Agent overview

Use XROH from agents, automations, and chat-like flows.

XROH abstracts all external liquidity sources behind internal route engines (X1/X2/X3).

Public docs never name third‑party providers or expose their endpoints.

XROH can be called from an agent runtime. The agent never bypasses scoring or safety checks.

What automations usually do

• request quotes with a strategy

• compare top routes

• ask for user approval

• execute with guardrails

• watch execution state and retries

Core building blocks

• Agent interface (OpenClaw runtime)

• AI agent API

• Tool contracts

• Safety gating

Keep humans in the loop for final execution. Do not let an agent sign transactions unreviewed.