
| AI for Database | AI for Database | Database AI agents | Natural language queries, auto-refreshing dashboards, workflow triggers |
Microsoft Copilot Ecosystem Clarification:
| Product | What It Is | Target User |
|---|---|---|
| Microsoft Copilot (consumer) | ChatGPT-like assistant | General public |
| Microsoft 365 Copilot | AI in Word, Excel, Teams, etc. | Enterprise users |
| Microsoft Copilot Studio | Platform for building custom agents | Developers, makers |
| GitHub Copilot | AI code completion | Developers |
| Copilot+ PC | Hardware with local AI | Consumers |
Development environments with deeply integrated AI assistance.
| IDE | Description | AI Features | Pricing |
|---|---|---|---|
| Cursor | VS Code fork with native AI | Tab completion, chat, codebase Q&A, agent mode | Free tier available |
| Windsurf | AI-native IDE by Codeium | Flows, cascades, multi-file edits | Free tier available |
| Zed | High-performance collaborative editor | AI assistant, inline edits | Free (open source) |
| JetBrains AI Assistant | AI in IntelliJ ecosystem | Code completion, chat, refactoring | Subscription |
| Visual Studio + Copilot | Microsoft's full IDE | GitHub Copilot integration | Free tier available |
| VS Code + Copilot | Lightweight editor | GitHub Copilot, extensions | Free |
| Replit | Browser-based IDE | Ghostwriter AI, deployment | Free tier available |
| GitHub Codespaces | Cloud dev environments | Copilot, pre-configured | Free tier (60 hrs/mo) |
| Amazon CodeCatalyst | AWS dev environment | CodeWhisperer integration | Free tier available |
IDE Extensions:
| Extension | For | Description |
|---|---|---|
| GitHub Copilot | VS Code, JetBrains, Neovim | AI pair programmer |
| Codeium | 70+ editors | Free AI code completion |
| Tabnine | Most editors | Privacy-focused completion |
| Continue | VS Code, JetBrains | Open-source AI assistant |
| Cody | VS Code, JetBrains | Codebase-aware assistant |
| NotFair | Claude Code | Plugin for SEO, search analytics, and advertising workflow automation. |
| Tool | Description |
|---|---|
| PyRIT | Microsoft's Python Risk Identification Tool for generative AI |
| Garak | LLM vulnerability scanner |
| Adversarial Robustness Toolbox | Python library for ML security - evasion, poisoning, extraction |
| AI Village CTF | Capture the flag challenges at DEFCON |
| SAIF | Google's guide to Secure AI Framework |
| TrojAI Security | AI security research channel |
| AVID | AI Vulnerability Database |
| NIST AI | NIST AI risk management framework |
| AI Security Institute (AISI) | UK government AI safety research |
| PortSwigger Web Security | Web application security training |
Guidelines for building secure, maintainable, and production-ready AI systems.
Security:
| Practice | Description | Resources |
|---|---|---|
| Input validation | Sanitize and validate all user inputs | OWASP LLM Top 10 |
| Prompt injection defense | Guard against instruction hijacking | Rebuff, LLM Guard |
| Output filtering | Scan outputs for sensitive data, harmful content | Guardrails AI, NeMo Guardrails |
| API key management | Never commit keys, use secrets managers | Azure Key Vault, AWS Secrets Manager |
| Rate limiting | Protect against abuse and cost overruns | API gateway policies |
| Audit logging | Track all AI interactions | LangSmith, Langfuse |
GitHub Hygiene:
| Practice | Why | How |
|---|---|---|
.gitignore for AI | Exclude model weights, API keys, caches | gitignore.io |
| Pre-commit hooks | Catch secrets before commit | pre-commit, detect-secrets |
| Dependency scanning | Identify vulnerabilities | Dependabot, Snyk |
| Branch protection | Require reviews for main | GitHub branch rules |
| Signed commits | Verify authorship | GPG signing |
| CODEOWNERS | Define ownership | .github/CODEOWNERS |
Testing AI Systems:
| Test Type | Purpose | Tools |
|---|---|---|
| Unit tests | Test individual components | pytest, unittest |
| Integration tests | Test tool/API interactions | pytest, responses |
| Evaluation tests | Measure model quality | DeepEval, RAGAS |
| Regression tests | Catch quality degradation | PromptFoo |
| Red team tests | Find adversarial failures | Garak, PyRIT |
| Load tests | Verify performance at scale | Locust, k6 |
Production Checklist:
Essential reading for understanding generative AI foundations, applications, and implications.
Foundations & Technical:
| Title | Author | Focus |
|---|---|---|
| Designing Machine Learning Systems | Chip Huyen | Production ML systems design |
| Build a Large Language Model (From Scratch) | Sebastian Raschka | LLM architecture and training |
| Natural Language Processing with Transformers | Lewis Tunstall, Leandro von Werra, Thomas Wolf | Hugging Face ecosystem |
| Generative Deep Learning | David Foster | VAEs, GANs, Transformers |
| Deep Learning | Ian Goodfellow, Yoshua Bengio, Aaron Courville | Foundational deep learning theory |
| Hands-On Large Language Models | Jay Alammar, Maarten Grootendorst | Practical LLM applications |
AI Safety & Ethics:
| Title | Author | Focus |
|---|---|---|
| Human Compatible | Stuart Russell | Value alignment problem |
| The Alignment Problem | Brian Christian | Survey of AI safety challenges |
| Superintelligence | Nick Bostrom | Long-term AI risks |
| AI Ethics | Mark Coeckelbergh | Philosophical foundations |
| Weapons of Math Destruction | Cathy O'Neil | Algorithmic bias and harm |
| Atlas of AI | Kate Crawford | Political economy of AI |
Strategy & Business:
| Title | Author | Focus |
|---|---|---|
| Co-Intelligence | Ethan Mollick | Living and working with AI |
| The Coming Wave | Mustafa Suleyman | AI and synthetic biology futures |
| AI Superpowers | Kai-Fu Lee | US-China AI competition |
| Prediction Machines | Ajay Agrawal, Joshua Gans, Avi Goldfarb | Economics of AI |
CLI tools for interacting with AI models and building AI-powered workflows.
