owainlewis/awesome-artificial-intelligence

A curated list of Artificial Intelligence (AI) courses, books, video lectures and papers.

What it is

A hand-picked, regularly updated list of learning materials and tools for software developers who want to build AI-powered applications — especially ones that use large language models and autonomous "agent" systems. Think of it as a curated bookshelf and toolbox rather than an exhaustive directory.

Who it's for

Developers who want to:

  • Learn the core ideas behind modern AI
  • Build apps using language models, search/retrieval, and AI agents
  • Test, monitor, and launch AI systems in real products
  • Use AI coding assistants to write software faster

How it's curated

The maintainer is intentionally selective. Every entry must meet a quality bar for technical depth, practical usefulness, evidence, and uniqueness. The list is reviewed weekly by an automated process that validates and merges changes. Categories can be short — the maintainer prefers a few strong picks over many mediocre ones.

What's inside

  1. Learn — Books (e.g., Artificial Intelligence: A Modern Approach, Build a Large Language Model from Scratch), online courses (e.g., Fast.ai, Hugging Face's LLM course), and foundational research papers (e.g., "Attention Is All You Need", which introduced the Transformer architecture).

  2. Build AI systems — Practical guides from companies like Anthropic and OpenAI, engineering patterns for LLM apps, communication protocols (Model Context Protocol, Agent2Agent), agent frameworks (LangGraph, Pydantic AI), retrieval tools (LlamaIndex, Haystack), evaluation frameworks (Promptfoo, Ragas), and deployment tools (vLLM, Langfuse).

  3. Agentic software engineering — A section on AI coding agents (Claude Code, Codex CLI, Aider, Cline, and others), plus resources on orchestrating multiple agents and building "software factories" that use AI to plan, write, review, and ship code.

Notable extras

The README links to a free "AI Engineer starter pack" with tutorials and software discounts. It also points to several companion projects by the same maintainer: Neo (a terminal coding agent), Blueprint (agent skills), and Factory (a control plane for coordinating multiple coding agents).

How to contribute

Suggestions are welcome but must follow a contribution guide and curation policy. Proposed resources should serve developers, offer real technical value, be current (unless foundational), differ meaningfully from existing entries, and have factual descriptions backed by primary sources. Contributors must disclose any affiliation with the resource they suggest.

Related

  • Project
    MODSetter/SurfSense

    SurfSense is an open‑source, Apache‑2.0‑licensed desktop app that provides an offline AI agent for researching, creating, editing, and converting documents (PDF, Word, Excel, PPT, images, audio, etc.). Users choose any OpenAI‑compatible or local LLM, keep all data on‑device, and can extend functionality with web‑search plugins.

  • Project
    xpzouying/xiaohongshu-mcp

    A self‑hosted MCP server that lets AI assistants read/write Xiaohongshu (login, post images/video, search, comment, like, fetch profiles, etc.). Install via binary, Docker, or source, log in once, start the service on port 18060, and connect any MCP‑compatible client (Claude Code, Cursor, VS Code, Open Claw, etc.).

  • Project
    ag-ui-protocol/ag-ui

    AG‑UI is an open, lightweight, event‑based protocol that standardises how AI agents interact with user‑facing applications. It defines ~16 event types, supports any transport (SSE, WebSocket, webhook), and provides middleware, SDKs (Kotlin, Go, Rust, etc.) and first‑party integrations (LangChain, CrewAI, Microsoft Agent Framework, CopilotKit). Features include real‑time streaming chat, bi‑directional state sync, generative UI messages, and human‑in‑the‑loop collaboration. The project offers a CLI starter, a Dojo of small examples, and is MIT‑licensed with an active community.

  • Project
    xbtlin/ai-berkshire

    A structured investment research framework for Claude Code and Codex that applies value investing methodologies to generate professional, decision-grade financial reports.