Discover
Find something worth learning.
Agent Harnesses: Anatomy, Build, Frameworks, Benchmarks
Take apart Claude Code, Codex CLI, OpenCode, Pi and DeepSeek Harness on one 10-point rubric, build your own coding-agent harness in Python on OpenRouter, rebuild it on LangGraph, the OpenAI and Claude Agent SDKs and more, read the leading benchmarks critically, and ship it on a Terminal-Bench 4.0 slice through Harbor. 32 lessons, BYOK.
Explore course
Claude Artifacts Essentials
A beginner, no-code course on Claude artifacts as they work in 2026. Make docs, decks, designs and simple pages with Claude on the web or desktop, edit and version them, pick the right form for each job, and share them safely. You build a three-piece Launch Kit for a fictional tea shop. Course 1 of the Claude Artifacts series.
Build Interactive Tools with Claude Artifacts
Trackers, calculators and dashboards you describe in plain English and share with your team. Write a four-part brief, learn what an artifact page can and can't do, get a polished phone-friendly design, share with the right roles, and update a tool safely. You ship the Autumn Ember Launch Tracker for a fictional tea shop. No code; about 4 hours.
Explore the library
More filters
AI Agents for Beginners
Microsoft's open-source AI Agents for Beginners curriculum (MIT), ported for LearnOS: 6 modules and 20 lessons on agent design patterns, tool use, agentic RAG, trustworthy agents, planning, multi-agent systems, metacognition, protocols (MCP, A2A), context engineering, memory, and production deployment and security. Searchable and citable inside Claude Code, Cursor, or Codex.
MCP for Beginners
Microsoft's open-source MCP for Beginners curriculum (MIT), ported for LearnOS: 13 modules and 67 lessons covering core concepts, security, building servers and clients, advanced topics, best practices, case studies, and a 14-part PostgreSQL hands-on lab. Read it inside Claude Code, Cursor, or Codex via the LearnOS MCP server; every section is searchable and citable.
Jev by TypeSafe AI: System One Models & Open-Source Alternatives
Learn Jev, TypeSafe AI's System One model, plus its open-source alternatives Laya and Von. This hands-on course covers the /v1/systemone API, the Choice, Score and Noul questions, confidence routing, TypeSafe's cookbooks, calibration (ECE), and CEO Diogo Almeida's "Prod, not God" thesis. You finish by building a triage pipeline that runs on either the hosted or a self-hosted backend.
Claude Code at Work
This is an intro on how to use Claude Code at work
State of Frontier LLMs
A living catalog of frontier LLM releases: learn to read any model launch like an analyst (benchmarks, pricing, context, open vs closed), then track each lab's models with a standardized stat block, timelines, and runnable code for open models.
MBA for Vibe Coders
A focused MBA for builders shipping with AI coding tools and tiny teams. Nine modules — business models, accounting, finance, marketing, product, operations, people, law — close with a capstone that ships a venture memo, financial model, GTM plan, and pitch. 45 lessons with runnable code and 8 live case labs (Figma, Cursor, Lovable, OpenAI, Duolingo, Vercel v0, Anthropic, GitHub Copilot).
AI Engineering
This is a comprehensive course regarding AI Engineering with current references, best practices, and hands-on activities.
Intro to CS
An intro course to computer science
RAG
A comprehensive course intro in RAG (Retrieval Augmented Generation).
OSSU — Computer Science
A complete, self-taught computer science curriculum using open courses from top universities. Structured modules from intro programming through advanced systems.
Web Development for Beginners
A 12-week introduction to web development with JavaScript, HTML, and CSS. Project-based lessons from Microsoft's open curriculum.