| Tool | Provider | Description | Install |
|---|---|---|---|
| Claude CLI | Anthropic | Chat with Claude from terminal | npm install -g @anthropic-ai/claude-cli |
| Gemini CLI | Interact with Gemini models | npm install -g @anthropic-ai/gemini-cli | |
| OpenAI CLI | OpenAI | GPT models from command line | pip install openai |
| Aider | Open Source | AI pair programming in terminal | pip install aider-chat |
| Agent QA | Vostride | Natural-language web and mobile regression tests with persistent memory and run evidence; source-available under FSL-1.1-ALv2 | npm install -D agent-qa |
| LangChain CLI | LangChain | Scaffold and manage LangChain projects | pip install langchain-cli |
| LlamaIndex CLI | LlamaIndex | Build and query indices | pip install llama-index |
| Ollama | Ollama | Run open models locally | curl -fsSL https://ollama.ai/install.sh | sh |
| Simon Willison's LLM | Open Source | Access multiple LLMs from CLI | pip install llm |
| Fabric | Open Source | AI prompts and patterns library | pip install fabric-ai |
| sgpt | Open Source | Shell-GPT for command line | pip install shell-gpt |
| Warp AI | Warp | AI-native terminal | Desktop app |
| GitHub CLI + Copilot | GitHub | Copilot in the terminal | gh extension install github/gh-copilot |
Frameworks & Databases:
Tools:
Learning:
| Tool | Focus | Description |
|---|---|---|
| Inspect AI | General evaluation | UK AISI's open-source task-based eval framework |
| HELM | Holistic evaluation | Stanford's comprehensive LLM benchmarks |
| LM Evaluation Harness | Benchmark suite | EleutherAI's 200+ task evaluation framework |
| DeepEval | LLM testing | Unit tests and CI/CD for LLM apps |
| RAGAS | RAG evaluation | Retrieval quality and answer relevance metrics |
| TruLens | App evaluation | Feedback functions for groundedness and relevance |
| PromptFoo | Prompt testing | CLI-based prompt evaluation and comparison |
| Giskard | ML testing | Bias and robustness testing |
| OpenAI Evals | Eval framework | OpenAI's evaluation framework |
| Future AGI | LLM and agent evaluation | Open-source platform for evaluating, tracing, simulating, and improving LLM and AI agent applications. |
| Tool | Description | Key Features |
|---|---|---|
| LangChain | LLM application framework | Chains, memory, tool integration |
| LangGraph | Stateful multi-agent orchestration | Cycles, persistence, human-in-the-loop |
| LlamaIndex | Data framework for LLM apps | Indexing, retrieval, query engines |
| CrewAI | Role-playing agent orchestration | Agent roles, delegation, collaboration |
| AutoGen | Multi-agent conversation framework | Conversational patterns |
| DSPy | Programming (not prompting) LLMs | Optimizers, signatures, modules |
| Semantic Kernel | LLM integration SDK | Plugins, planners, memory |
| Haystack | End-to-end NLP framework | Pipelines, document stores |
| Pydantic AI | Type-safe agent framework | Model-agnostic, structured outputs |
Structured learning paths and certifications for AI skills.
| Platform | Focus | Cost |
|---|---|---|
| Google Cloud Skills Boost | GCP, Gemini, Vertex AI | Free + paid labs |
| Microsoft Learn | Azure AI, Copilot, M365 | Free |
| DeepLearning.AI | ML/AI courses by Andrew Ng | Free + paid |
| Coursera ML/AI Specializations | University courses | Subscription |
| fast.ai | Practical deep learning | Free |
| Hugging Face Learn | NLP, Transformers, Diffusion | Free |
| OpenAI Academy | Prompt engineering, APIs | Free |
| LangChain Academy | LangChain, LangGraph | Free |
| AWS Skill Builder | AWS AI services | Free + paid |
| DataCamp | Data science, ML | Subscription |
| Kaggle Learn | ML, Python, SQL | Free |
| Full Stack LLM Bootcamp | Production LLM apps | Free |
| Weights & Biases Courses | MLOps, LLMs | Free |
| Cohere LLM University | NLP fundamentals | Free |
| Link | Description |
|---|---|
| SingSong | We present SingSong, a system which generates instrumental music to accompany input vocals, potentially offering musicians and non-musicians alike an intuitive new way to create music featuring their own voice. |
| AI21labs | Build generative AI applications that solve today's business challenges, powered by AI21's state-of-the-art foundation and task-specific models. |
| HuggingFace AI Community | Host and collaborate on unlimited models, datasets and applications. |
| DeepSpeed | DeepSpeed is an easy-to-use deep learning optimization software suite that enables unprecedented scale and speed for DL Training and Inference. |
| Eleuther.ai | Empowering Open-Source Artificial Intelligence Research |
| Chainer.org | A Powerful, Flexible, and Intuitive Framework for Neural Networks |
| Kubeflow | The Machine Learning Toolkit for Kubernetes |
| Ainow | The AI Now Institute produces diagnosis and actionable policy research on artificial intelligence. |
| Microsoft responsible-ai-toolbox | About Responsible AI Toolbox is a suite of tools providing model and data exploration and assessment user interfaces and libraries that enable a better understanding of AI systems. |
| Trulens | Evaluate, iterate faster, and select your best LLM app with TruLens. |
| Jailbreak Chat | Your weekly report on all things AI and language models. Read by over 10,000 others at places like at Google, Tesla, Microsoft, a16z, and more. |
| ETHICAL INTELLIGENCE | Elevating the human in the equation |
| Purple Llama | An umbrella project featuring open trust and safety tools and evaluations meant to level the playing field for developers to responsibly deploy generative AI models and experiences in accordance with best practice |
| Oxa | Self-driving software and services that unlock the power of autonomy. |
| Deeprender.ai | Developing the next generation of compression technology using AI, we’re here to completely rethink, reshape and revolutionise what’s possible. |
| Papercup | We use data from real actors to produce voices so real that audiences can’t tell them apart from the real thing. |
| Onfido | Create trust at onboarding and beyond with a complete, AI-powered digital identity solution built to help you know your customers online. |
| Quantexa | Protect, optimize, and grow your organization with the power of Quantexa’s Decision Intelligence Platform and outcome-driven solutions. |
| Synthesia | Our AI Video Generator enables everyone to create professional videos without mics, cameras, actors or studios. |
| Causalens.com | Gain insights into Causal AI from blogs, white papers, case studies, webinars, and more. |
| Robina | The AI Copilot for your Contracts |
| PhysicsX | We are building AI and simulation engineering technologies to reinvent the design and operation of machines and products in advanced industries, with a strong focus on applications impacting the climate and human health. |
| Pitch | Pitch is the fastest way for your team to create and share beautiful presentations that get results. |
| Playgroundai | At Playground, we’re building an image editor that combines AI research and product design to enable people to create graphics like a Pro without being one. |
| Nexusflow.ai | Open source NexusRaven-V2, a 13B LLM outperforming GPT-4 in zero-shot function calling, the capability to turn natural language instructions into executable code to use tools. |
| Perplexity | Copilot |
| Giskard | Eliminate risks of biases, performance issues & security holes in ML models. In <8 lines of code. |
| Haystack | Open-source LLM framework to build production-ready applications |
| Bing Chat | Your everyday AI companion |
| N-Bref | Introducing N-Bref: a neural-based decompiler framework |
