Documentation

Welcome

Understand why The One exists for Multi-Agent architecture and where to start.

The One is a desktop application built for Multi-Agent architecture. It helps you build, run, observe, and iterate on your own multi-agent systems.

Core idea

Multi-Agent systems are the future of AI Agents, but most exploration today is still stuck at the stage of writing a few Agents by hand and hard-coding a few call chains. That workflow is slow, fragile, hard to reuse, and difficult to observe.

The One has a direct goal: let people build any Multi-Agent architecture they can imagine with one piece of software.

This turns Multi-Agent architecture from a hidden code path into a visible system design that can be discussed, modified, and improved.

The One is explicitly against black-box Agent execution. In The One, you can observe a Graph run from a system-level view: how Agents communicate, how they call tools, how state moves, and what context each Agent currently has.

That transparency is not decoration. It is infrastructure for Multi-Agent exploration. If you cannot see how Agents collaborate, you cannot improve the architecture systematically.

Start here

  • Quick Start: Install The One and run your first Multi-Agent Graph.
  • Models and Pricing: Understand official model service, third-party providers, subscriptions, and top-ups.
  • Single Agent: Understand one Agent before moving into Multi-Agent systems.
  • Definition Space: Learn how The One manages Prompts, Skills, MCP, Agents, and Graphs.
  • Release Notes: Read the latest public version notes.

More resources