Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.zhentan.me/llms.txt

Use this file to discover all available pages before exploring further.

Zhentan is built on three independently runnable components that work together: an instant deterministic scoring layer, an interactive AI agent layer, and a smart account execution layer.

Architecture

System overview, component breakdown, and data flow diagrams.

Risk Scoring

How transactions are scored 0–100 against behavioral patterns.

Agent

The OpenClaw skill pack — skills, lifecycle, and Telegram commands.

Contract Deployments

Safe, ERC-4337, and infrastructure contract addresses on BNB Chain.

​
Design Principles

  • No LLM on the hot path — inline risk scoring is deterministic and instant. The agent only steps in after a verdict is reached.
  • Safe multisig is the foundation — battle-tested infrastructure. Zhentan adds AI intelligence on top without replacing key management.
  • The agent owns communication and the 2nd key — no transaction executes without its signature, making it genuinely agentic.
  • Continuous learning — patterns are recorded after every confirmed transaction. The profile improves automatically.