# Introducing AIGITrading

**AIGITrading** is an AI-powered high-performance decentralized on-chain derivatives exchange. AIGI’s AI Agents analyze trends, detect volatility, and identify key trading opportunities before the market reacts. Users can create, modify, and monitor AI models tailored to their trading strategies, executing buy or sell orders.

### **underlying architecture**

**CLOB** — Shared Central Limit Order Book (unified across all chains)

**Matching Engine** — Low-latency order matching (CEX-level performance)

**Vault** — On-chain settlement with self-custody

**Risk Management** — Liquidation engine and position monitoring

**Settlement Networks**

EVM: Arbitrum, Optimism, Base, Ethereum, Polygon, Mantle

Non-EVM: Solala

### **Core AI components**

* ***Twitter Track Agent***\
  \&#xNAN;*Real-time sentiment analysis of tweets related to specific assets, delivering immediate alerts on social signals impacting the market.*
* ***Volume Detection Agent***\
  \&#xNAN;*Monitors abnormal trading volumes and analyzes historical patterns, providing instant alerts on major market shifts.*
* ***Wallet Track Agent***\
  \&#xNAN;*Tracks activity from significant wallets, identifying large trades. Create watchlists to follow notable buys, sells, and wallet movements.*
* ***Personalized Customization***\
  \&#xNAN;*Secure and efficient collaboration among AI agents to handle complex tasks in a seamless, coordinated manner.*

Here, you can experience AI-assisted execution for trades (buy, sell, take profit, and trailing profit), along with actionable insights into trading activity, asset performance, and market trends.


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://aigi-protocol.gitbook.io/aigi-protocol/overview/user-facing/aigitrading/editor.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.