| Hydra | A framework for elegantly configuring complex applications |
| Ml-ferret | An End-to-End MLLM that Accept Any-Form Referring and Ground Anything in Response. |
| GTN | A new open source framework for automatic differentiation with graphs |
| ParlAI | ParlAI is a unified platform that streamlines the process of researching, training, and evaluating conversational AI models across multiple tasks at once. |
| Dynabench | DynaBench is a research platform for dynamic data collection and benchmarking. |
| KILT Benchmarking | KILT is a resource for training, evaluating and analyzing NLP models on Knowledge Intensive Language Tasks. |
| Glow | Glow is a machine learning compiler that accelerates the performance of deep learning frameworks on different hardware platforms. |
| AudioCraft | AudioCraft is a single-stop code base for all your generative audio needs: music, sound effects, and compression after training on raw audio signals. We have released controllable and high-quality models for music and audio generation from text inputs. |
| ELF | ELF is an extensive, lightweight, and flexible platform for game research that allows researchers and developers to train and test their algorithms in various game environments from board games to custom real-time strategy games. |
| PHYRE | PHYRE is a benchmark for PHYsical REasoning that contains a set of simple classical mechanics puzzles in a 2D environment. |
| Imagen 2 | DeepMind's most advanced text-to-image technology |
| SynthID | Identifying AI-generated content with SynthID |
| AlphaFold | AlphaFold is accelerating research in nearly every field of biology. |
| Phenaki | A model that can synthesize realistic videos from textual prompt sequences. |
| AlphaZero and MuZero | AlphaZero and MuZero are powerful, general AI systems, that mastered a range of board games and video games — and are now helping us solve real-world problems. |
| AlphaGo | AlphaGo mastered the ancient game of Go, defeated a Go world champion, and inspired a new era of AI systems. |
| PaLM 2 | PaLM 2 is our next generation large language model that builds on Google’s legacy of breakthrough research in machine learning and responsible AI. |
| PaLM-SayCan | a robotics algorithm that combines the understanding of language models with the real-world capabilities of a helper robot. |
| Universal Speech Model | Universal Speech Model (USM) is a family of state-of-the-art speech models with 2B parameters trained on 12 million hours of speech and 28 billion sentences of text, spanning 300+ languages. |
| WaveNet | Introduced in 2016, WaveNet was one of the first AI models to generate natural-sounding speech. |
| AlphaDev | AlphaDev uncovered a faster algorithm for sorting, a method for ordering data. Billions of people use these algorithms everyday without realising it. |
| AlphaCode | As part of DeepMind’s mission to solve intelligence, we created a system called AlphaCode that writes computer programs at a competitive level. |
| AlphaTensor | AlphaTensor, the first artificial intelligence (AI) system for discovering novel, efficient, and provably correct algorithms for fundamental tasks such as matrix multiplication. |
| AlphaStar | AlphaStar is the first AI to reach the top league of a widely popular esport without any game restrictions. |
| Gemini | Gemini is built from the ground up for multimodality — reasoning seamlessly across text, images, video, audio, and code. |
| Unsloth | Fast fine-tuning for LLMs, 2x faster with 60% less memory |
| Crawl4AI | Open-source LLM-friendly web crawler and scraper |
| ExcaliDraw | Virtual whiteboard for hand-drawn diagrams |
| Foldify | Protein folding prediction tool |
| Adaline.AI | AI workflow automation |
| CopilotKit | Open-source toolkit for building AI copilots |
| AG-UI Protocol | Agent-User Interaction Protocol for frontend apps |
| RAG-Anything | All-in-one RAG framework |
| GenAgents | Generative agents research implementation |
| Climate TRACE | AI-powered emissions tracking |
| Veo 3/4 | Google's AI video generation |
| Hailuo AI | Cinematic quality video generation by MiniMax |
| BasedLabs.ai | AI image and video creator |
| Jupyter Agent 2 | AI agent for Jupyter notebooks |
| prompts.chat | Awesome AI prompts library |
| AGENTS.md | Open source agent documentation tool |
| Microsoft Fabric Toolbox | Tools and accelerators for Microsoft Fabric |
| Copilot Studio Kit | Microsoft Copilot Studio accelerator kit |
| LlamaIndex | Build knowledge assistants over enterprise data |
| vLLM | High-throughput LLM serving with Qwen3-Next support |
| Weavy | AI-powered design workflows |
| CoreML for YOLO | CoreML export for YOLO11 models |
| Qwen | Qwen 3-Next open model |
| Model | Provider | Capabilities |
|---|---|---|
| GPT-4o | OpenAI | Text, vision, audio |
| Claude 3.5 | Anthropic | Text, vision, documents |
| Gemini Pro | Text, vision, audio, video | |
| Llama 3.2 Vision | Meta | Text, vision (open weights) |
| Pixtral | Mistral | Text, vision |
| Qwen2-VL | Alibaba | Text, vision (open weights) |
| Boogu-Image-0.1 | Boogu Project | Image understanding, text-to-image generation, image editing, bilingual text rendering (open weights) |
| Tool | Description | Key Features |
|---|---|---|
| LangSmith | LangChain's observability platform | Tracing, debugging, datasets |
| Phoenix (Arize) | Open-source LLM observability | Traces, embeddings, evals |
| Langfuse | Open-source tracing | Self-hostable, scores, cost tracking |
| Helicone | LLM observability | Logging, caching, analytics |
| Weights & Biases | ML experiment tracking | Prompts, artifacts, sweeps |
| Portkey | AI gateway | Observability, routing, fallbacks |
| Braintrust | Eval and logging platform | Experiments, datasets |
| Bifrost | AI gateway | Provider routing, failover, guardrails, usage controls, MCP, observability |
| Tool | Purpose | Key Feature |
|---|---|---|
| Hugging Face Hub | Model repository | 500k+ models available |
| Ollama | Local model runner | Simple CLI interface |
| LM Studio | Desktop app | GUI for running local models |
| llama.cpp | CPU inference | Efficient quantization |
| vLLM | High-throughput serving | PagedAttention optimization |
| Axolotl | Fine-tuning | Easy configuration-based training |
| Unsloth | Fast fine-tuning | 2x faster, 60% less memory |
Official guidance and blueprints from major AI providers.
Microsoft:
| Playbook | Focus |
|---|---|
| Azure AI Landing Zone | Enterprise AI architecture |
| Responsible AI Playbook | Ethics and governance |
| Copilot Studio Governance | Low-code agent governance |
| Azure OpenAI Landing Zone | Reference architecture |
| AI Red Team Playbook | Security testing |
OpenAI:
| Playbook | Focus |
|---|---|
| GPT Best Practices | Prompt engineering |
| Safety Best Practices | Safe deployments |
| Production Best Practices | Scaling guidance |
| Moderation Guide | Content filtering |
Google:
| Playbook | Focus |
|---|---|
| Generative AI on Vertex AI | GCP AI architecture |
| Responsible AI Practices | Ethics guidance |
| SAIF (Secure AI Framework) | Security framework |
| Gemini API Best Practices | API usage |
AWS:
| Playbook | Focus |
|---|---|
| Generative AI on AWS | AWS AI architecture |
| Bedrock Security | Bedrock security |
| Well-Architected ML Lens | ML best practices |
Community:
| Playbook | Focus |
|---|---|
| LangChain RAG Best Practices | RAG architecture |
| Anthropic Prompt Engineering | Claude prompting |
| Hugging Face Production Guide | Model deployment |
Researchers, practitioners, and thought leaders shaping the AI landscape.
