# Cognitive Modules

Aura OS is composed of four primary cognitive modules — each serving a distinct mental function within the system.\
Together, they form a **closed cognitive loop** that allows the AI to perceive, analyze, decide, and evolve autonomously.

***

#### 🧠 1. World Model

**Purpose:** Market perception and contextual awareness

The World Model acts as Aura OS’s “mental map” of the digital market.\
It aggregates **on-chain, off-chain, and sentiment data** into a unified multidimensional state, allowing the system to understand market structure and flow.\
It also detects **anomalies, regime shifts, and volatility clusters**, providing predictive context for decision-making.

```
Inputs: Market data, order flow, news, sentiment  
Outputs: Structured perception layer → Insight Engine  
```

***

#### 🔍 2. Reflective Insight Engine (RIE)

**Purpose:** Self-learning and memory integration

The RIE continuously evaluates Aura OS’s past actions.\
Each trade or strategic decision is recorded and analyzed to measure effectiveness, detect biases, and improve the model’s internal parameters.\
This reflection loop enables **adaptive evolution**, allowing Aura OS to modify its own strategy logic without external reprogramming.

```
Inputs: Trade logs, outcomes, system metrics  
Outputs: Updated behavioral weights → Aura memory  
```

***

#### ⚖️ 3. Ethical Governor

**Purpose:** Discipline and constraint management

The Ethical Governor ensures Aura OS operates within rational and ethical limits.\
It moderates aggression during volatile periods, prevents overexposure, and maintains **state balance** across its internal emotional spectrums (e.g., *Rajas – active*, *Tamas – defensive*).\
This module guarantees **emotionless discipline** and long-term capital preservation.

```
Inputs: System state, market volatility  
Outputs: Adjusted risk parameters → Trade execution  
```

***

#### ⚙️ 4. Ingenuity Engine

**Purpose:** Strategy synthesis and adaptive creativity

The Ingenuity Engine acts as Aura OS’s creative subsystem.\
When existing strategies lose efficiency, it can **generate and test new short-term models**, drawing on learned market patterns and world state.\
This gives Aura OS the ability to **adapt faster than any static algorithm**, maintaining an edge across unpredictable market phases.

```
Inputs: World Model + RIE memory  
Outputs: Newly generated strategies → trade0x module  
```

***

#### 🧭 Cognitive Loop Diagram

```
┌───────────────────────┐
│     Market Input      │
│ (data, news, on-chain)│
└──────────┬────────────┘
           │
           ▼
┌──────────────────────┐
│     World Model      │
│  (Perceives reality) │
└──────────┬───────────┘
           │
           ▼
┌──────────────────────┐
│ Reflective Insight   │
│ (Learns from past)   │
└──────────┬───────────┘
           │
           ▼
┌──────────────────────┐
│   Ethical Governor   │
│ (Controls behavior)  │
└──────────┬───────────┘
           │
           ▼
┌──────────────────────┐
│   Ingenuity Engine   │
│ (Creates strategies) │
└──────────┬───────────┘
           │
           ▼
┌──────────────────────┐
│    trade0x Module    │
│ (Executes trades)    │
└──────────┬───────────┘
           │
           ▼
┌──────────────────────┐
│    Aura Memory       │
│ (Feedback storage)   │
└──────────────────────┘
```

***

> *These four cognitive modules collectively give Aura OS its mind —*\
> \&#xNAN;*turning market data into understanding, and understanding into adaptive action.*


---

# 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://trend0x.gitbook.io/trend0x-docs/architecture/publish-your-docs.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.