Interactive system-design builds you can run in the browser, long-form handbooks, runnable labs and coding challenges, and visual roadmaps — no sign-up, no paywall, built in the open.
Vibe Engines is a free, open learning platform for AI engineering and system design. The core of it is interactive: system designs you assemble step by step in the browser, Python challenges that run against real tests without any setup, and labs where the concept is something you operate, not just read about.
Around that sit the reference layers — long-form handbooks on LLM systems, agents, and distributed systems; visual roadmaps for roles like platform engineer and Forward Deployed Engineer; cheatsheets and flashcards for the recall work. Everything is built by someone doing the work, for people doing the work.
There is no account, no paywall, and no email gate in front of any of it. Progress lives in your browser. If something here helps you build or land the job, that's the whole business model.
If you're wiring up an LLM product on weekends and need real patterns — evals that catch regressions, caching that actually saves money, agent loops that don't spiral — the handbooks and repos here are written for that pace.
Stitching a stack together as a team of one means every dependency has to pull its weight. The tooling here is small, legible, and built to be forked — not framework lock-in dressed up as a library.
For backend and full-stack engineers moving into agentic systems, LLM infrastructure, and Claude / MCP workflows. Deep on the mechanics, light on the hype, and always with working code attached.
Full-length field manuals on agentic AI, LLM systems, and engineering craft. Free to read. Written from the workshop floor.
Browse handbooks →125+ guided system designs — Netflix, WhatsApp, RAG pipelines, LLM gateways — assembled step by step in the browser, with predictions, chaos drills, and a quiz at the end.
Start a build →The most useful thing here is usually the next handbook. Start there.
Go to the handbook library →