Research & Academia:
| Person | Affiliation | Focus | Links |
|---|---|---|---|
| Andrew Ng | DeepLearning.AI, Stanford | ML education, AI applications | Twitter, LinkedIn |
| Yann LeCun | Meta AI, NYU | Deep learning, self-supervised learning | |
| Fei-Fei Li | Stanford HAI | Computer vision, human-centered AI | |
| Demis Hassabis | Google DeepMind | AGI, AlphaFold | |
| Ilya Sutskever | Safe Superintelligence Inc | Alignment, scaling | |
| Geoffrey Hinton | University of Toronto | Neural networks, AI safety | Website |
| Yoshua Bengio | Mila, University of Montreal | Deep learning, AI safety | |
| Andrej Karpathy | Independent | Neural networks, education | Twitter, YouTube |
Industry & Practice:
| Person | Affiliation | Focus | Links |
|---|---|---|---|
| Sam Altman | OpenAI | AI products, strategy | |
| Dario Amodei | Anthropic | AI safety, Claude | Anthropic |
| Mustafa Suleyman | Microsoft AI | AI products, ethics | |
| Satya Nadella | Microsoft | Enterprise AI | |
| Jensen Huang | NVIDIA | AI compute, hardware | NVIDIA |
| Emad Mostaque | Stability AI | Open-source AI |
Practitioners & Educators:
| Person | Focus | Links |
|---|---|---|
| Chip Huyen | MLOps, production ML | Twitter, Blog |
| Simon Willison | LLM tools, Datasette | Twitter, Blog |
| Hamel Husain | LLM engineering | Twitter, Blog |
| Eugene Yan | ML systems, RecSys | Twitter, Blog |
| Lilian Weng | OpenAI, ML research | Blog |
| Jay Alammar | LLM visualization | Blog |
| Sebastian Raschka | ML education | Twitter, Blog |
| Harrison Chase | LangChain | |
| Jerry Liu | LlamaIndex |
AI Safety & Ethics:
| Person | Focus | Links |
|---|---|---|
| Stuart Russell | Value alignment | Website |
| Max Tegmark | AI existential risk | |
| Timnit Gebru | AI ethics, bias | |
| Joy Buolamwini | Algorithmic justice | |
| Rumman Chowdhury | Responsible AI |
| Tool | Type | Description |
|---|---|---|
| Chroma | Vector DB | Open-source embedding database |
| Pinecone | Vector DB | Managed vector search service |
| Weaviate | Vector DB | Open-source with GraphQL API |
| Qdrant | Vector DB | High-performance vector similarity search |
| Milvus | Vector DB | Scalable open-source vector database |
| FAISS | Library | Facebook's efficient similarity search |
| Cohere Rerank | API | Neural reranking for search results |
| Unstructured | Preprocessing | Document parsing and chunking |
AI governance frameworks and regulations by jurisdiction.
European Union:
| Regulation | Status | Key Points |
|---|---|---|
| EU AI Act | In force (2024) | Risk-based classification, prohibited uses, conformity assessments |
| GDPR | In force | Data protection, automated decision-making rights |
| AI Liability Directive | Proposed | Fault-based liability for AI systems |
United Kingdom:
| Regulation | Status | Key Points |
|---|---|---|
| AI Safety Institute | Active | Pre-deployment testing, safety research |
| UK AI Regulation (Pro-Innovation) | Framework | Sector-specific, principles-based |
| ICO AI Guidance | Guidance | Data protection in AI |
United States:
| Regulation | Status | Key Points |
|---|---|---|
| Executive Order on AI (14110) | In force (2023) | Safety standards, red-teaming, watermarking |
| NIST AI Risk Management Framework | Published | Risk management guidance |
| State AI Laws | Various | Colorado, California, others |
China:
| Regulation | Status | Key Points |
|---|---|---|
| Generative AI Measures | In force (2023) | Content moderation, training data requirements |
| Algorithm Recommendation Rules | In force (2022) | Algorithmic transparency |
| Deep Synthesis Provisions | In force (2023) | Deepfake labeling |
International Standards:
| Standard | Organization | Focus |
|---|---|---|
| ISO/IEC 42001 | ISO | AI management system |
| ISO/IEC 23894 | ISO | AI risk management |
| IEEE 7000 | IEEE | Ethical system design |
| OECD AI Principles | OECD | International guidelines |
Tracking Resources:
| Tool | Type | Description |
|---|---|---|
| Guardrails AI | Library | Output validation and safety rails for LLM apps |
| NeMo Guardrails | Toolkit | NVIDIA's programmable safety rails |
| LLM Guard | Library | Input/output scanning for security risks |
| Rebuff | Library | Prompt injection detection |
| Lakera Guard | API | Real-time threat detection |
| Garak | Tool | LLM vulnerability scanner |
| Arthur Shield | Platform | Toxicity and hallucination detection |
Research Organizations:
Fliki - Video creation tool.
Lumen5 - AI-powered platform for engaging video content creation.
Synthesia - Generates videos from text inputs.
DeepBrain AI - Video tool.
Runway - Video tool.
Pictory - Video tool.
Flexclip - Offers templates and tools for editing and creating videos.
Elai - Customized AI video creation platform.
Veed.io - Generates professional-quality videos with speech-to-subtitle features.
PVID - AI video generation platform for photo-to-video, text-to-video, and video-to-video workflows, with access to models such as Kling, Sora, and Veo.
videos.social - Turns articles, PDFs, and prompts into narrated videos with editable scenes, scripts, and voiceovers.
OrkasVideoStudio - MIT-licensed, local-first TypeScript CLI and MCP toolkit for composing, editing, generating, and assembling videos from editable plan.json timelines.
shortshort - Turns one long talk, podcast, or course into vertical 9:16 shorts with word-by-word captions.
flowchart LR
API[Generative AI APIs] -->|Integration| FW[Frameworks]
FW -->|Customization| AI[AI Projects]
A repository dedicated to showcasing and exploring the fascinating world of generative artificial intelligence. 🌟 Star if you like it!
See the code
🆕 Last updated: January 2025
| Resource | Category | Description |
|---|---|---|
| LangGraph | Agent Frameworks | Stateful multi-agent orchestration |
| Inspect AI | Evaluation | UK AISI's open-source eval framework |
| DSPy | Frameworks | Programming (not prompting) LLMs |
| Pydantic AI | Agent Frameworks | Type-safe, model-agnostic agents |
| RAGAS | Evaluation | RAG pipeline evaluation |
Created by NatNew and Contributors
Awesome-Generative-AI is your go-to open source repository for exploring the dynamic and creative world of generative artificial intelligence. From AI-generated art to innovative applications in various domains, this repository offers a wealth of resources, projects, and inspiration. Project Roadmap
Generative AI is not just about technology; it's about the art of the possible. In this section, we delve into the vision, scope, and potential of generative AI. Learn about our community and how you can be a part of this exciting journey.
New to generative AI? No worries! Our step-by-step guide will help you set up your environment and start exploring the world of AI-driven creativity.
What is Generative AI?
| Link | Preview |
|---|---|
| What is generative AI? - McKinsey & Company | Generative artificial intelligence (AI) describes algorithms (such as ChatGPT) that can be used to create new content, including audio, code, images, text, simulations, and videos. Recent breakthroughs in the field have the potential to drastically change the way we approach content creation. |
| What is generative AI? - Gartner | Generative AI can learn from existing artifacts to generate new, realistic artifacts (at scale) that reflect the characteristics of the training data but don’t repeat it. It can produce a variety of novel content, such as images, video, music, speech, text, software code and product designs. |
| What is Generative AI? - Nvidia | Generative AI enables users to quickly generate new content based on a variety of inputs. Inputs and outputs to these models can include text, images, sounds, animation, 3D models, or other types of data. |
| What Is Generative AI: A Super-Simple Explanation Anyone Can Understand- Forbes | The term AI, as it's used today, refers to computer algorithms that can effectively simulate human cognitive processes - learning, decision-making, problem-solving, and even creativity. |
| The Turing Lectures: What is generative AI? | Generative AI refers to a type of artificial intelligence that involves creating new and original data or content. Unlike traditional AI models that rely on large datasets and algorithms to classify or predict outcomes, generative AI models are designed to learn the underlying patterns and structure of the data and generate novel outputs that mimic human creativity. |
Dive into our curated collection of the most innovative and inspiring generative AI projects. Each project comes with a comprehensive description, source codes, and insights.
