AgenTopology

What is AgenTopology?

The declarative standard for multi-agent systems

What is AgenTopology?

AgenTopology is a declarative language for defining multi-agent systems. Write your agent team once in a single .at file — then deploy to any platform.

The Problem

Building one AI agent is easy. Building a team of agents that actually works together is brutal.

You want a marketing team? A dev pipeline? A support squad? You spend hours wiring up agent configs, MCP servers, hooks, and scripts. You get it working in Claude Code. Then you need the same team in Codex — and you start from scratch.

AgenTopology fixes all of this.

How It Works

topology code-review : [pipeline] {
  agent researcher  { model: sonnet  tools: [Read, Grep, WebSearch] }
  agent writer      { model: sonnet  tools: [Read, Write] }
  agent reviewer    { model: opus    tools: [Read, Grep] }

  flow {
    researcher -> writer -> reviewer
    reviewer -> writer  [when reviewer.verdict == revise, max 2]
  }
}

Write your topology. Validate it. Scaffold it to any platform in one command.

Key Features

  • One file, any platform — Write once, deploy to Claude Code, Codex, Cursor, Gemini CLI, Copilot, Kiro, and more
  • Visual + Validated — See your agent graph. Catch errors before deployment
  • Pattern library — Pipeline, supervisor, fan-out, debate, human-gate — all built-in
  • Interactive builder — The /at skill lets you design topologies conversationally

On this page