A curated library of the best AI learning resources—courses, tutorials, docs, and talks on agentic AI, MCP, Agent Skills, RAG, machine learning, fine-tuning, models, and frameworks, for AI engineers and technical teams.
Take a customer-support agent from first run to production with tracing, datasets, LLM-as-judge and online evals.
Why a two-point lead on an agentic coding leaderboard can come from container limits rather than the model.
Three patterns for agents with hundreds of tools: tool search, programmatic tool calling and tool use examples.
A real build log for serving frontier open-weight LLMs at home: budget tiers, 4x RTX PRO 6000, PCIe switches, vLLM and the BIOS/kernel fixes that make P2P work.
Build a complete multi-agent framework from scratch, then use it for workflows, orchestration, computer use, evals and MCP/A2A.
A free 21-lesson, code-first on-ramp from prompts to RAG, function calling, agents and fine-tuning, in Python and TypeScript.
The resources learners opened most this week.
Simon Willison's free, growing guide to getting reliable, reviewable code out of coding agents like Claude Code and OpenAI Codex.
A free, open-source 10-chapter textbook on building AI agents, from context engineering and memory to evals, post-training and multi-agent systems, with runnable Python experiments.
Build and train a ~10M-parameter GPT on your laptop in six guided parts, from tokenizer to text generation
CMU's full-semester generative AI course, from RNN language models to diffusion, MoE, reasoning models and agents
A peer-reviewed map of agentic LLMs organised as reason, act and interact, with a five-point research agenda.
Google's free five-day agents intensive, rebuilt around vibe coding: tools, skills, memory, security and production deployment.
Give AI agents safe, pooled, observable database tools over MCP, defined in a single tools.yaml.
Train multi-turn, tool-using LLM agents with RL on your own GPUs, including running Tinker scripts unchanged.
Learn how AI agents can return rich, native UIs as safe declarative JSON instead of text or executable code.
MIT's graduate deep learning course, co-taught by Kaiming He and Phillip Isola, covering architectures, representation learning, scaling laws and generative models.
A dense, free ~185-page deep learning primer that takes you from losses and backprop to transformers, diffusion, quantization and adapters.
Harvard's graduate AI safety seminar, 2026 edition: RL post-training, interpretability, cyber and bio risk, taught with guests from Anthropic and OpenAI.
Build a private, offline multimodal memory for an AI assistant with Qdrant Edge, CLIP, YOLO and Whisper.
Nathan Lambert's free video lecture series on LLM post-training: reward models, RL, DPO, reasoning models and agents.
Chelsea Finn's Stanford deep RL course, from policy gradients to RL for LLM preference optimization and reasoning.
Hugging Face's March 2026 write-up of 90 rephrasing experiments, 1T+ generated tokens and 12.7 GPU-years: how to generate synthetic pretraining data that works.
Anthropic's free follow-up MCP course on sampling, notifications, roots, and the STDIO and StreamableHTTP transports you need in production.
The free, 83k-star roadmap from LLM math to fine-tuning, quantization, RAG, agents and deployment, with runnable Colab notebooks.