Experience AI like never before with our interactive demos. Play around with AI models, create your art, music, or text, and see the magic unfold in real time.
Whether you're a beginner or an advanced learner, our collection of tutorials, guides, and resources will help you deepen your understanding of generative AI.
Your creativity can inspire many! Learn how you can contribute to this repository, and check out the amazing work done by our community.
Enter our virtual gallery showcasing a mesmerizing array of AI-generated art and media. Be inspired and perhaps contribute your masterpiece!
Got questions? Need help? Join our vibrant community in discussions, Q&A sessions, and get all the support you need for your generative AI journey.
Explore more! Here's a list of additional resources, tools, communities, and reading materials to fuel your curiosity and knowledge in generative AI.
Platforms for building, deploying, and managing AI agents at scale.
| Platform | Provider | Best For | Key Features |
|---|---|---|---|
| Microsoft Copilot Studio | Microsoft | Enterprise agents | Low-code, M365 integration, multi-agent orchestration |
| OpenAI Assistants API | OpenAI | Custom GPT agents | Code interpreter, retrieval, function calling |
| Google Vertex AI Agent Builder | Enterprise search & agents | Grounding, RAG, Google Cloud integration | |
| Amazon Bedrock Agents | AWS | AWS-integrated agents | Knowledge bases, action groups, guardrails |
| Azure AI Agent Service | Microsoft | Azure-native agents | Enterprise security, Azure integration |
| Salesforce Agentforce | Salesforce | CRM agents | Sales, service, marketing automation |
| LangGraph Platform | LangChain | Custom agent workflows | Stateful graphs, human-in-loop, LangSmith |
| Relevance AI | Relevance AI | No-code agents | Visual builder, tool library |
| Voiceflow | Voiceflow | Conversational agents | Visual design, multi-channel |
| Botpress | Botpress | Open-source agents | Self-hostable, visual flow builder |
| AI for Database | AI for Database | Database AI agents | Natural language queries, auto-refreshing dashboards, workflow triggers |
Microsoft Copilot Ecosystem Clarification:
| Product | What It Is | Target User |
|---|---|---|
| Microsoft Copilot (consumer) | ChatGPT-like assistant | General public |
| Microsoft 365 Copilot | AI in Word, Excel, Teams, etc. | Enterprise users |
| Microsoft Copilot Studio | Platform for building custom agents | Developers, makers |
| GitHub Copilot | AI code completion | Developers |
| Copilot+ PC | Hardware with local AI | Consumers |
Development environments with deeply integrated AI assistance.
| IDE | Description | AI Features | Pricing |
|---|---|---|---|
| Cursor | VS Code fork with native AI | Tab completion, chat, codebase Q&A, agent mode | Free tier available |
| Windsurf | AI-native IDE by Codeium | Flows, cascades, multi-file edits | Free tier available |
| Zed | High-performance collaborative editor | AI assistant, inline edits | Free (open source) |
| JetBrains AI Assistant | AI in IntelliJ ecosystem | Code completion, chat, refactoring | Subscription |
| Visual Studio + Copilot | Microsoft's full IDE | GitHub Copilot integration | Free tier available |
| VS Code + Copilot | Lightweight editor | GitHub Copilot, extensions | Free |
| Replit | Browser-based IDE | Ghostwriter AI, deployment | Free tier available |
| GitHub Codespaces | Cloud dev environments | Copilot, pre-configured | Free tier (60 hrs/mo) |
| Amazon CodeCatalyst | AWS dev environment | CodeWhisperer integration | Free tier available |
IDE Extensions:
| Extension | For | Description |
|---|---|---|
| GitHub Copilot | VS Code, JetBrains, Neovim | AI pair programmer |
| Codeium | 70+ editors | Free AI code completion |
| Tabnine | Most editors | Privacy-focused completion |
| Continue | VS Code, JetBrains | Open-source AI assistant |
| Cody | VS Code, JetBrains | Codebase-aware assistant |
| NotFair | Claude Code | Plugin for SEO, search analytics, and advertising workflow automation. |
| Tool | Description |
|---|---|
| PyRIT | Microsoft's Python Risk Identification Tool for generative AI |
| Garak | LLM vulnerability scanner |
| Adversarial Robustness Toolbox | Python library for ML security - evasion, poisoning, extraction |
| AI Village CTF | Capture the flag challenges at DEFCON |
| SAIF | Google's guide to Secure AI Framework |
| TrojAI Security | AI security research channel |
| AVID | AI Vulnerability Database |
| NIST AI | NIST AI risk management framework |
| AI Security Institute (AISI) | UK government AI safety research |
| PortSwigger Web Security | Web application security training |
Guidelines for building secure, maintainable, and production-ready AI systems.
Security:
| Practice | Description | Resources |
|---|---|---|
| Input validation | Sanitize and validate all user inputs | OWASP LLM Top 10 |
| Prompt injection defense | Guard against instruction hijacking | Rebuff, LLM Guard |
| Output filtering | Scan outputs for sensitive data, harmful content | Guardrails AI, NeMo Guardrails |
| API key management | Never commit keys, use secrets managers | Azure Key Vault, AWS Secrets Manager |
| Rate limiting | Protect against abuse and cost overruns | API gateway policies |
| Audit logging | Track all AI interactions | LangSmith, Langfuse |
GitHub Hygiene:
| Practice | Why | How |
|---|---|---|
.gitignore for AI | Exclude model weights, API keys, caches | gitignore.io |
| Pre-commit hooks | Catch secrets before commit | pre-commit, detect-secrets |
| Dependency scanning | Identify vulnerabilities | Dependabot, Snyk |
| Branch protection | Require reviews for main | GitHub branch rules |
| Signed commits | Verify authorship | GPG signing |
| CODEOWNERS | Define ownership | .github/CODEOWNERS |
Testing AI Systems:
| Test Type | Purpose | Tools |
|---|---|---|
| Unit tests | Test individual components | pytest, unittest |
| Integration tests | Test tool/API interactions | pytest, responses |
| Evaluation tests | Measure model quality | DeepEval, RAGAS |
| Regression tests | Catch quality degradation | PromptFoo |
| Red team tests | Find adversarial failures | Garak, PyRIT |
| Load tests | Verify performance at scale | Locust, k6 |
Production Checklist:
Essential reading for understanding generative AI foundations, applications, and implications.
