owainlewis / awesome-artificial-intelligence

2015-01-27 · Source: Github Trending: All languages · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Software Development & Engineering, Robotics & Autonomous Systems · Depth: Intermediate, medium

Summary

The "owainlewis / awesome-artificial-intelligence" GitHub repository presents a curated collection of actively maintained resources for building and deploying AI systems, with a strong focus on AI engineering, including RAG, agents, evaluations, guardrails, and deployment. The repository is structured into several key sections: "Learn" offers modern and foundational books, courses from Google and Stanford, and landmark papers like "Attention Is All You Need." The "Build" section details guides, frameworks such as LangGraph and LlamaIndex, evaluation tools, and LLM-powered IDEs like Cursor. "Agents" lists various coding agents, including Claude Code and AutoGen, with performance comparisons available on Terminal-Bench. "Models" covers leading language models (e.g., ChatGPT, Llama, Mistral), image generators (Midjourney), video tools (Google Veo), and audio platforms (ElevenLabs). It also includes "Compare" for live benchmarks and "Follow" for newsletters.

Key takeaway

For AI Engineers building or deploying complex AI systems, this curated list is an invaluable starting point. You should consult it to identify robust tools for RAG, agent development, and model evaluation. This ensures your projects use actively maintained and effective resources. Review the "Learn" section for foundational knowledge or specific courses. Explore the "Models" section for advanced options across modalities. This resource streamlines your search for reliable AI engineering components.

Key insights

The repository provides a comprehensive, curated toolkit for AI engineering, from foundational learning to advanced deployment.

Principles

• Prioritize actively maintained, essential AI resources.
• Emphasize AI engineering for robust system deployment.
• Foundational knowledge ensures long-term value.

In practice

• Explore specific LLM frameworks like LangGraph or LlamaIndex.
• Utilize coding agents such as Claude Code for refactoring.
• Consult OpenRouter for live model pricing and comparisons.

Topics

• AI Engineering
• Retrieval-Augmented Generation
• AI Agents
• LLM Frameworks
• Model Evaluation
• Generative AI Models

Code references

• SylphAI-Inc/LLM-engineer-handbook
• docling-project/docling
• openai/evals
• features/copilot
• openai/codex

Best for: AI Engineer, Machine Learning Engineer, MLOps Engineer

Related on AIssential

• Top 20 AI Keywords Everyone Should Know in 2026 (From LLMs to Autonomous AI Systems) — Modern AI systems are built on foundational concepts evolving into autonomous, multi-agent architectures.
• AI Engineering Book Summary — AI engineering prioritizes integrating pre-trained foundation models via APIs over training from scratch.
• Expert Guide to Building RAG Systems in 2026* — RAG systems have evolved significantly, requiring advanced architectures and comprehensive optimization for future effectiveness.
• AI for Developers - Cohere — Cohere's "AI for Developers" blog highlights recent advancements and practical guides across various AI domains, with articles published from October 2024 through May 2026.
• How to Actually Build an AI Agent: A Complete Step-by-Step Guide for 2026 — Building effective AI agents requires a structured approach beyond just model selection, focusing on goals, memory, tools, and rigorous testing.
• This Week in AI: Your Recap — Augmenting LLMs with advanced techniques like RAG and agentic workflows significantly enhances their real-world utility and precision.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Github Trending: All languages.