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.
The ingestion half of RAG, documented properly: partition strategies, typed elements, element metadata and document-aware chunking.
Anthropic's own 84-lesson path from a first API call to production evals, RAG, MCP servers and agent workflows.
Open the black box you call every day — from the autoregressive loop to KV cache, flash attention and speculative decoding.
The reference card for Meta's Apache-2.0 30B agentic model, with the quantised memory footprints an engineer actually needs.
Run a coding agent unattended inside a microVM that cannot reach your host, your keys or your other repos.
Hard evidence, from 824 programmatic checks, that your AGENTS.md does not actually govern your agent.
The resources learners opened most this week.
A 15,000-word open recipe: hybrid Mamba-2 MoE architecture, training data, RL stages and serving.
Train, index and serve ColBERT-style multi-vector retrievers with a Sentence Transformers API.
Anthropic's own hour-long course on running Claude Code unsupervised and trusting the result.
The full manual for running an approval-gated coding agent across your editor, terminal and CI.
Bolt reinforcement learning onto the agent you already shipped, without rewriting it for a trainer.
Write one environment spec that serves both your evals and your RL training run — then publish it as a wheel.
Replace similarity-only RAG with a self-hosted knowledge graph your agents can remember across sessions.
The reference for running a provider-agnostic coding agent you configure, permission and extend yourself.
The OAuth and per-action authorization layer most agent frameworks leave you to write yourself.
Build production agents in idiomatic Kotlin or Java without bolting on a Python service.
Run the same benchmark against vLLM, SGLang or a hosted API and get comparable numbers.
Twenty-three runnable tutorials covering every production layer an agent demo skips.
Knowledge-graph RAG that indexes incrementally instead of rebuilding — the practical answer to GraphRAG's cost.
Stanford's quarter-long tour from word2vec to GRPO, with a free 250-page illustrated textbook and a printable cheatsheet.
Self-host one OpenAI-compatible server that fronts 50+ inference, vector-store and tool providers — swap models without touching app code.
The official MCP extension that lets your tools return a sandboxed interactive UI instead of a wall of text.
The open model currently topping olmOCR-Bench — turns messy PDFs, forms and handwriting into layout-preserving Markdown, HTML or JSON.
Two inference engines under one CLI — a C++/CUDA one for throughput and a pure-Python one you can actually read and patch.