Foundations & Technical:
| Title | Author | Focus |
|---|---|---|
| Designing Machine Learning Systems | Chip Huyen | Production ML systems design |
| Build a Large Language Model (From Scratch) | Sebastian Raschka | LLM architecture and training |
| Natural Language Processing with Transformers | Lewis Tunstall, Leandro von Werra, Thomas Wolf | Hugging Face ecosystem |
| Generative Deep Learning | David Foster | VAEs, GANs, Transformers |
| Deep Learning | Ian Goodfellow, Yoshua Bengio, Aaron Courville | Foundational deep learning theory |
| Hands-On Large Language Models | Jay Alammar, Maarten Grootendorst | Practical LLM applications |
AI Safety & Ethics:
| Title | Author | Focus |
|---|---|---|
| Human Compatible | Stuart Russell | Value alignment problem |
| The Alignment Problem | Brian Christian | Survey of AI safety challenges |
| Superintelligence | Nick Bostrom | Long-term AI risks |
| AI Ethics | Mark Coeckelbergh | Philosophical foundations |
| Weapons of Math Destruction | Cathy O'Neil | Algorithmic bias and harm |
| Atlas of AI | Kate Crawford | Political economy of AI |
Strategy & Business:
| Title | Author | Focus |
|---|---|---|
| Co-Intelligence | Ethan Mollick | Living and working with AI |
| The Coming Wave | Mustafa Suleyman | AI and synthetic biology futures |
| AI Superpowers | Kai-Fu Lee | US-China AI competition |
| Prediction Machines | Ajay Agrawal, Joshua Gans, Avi Goldfarb | Economics of AI |
CLI tools for interacting with AI models and building AI-powered workflows.
| Tool | Provider | Description | Install |
|---|---|---|---|
| Claude CLI | Anthropic | Chat with Claude from terminal | npm install -g @anthropic-ai/claude-cli |
| Gemini CLI | Interact with Gemini models | npm install -g @anthropic-ai/gemini-cli | |
| OpenAI CLI | OpenAI | GPT models from command line | pip install openai |
| Aider | Open Source | AI pair programming in terminal | pip install aider-chat |
| Agent QA | Vostride | Natural-language web and mobile regression tests with persistent memory and run evidence; source-available under FSL-1.1-ALv2 | npm install -D agent-qa |
| LangChain CLI | LangChain | Scaffold and manage LangChain projects | pip install langchain-cli |
| LlamaIndex CLI | LlamaIndex | Build and query indices | pip install llama-index |
| Ollama | Ollama | Run open models locally | curl -fsSL https://ollama.ai/install.sh | sh |
| Simon Willison's LLM | Open Source | Access multiple LLMs from CLI | pip install llm |
| Fabric | Open Source | AI prompts and patterns library | pip install fabric-ai |
| sgpt | Open Source | Shell-GPT for command line | pip install shell-gpt |
| Warp AI | Warp | AI-native terminal | Desktop app |
| GitHub CLI + Copilot | GitHub | Copilot in the terminal | gh extension install github/gh-copilot |
Frameworks & Databases:
Tools:
Learning:
| Tool | Focus | Description |
|---|---|---|
| Inspect AI | General evaluation | UK AISI's open-source task-based eval framework |
| HELM | Holistic evaluation | Stanford's comprehensive LLM benchmarks |
| LM Evaluation Harness | Benchmark suite | EleutherAI's 200+ task evaluation framework |
| DeepEval | LLM testing | Unit tests and CI/CD for LLM apps |
| RAGAS | RAG evaluation | Retrieval quality and answer relevance metrics |
| TruLens | App evaluation | Feedback functions for groundedness and relevance |
| PromptFoo | Prompt testing | CLI-based prompt evaluation and comparison |
| Giskard | ML testing | Bias and robustness testing |
| OpenAI Evals | Eval framework | OpenAI's evaluation framework |
| Future AGI | LLM and agent evaluation | Open-source platform for evaluating, tracing, simulating, and improving LLM and AI agent applications. |
| Tool | Description | Key Features |
|---|---|---|
| LangChain | LLM application framework | Chains, memory, tool integration |
| LangGraph | Stateful multi-agent orchestration | Cycles, persistence, human-in-the-loop |
| LlamaIndex | Data framework for LLM apps | Indexing, retrieval, query engines |
| CrewAI | Role-playing agent orchestration | Agent roles, delegation, collaboration |
| AutoGen | Multi-agent conversation framework | Conversational patterns |
| DSPy | Programming (not prompting) LLMs | Optimizers, signatures, modules |
| Semantic Kernel | LLM integration SDK | Plugins, planners, memory |
| Haystack | End-to-end NLP framework | Pipelines, document stores |
| Pydantic AI | Type-safe agent framework | Model-agnostic, structured outputs |
Structured learning paths and certifications for AI skills.
| Platform | Focus | Cost |
|---|---|---|
| Google Cloud Skills Boost | GCP, Gemini, Vertex AI | Free + paid labs |
| Microsoft Learn | Azure AI, Copilot, M365 | Free |
| DeepLearning.AI | ML/AI courses by Andrew Ng | Free + paid |
| Coursera ML/AI Specializations | University courses | Subscription |
| fast.ai | Practical deep learning | Free |
| Hugging Face Learn | NLP, Transformers, Diffusion | Free |
| OpenAI Academy | Prompt engineering, APIs | Free |
| LangChain Academy | LangChain, LangGraph | Free |
| AWS Skill Builder | AWS AI services | Free + paid |
| DataCamp | Data science, ML | Subscription |
| Kaggle Learn | ML, Python, SQL | Free |
| Full Stack LLM Bootcamp | Production LLM apps | Free |
| Weights & Biases Courses | MLOps, LLMs | Free |
| Cohere LLM University | NLP fundamentals | Free |
| Link | Description |
|---|---|
| SingSong | We present SingSong, a system which generates instrumental music to accompany input vocals, potentially offering musicians and non-musicians alike an intuitive new way to create music featuring their own voice. |
| AI21labs | Build generative AI applications that solve today's business challenges, powered by AI21's state-of-the-art foundation and task-specific models. |
| HuggingFace AI Community | Host and collaborate on unlimited models, datasets and applications. |
| DeepSpeed | DeepSpeed is an easy-to-use deep learning optimization software suite that enables unprecedented scale and speed for DL Training and Inference. |
| Eleuther.ai | Empowering Open-Source Artificial Intelligence Research |
| Chainer.org | A Powerful, Flexible, and Intuitive Framework for Neural Networks |
| Kubeflow | The Machine Learning Toolkit for Kubernetes |
| Ainow | The AI Now Institute produces diagnosis and actionable policy research on artificial intelligence. |
| Microsoft responsible-ai-toolbox | About Responsible AI Toolbox is a suite of tools providing model and data exploration and assessment user interfaces and libraries that enable a better understanding of AI systems. |
| Trulens | Evaluate, iterate faster, and select your best LLM app with TruLens. |
| Jailbreak Chat | Your weekly report on all things AI and language models. Read by over 10,000 others at places like at Google, Tesla, Microsoft, a16z, and more. |
| ETHICAL INTELLIGENCE | Elevating the human in the equation |
| Purple Llama | An umbrella project featuring open trust and safety tools and evaluations meant to level the playing field for developers to responsibly deploy generative AI models and experiences in accordance with best practice |
| Oxa | Self-driving software and services that unlock the power of autonomy. |
| Deeprender.ai | Developing the next generation of compression technology using AI, we’re here to completely rethink, reshape and revolutionise what’s possible. |
| Papercup | We use data from real actors to produce voices so real that audiences can’t tell them apart from the real thing. |
| Onfido | Create trust at onboarding and beyond with a complete, AI-powered digital identity solution built to help you know your customers online. |
| Quantexa | Protect, optimize, and grow your organization with the power of Quantexa’s Decision Intelligence Platform and outcome-driven solutions. |
