人工智能

Awesome Artificial Intelligence¶

A curated collection of must-use, actively maintained resources for building and shipping AI systems.

Focus: AI engineering (RAG, agents, evals, guardrails, deploy) plus the best books, guides, papers, and a carefully selected set of tools.

🏛 Core Resources (Evergreen)¶

The foundations — these will still be valuable five years from now, even if today’s tools are gone.

📚 Books¶

Modern & Practical - Designing Machine Learning Systems — Scalable, maintainable ML pipelines (Chip Huyen). - Generative Deep Learning (2^nd Edition) — GANs, VAEs, diffusion models (David Foster). - AI Engineering — End-to-end AI product building (Chip Huyen). - 100 Page Language Models Book — This book guides you through the evolution of language models, starting from machine learning fundamentals.

Foundational - Artificial Intelligence: A Modern Approach — Comprehensive AI theory (Russell & Norvig). - Deep Learning — Neural networks & architectures (Goodfellow, Bengio, Courville). - Reinforcement Learning: An Introduction (2^nd Edition) — RL fundamentals (Sutton & Barto).

🏗 AI Engineering¶

Frameworks and design patterns for building robust, production-grade AI systems.
Personal note: you don't need tons of frameworks — start with simple LLM calls and work up.

📖 Guides & Playbooks¶

Building Effective Agents (Anthropic) — ⭐ Patterns, pitfalls, and tradeoffs for designing AI agents.
OpenAI Agents Guide — Practical guide on building agents
Google AI Agents Paper - Practical guide to building AI agents from Google
Google Agents Companion Paper - Guide from Google
OpenAI Cookbook — Example code, recipes, and best practices for working with OpenAI APIs.
LLM Engineer Handbook — A goldmine of useful links for AI engineers

🤖 Frameworks¶

PocketFlow — Extremely minimalist AI agent framework in just 100 lines of code. Fantastic way to learn.
Google ADK — Google's Agent Development Kit (Python, Java). Great local development experience + A2A + MCP.
Pydantic-AI — Typed, structured LLM orchestration framework built on Pydantic models for safe, predictable outputs.
LangGraph — Build multi-agent workflows with stateful graphs on top of LangChain.
CrewAI — Agent orchestration with structured tasks and human-in-the-loop controls.
AutoGen — Microsoft’s framework for multi-agent conversation and collaboration.

📦 Retrieval-Augmented Generation (RAG)¶

LlamaIndex — Data framework for ingesting, indexing, and querying private data with LLMs.
Haystack — Open-source search/RAG framework with modular pipelines.
Docling — Great library for ingesting any kind of document for RAG ⭐

Evals¶

OpenAI Evals — OpenAI's framework for writing evals

📄 Landmark Papers¶

Research that shaped modern AI — worth reading to understand the "why" behind today’s architectures. - Attention Is All You Need — Transformer architecture. - Scaling Laws for Neural Language Models — Model/data/compute scaling. - Language Models are Few-Shot Learners — GPT-3 capabilities. - Constitutional AI — Safer model alignment.

🎓 Courses¶

Learn from the best — structured content for every level.

Beginner - Google Generative AI Learning Path - Hugging Face LLM Course - Fast.ai — Practical Deep Learning

Intermediate / Advanced - Stanford CS324: Large Language Models - Full Stack Deep Learning - MIT 6.S191: Intro to Deep Learning

Focused - DeepLearning.AI Short Courses - Google Deepmind| Introduction to Reinforcement Learning - Karpathy’s LLM Zero-to-Hero - Neural Nets - Zero-to-Hero

📰 Newsletters¶

Stay current with AI developments without drowning in noise. - The Rundown AI - AlphaSignal - Superhuman AI - AI Engineer

⚡ Tools¶

Tools for building and deploying AI applications.

💬 Models¶

ChatGPT — Best for general coding + reasoning.
Claude — Best for long-context analysis and structured thinking.
Gemini — Best for Google ecosystem integration.
Perplexity — Best for quick research with live citations.
Cohere — Best for enterprise LLMs with strong retrieval-augmented generation APIs.
Mistral — Best for lightweight, high-performance open-weight models.
Qwen — Best for multilingual and Chinese-first applications.
DeepSeek — Best for efficient, cost-optimized large models with competitive reasoning.

👨‍💻 Code & Developer Tools¶

Claude Code — IDE extensions with long-context code edits.
GitHub Copilot — In-IDE code completion, chat, and refactors.
Cursor — LLM-powered IDE for multi-file edits and codebase-aware chat.

🎨 Multimedia AI Tools¶

🖼 Image¶

ChatGPT-4o Image Generation — Integrated image creation with style control.
Midjourney — Artistic and photorealistic images and video.
Adobe Firefly — Integrated into Creative Cloud.
Ideogram — Precise, legible text in generated images.
Flux — High-res, prompt-editable images.

🎥 Video¶

Kling — Cinematic, realistic video generation.
Google Veo 3 — High-quality video with synchronized audio.
Runway — Video editing + generation.

🎙 Audio¶

ElevenLabs — High-quality text-to-speech.
Suno — AI music from text prompts.
Aiva — Music composition for media.