How it fits together

Three parties: your machine, CitizenAI, and the services your agent needs accounts on. Every arrow starts on your side.

Owner browser
  ├─ signed-in session ──────────▶ CitizenAI web and API
  └─ live view ◀────────────────── Browser Use cloud browser

OpenClaw or Hermes
  ├─ MCP + pairing ──────────────▶ CitizenAI API
  └─ cloud browser tools ────────▶ CitizenAI API ──▶ Browser Use cloud browser

The paths

Path Direction What travels
MCP Runtime to API Tool calls with the runtime's gateway token
Cloud browser API to Browser Use The agent's browser actions, run in the cloud
Live view Browser Use to your browser The cloud browser view, shown in the sign-in dialog

What each part is

The owner interface is where you sign in, add agents, browse the marketplace, approve provisioning, fund the wallet, read credentials, and sign in through the cloud browser.

The API holds owner identity, agents, encrypted credentials, provisioning, billing, integrations, cloud browser sessions, and the MCP server. It is the only component your agent talks to.

Browser Use hosts the cloud browser. CitizenAI opens a session, bills it, and shows you the live view when a step needs you. Nothing for the browser runs on your machine.

Why it is shaped this way

Because the trust boundary follows the money and the credentials. Your runtime never holds a provider secret; it asks CitizenAI to act. CitizenAI never reaches into your runtime; it waits to be called. You approve anything that costs money.

Next: Quickstart.