| Synthesia | Our AI Video Generator enables everyone to create professional videos without mics, cameras, actors or studios. |
| Causalens.com | Gain insights into Causal AI from blogs, white papers, case studies, webinars, and more. |
| Robina | The AI Copilot for your Contracts |
| PhysicsX | We are building AI and simulation engineering technologies to reinvent the design and operation of machines and products in advanced industries, with a strong focus on applications impacting the climate and human health. |
| Pitch | Pitch is the fastest way for your team to create and share beautiful presentations that get results. |
| Playgroundai | At Playground, we’re building an image editor that combines AI research and product design to enable people to create graphics like a Pro without being one. |
| Nexusflow.ai | Open source NexusRaven-V2, a 13B LLM outperforming GPT-4 in zero-shot function calling, the capability to turn natural language instructions into executable code to use tools. |
| Perplexity | Copilot |
| Giskard | Eliminate risks of biases, performance issues & security holes in ML models. In <8 lines of code. |
| Haystack | Open-source LLM framework to build production-ready applications |
| Bing Chat | Your everyday AI companion |
| N-Bref | Introducing N-Bref: a neural-based decompiler framework |
| Hydra | A framework for elegantly configuring complex applications |
| Ml-ferret | An End-to-End MLLM that Accept Any-Form Referring and Ground Anything in Response. |
| GTN | A new open source framework for automatic differentiation with graphs |
| ParlAI | ParlAI is a unified platform that streamlines the process of researching, training, and evaluating conversational AI models across multiple tasks at once. |
| Dynabench | DynaBench is a research platform for dynamic data collection and benchmarking. |
| KILT Benchmarking | KILT is a resource for training, evaluating and analyzing NLP models on Knowledge Intensive Language Tasks. |
| Glow | Glow is a machine learning compiler that accelerates the performance of deep learning frameworks on different hardware platforms. |
| AudioCraft | AudioCraft is a single-stop code base for all your generative audio needs: music, sound effects, and compression after training on raw audio signals. We have released controllable and high-quality models for music and audio generation from text inputs. |
| ELF | ELF is an extensive, lightweight, and flexible platform for game research that allows researchers and developers to train and test their algorithms in various game environments from board games to custom real-time strategy games. |
| PHYRE | PHYRE is a benchmark for PHYsical REasoning that contains a set of simple classical mechanics puzzles in a 2D environment. |
| Imagen 2 | DeepMind's most advanced text-to-image technology |
| SynthID | Identifying AI-generated content with SynthID |
| AlphaFold | AlphaFold is accelerating research in nearly every field of biology. |
| Phenaki | A model that can synthesize realistic videos from textual prompt sequences. |
| AlphaZero and MuZero | AlphaZero and MuZero are powerful, general AI systems, that mastered a range of board games and video games — and are now helping us solve real-world problems. |
| AlphaGo | AlphaGo mastered the ancient game of Go, defeated a Go world champion, and inspired a new era of AI systems. |
| PaLM 2 | PaLM 2 is our next generation large language model that builds on Google’s legacy of breakthrough research in machine learning and responsible AI. |
| PaLM-SayCan | a robotics algorithm that combines the understanding of language models with the real-world capabilities of a helper robot. |
| Universal Speech Model | Universal Speech Model (USM) is a family of state-of-the-art speech models with 2B parameters trained on 12 million hours of speech and 28 billion sentences of text, spanning 300+ languages. |
| WaveNet | Introduced in 2016, WaveNet was one of the first AI models to generate natural-sounding speech. |
| AlphaDev | AlphaDev uncovered a faster algorithm for sorting, a method for ordering data. Billions of people use these algorithms everyday without realising it. |
| AlphaCode | As part of DeepMind’s mission to solve intelligence, we created a system called AlphaCode that writes computer programs at a competitive level. |
| AlphaTensor | AlphaTensor, the first artificial intelligence (AI) system for discovering novel, efficient, and provably correct algorithms for fundamental tasks such as matrix multiplication. |
| AlphaStar | AlphaStar is the first AI to reach the top league of a widely popular esport without any game restrictions. |
| Gemini | Gemini is built from the ground up for multimodality — reasoning seamlessly across text, images, video, audio, and code. |
| Unsloth | Fast fine-tuning for LLMs, 2x faster with 60% less memory |
| Crawl4AI | Open-source LLM-friendly web crawler and scraper |
| ExcaliDraw | Virtual whiteboard for hand-drawn diagrams |
| Foldify | Protein folding prediction tool |
| Adaline.AI | AI workflow automation |
| CopilotKit | Open-source toolkit for building AI copilots |
| AG-UI Protocol | Agent-User Interaction Protocol for frontend apps |
| RAG-Anything | All-in-one RAG framework |
| GenAgents | Generative agents research implementation |
| Climate TRACE | AI-powered emissions tracking |
| Veo 3/4 | Google's AI video generation |
| Hailuo AI | Cinematic quality video generation by MiniMax |
| BasedLabs.ai | AI image and video creator |
| Jupyter Agent 2 | AI agent for Jupyter notebooks |
| prompts.chat | Awesome AI prompts library |
| AGENTS.md | Open source agent documentation tool |
| Microsoft Fabric Toolbox | Tools and accelerators for Microsoft Fabric |
| Copilot Studio Kit | Microsoft Copilot Studio accelerator kit |
| LlamaIndex | Build knowledge assistants over enterprise data |
| vLLM | High-throughput LLM serving with Qwen3-Next support |
| Weavy | AI-powered design workflows |
| CoreML for YOLO | CoreML export for YOLO11 models |
| Qwen | Qwen 3-Next open model |
| Model | Provider | Capabilities |
|---|---|---|
| GPT-4o | OpenAI | Text, vision, audio |
| Claude 3.5 | Anthropic | Text, vision, documents |
| Gemini Pro | Text, vision, audio, video | |
| Llama 3.2 Vision | Meta | Text, vision (open weights) |
| Pixtral | Mistral | Text, vision |
| Qwen2-VL | Alibaba | Text, vision (open weights) |
| Boogu-Image-0.1 | Boogu Project | Image understanding, text-to-image generation, image editing, bilingual text rendering (open weights) |
| Tool | Description | Key Features |
|---|---|---|
| LangSmith | LangChain's observability platform | Tracing, debugging, datasets |
| Phoenix (Arize) | Open-source LLM observability | Traces, embeddings, evals |
| Langfuse | Open-source tracing | Self-hostable, scores, cost tracking |
| Helicone | LLM observability | Logging, caching, analytics |
| Weights & Biases | ML experiment tracking | Prompts, artifacts, sweeps |
| Portkey | AI gateway | Observability, routing, fallbacks |
| Braintrust | Eval and logging platform | Experiments, datasets |
| Bifrost | AI gateway | Provider routing, failover, guardrails, usage controls, MCP, observability |
| Tool | Purpose | Key Feature |
|---|---|---|
| Hugging Face Hub | Model repository | 500k+ models available |
| Ollama | Local model runner | Simple CLI interface |
| LM Studio | Desktop app | GUI for running local models |
| llama.cpp | CPU inference | Efficient quantization |
| vLLM | High-throughput serving | PagedAttention optimization |
| Axolotl | Fine-tuning | Easy configuration-based training |
| Unsloth | Fast fine-tuning | 2x faster, 60% less memory |
Official guidance and blueprints from major AI providers.
