Vibe Code Pipeline
Learn how AI agents work by watching them work.
What it does
Vibe Code Pipeline is an interactive encyclopedia for AI agents, prompts, and vibe coding pipelines. Watch how agents loop, learn the patterns behind them, and build your own with confidence. Explore the catalog of 1006 agents and 1032 prompt templates, all designed to help you understand and create AI agents effectively.
An interactive visual encyclopedia and laboratory for understanding how AI agents are built, how they use tools, and how multi-agent systems coordinate.
Vibe Code Pipeline is the interactive encyclopedia for AI agents, prompts, and vibe coding pipelines. Watch how agents loop, learn the patterns behind them, and build your own with confidence. Every agent entry includes a step-through simulation showing the real loop — input, planning, tool calls, memory, output. See it before you build it. From single-agent basics to multi-agent orchestration. Guides, a glossary of 100+ terms, architecture diagrams, and vibe coding pipelines — all in one place. A prompt library, engineering methods, and an agent builder that produces a working blueprint. No live model calls. Just the structure you need to ship. Turn an open-ended question into a sourced…from vibecodepipeline.com
Does the same job
all alternatives →
More work this month
the category →
The app store for voice native apps that lives in your notch
Work · 28d ago · voiceos.com
The New Calendly▲211Handle all of the work before, during, and after meetings
Work · 17d ago · calendly.com
Launched alongside, August 2026
the whole month →- TL
Life & fun · 10d ago · louisabraham.github.io
- SA
Hello HN! I found that picking out plausible but diverse skin tones for my digital art and game development projects was kind of difficult, and I got curious about if there was a way to define a color space that made it easy. I've built a color picker and procedural generation algorithm based on the space as well as a bunch of other fun js features and demos throughout the page that use the equations. If you find it interesting, I have lots of explanations of how I built it and what properties the space has. The methodology might be a bit shaky, but hopefully the result is as helpful for…
Life & fun · Aug 2026 · toneyalexander.github.io
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 16d ago · simedw.com