Microsoft:
| Playbook | Focus |
|---|---|
| Azure AI Landing Zone | Enterprise AI architecture |
| Responsible AI Playbook | Ethics and governance |
| Copilot Studio Governance | Low-code agent governance |
| Azure OpenAI Landing Zone | Reference architecture |
| AI Red Team Playbook | Security testing |
OpenAI:
| Playbook | Focus |
|---|---|
| GPT Best Practices | Prompt engineering |
| Safety Best Practices | Safe deployments |
| Production Best Practices | Scaling guidance |
| Moderation Guide | Content filtering |
Google:
| Playbook | Focus |
|---|---|
| Generative AI on Vertex AI | GCP AI architecture |
| Responsible AI Practices | Ethics guidance |
| SAIF (Secure AI Framework) | Security framework |
| Gemini API Best Practices | API usage |
AWS:
| Playbook | Focus |
|---|---|
| Generative AI on AWS | AWS AI architecture |
| Bedrock Security | Bedrock security |
| Well-Architected ML Lens | ML best practices |
Community:
| Playbook | Focus |
|---|---|
| LangChain RAG Best Practices | RAG architecture |
| Anthropic Prompt Engineering | Claude prompting |
| Hugging Face Production Guide | Model deployment |
Researchers, practitioners, and thought leaders shaping the AI landscape.
Research & Academia:
| Person | Affiliation | Focus | Links |
|---|---|---|---|
| Andrew Ng | DeepLearning.AI, Stanford | ML education, AI applications | Twitter, LinkedIn |
| Yann LeCun | Meta AI, NYU | Deep learning, self-supervised learning | |
| Fei-Fei Li | Stanford HAI | Computer vision, human-centered AI | |
| Demis Hassabis | Google DeepMind | AGI, AlphaFold | |
| Ilya Sutskever | Safe Superintelligence Inc | Alignment, scaling | |
| Geoffrey Hinton | University of Toronto | Neural networks, AI safety | Website |
| Yoshua Bengio | Mila, University of Montreal | Deep learning, AI safety | |
| Andrej Karpathy | Independent | Neural networks, education | Twitter, YouTube |
Industry & Practice:
| Person | Affiliation | Focus | Links |
|---|---|---|---|
| Sam Altman | OpenAI | AI products, strategy | |
| Dario Amodei | Anthropic | AI safety, Claude | Anthropic |
| Mustafa Suleyman | Microsoft AI | AI products, ethics | |
| Satya Nadella | Microsoft | Enterprise AI | |
| Jensen Huang | NVIDIA | AI compute, hardware | NVIDIA |
| Emad Mostaque | Stability AI | Open-source AI |
Practitioners & Educators:
| Person | Focus | Links |
|---|---|---|
| Chip Huyen | MLOps, production ML | Twitter, Blog |
| Simon Willison | LLM tools, Datasette | Twitter, Blog |
| Hamel Husain | LLM engineering | Twitter, Blog |
| Eugene Yan | ML systems, RecSys | Twitter, Blog |
| Lilian Weng | OpenAI, ML research | Blog |
| Jay Alammar | LLM visualization | Blog |
| Sebastian Raschka | ML education | Twitter, Blog |
| Harrison Chase | LangChain | |
| Jerry Liu | LlamaIndex |
AI Safety & Ethics:
| Person | Focus | Links |
|---|---|---|
| Stuart Russell | Value alignment | Website |
| Max Tegmark | AI existential risk | |
| Timnit Gebru | AI ethics, bias | |
| Joy Buolamwini | Algorithmic justice | |
| Rumman Chowdhury | Responsible AI |
| Tool | Type | Description |
|---|---|---|
| Chroma | Vector DB | Open-source embedding database |
| Pinecone | Vector DB | Managed vector search service |
| Weaviate | Vector DB | Open-source with GraphQL API |
| Qdrant | Vector DB | High-performance vector similarity search |
| Milvus | Vector DB | Scalable open-source vector database |
| FAISS | Library | Facebook's efficient similarity search |
| Cohere Rerank | API | Neural reranking for search results |
| Unstructured | Preprocessing | Document parsing and chunking |
AI governance frameworks and regulations by jurisdiction.
European Union:
| Regulation | Status | Key Points |
|---|---|---|
| EU AI Act | In force (2024) | Risk-based classification, prohibited uses, conformity assessments |
| GDPR | In force | Data protection, automated decision-making rights |
| AI Liability Directive | Proposed | Fault-based liability for AI systems |
United Kingdom:
| Regulation | Status | Key Points |
|---|---|---|
| AI Safety Institute | Active | Pre-deployment testing, safety research |
| UK AI Regulation (Pro-Innovation) | Framework | Sector-specific, principles-based |
| ICO AI Guidance | Guidance | Data protection in AI |
United States:
| Regulation | Status | Key Points |
|---|---|---|
| Executive Order on AI (14110) | In force (2023) | Safety standards, red-teaming, watermarking |
| NIST AI Risk Management Framework | Published | Risk management guidance |
| State AI Laws | Various | Colorado, California, others |
China:
| Regulation | Status | Key Points |
|---|---|---|
| Generative AI Measures | In force (2023) | Content moderation, training data requirements |
| Algorithm Recommendation Rules | In force (2022) | Algorithmic transparency |
| Deep Synthesis Provisions | In force (2023) | Deepfake labeling |
International Standards:
| Standard | Organization | Focus |
|---|---|---|
| ISO/IEC 42001 | ISO | AI management system |
| ISO/IEC 23894 | ISO | AI risk management |
| IEEE 7000 | IEEE | Ethical system design |
| OECD AI Principles | OECD | International guidelines |
Tracking Resources:
| Tool | Type | Description |
|---|---|---|
| Guardrails AI | Library | Output validation and safety rails for LLM apps |
| NeMo Guardrails | Toolkit | NVIDIA's programmable safety rails |
| LLM Guard | Library | Input/output scanning for security risks |
| Rebuff | Library | Prompt injection detection |
| Lakera Guard | API | Real-time threat detection |
| Garak | Tool | LLM vulnerability scanner |
| Arthur Shield | Platform | Toxicity and hallucination detection |
Research Organizations:
Fliki - Video creation tool.
Lumen5 - AI-powered platform for engaging video content creation.
Synthesia - Generates videos from text inputs.
DeepBrain AI - Video tool.
Runway - Video tool.
Pictory - Video tool.
Flexclip - Offers templates and tools for editing and creating videos.
Elai - Customized AI video creation platform.
Veed.io - Generates professional-quality videos with speech-to-subtitle features.
PVID - AI video generation platform for photo-to-video, text-to-video, and video-to-video workflows, with access to models such as Kling, Sora, and Veo.
videos.social - Turns articles, PDFs, and prompts into narrated videos with editable scenes, scripts, and voiceovers.
OrkasVideoStudio - MIT-licensed, local-first TypeScript CLI and MCP toolkit for composing, editing, generating, and assembling videos from editable plan.json timelines.
shortshort - Turns one long talk, podcast, or course into vertical 9:16 shorts with word-by-word captions.
flowchart LR
API[Generative AI APIs] -->|Integration| FW[Frameworks]
FW -->|Customization| AI[AI Projects]