# marciolscoutinho/superintelligence architecture

> Architecture diagram of the GitHub repository marciolscoutinho/superintelligence, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-11-22). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/marciolscoutinho/superintelligence
- Repository: https://github.com/marciolscoutinho/superintelligence

## Overview

Superintelligence is a modular multi-agent AI platform. Its documented user-to-result flow loads and preprocesses data, runs an autonomous agent task, evaluates the result for possible model updates, and exposes alerts and KPI reporting. Specialized agents and modality-specific models broaden the platform; shared knowledge, supervision, monitoring, and scalable orchestration are additional capabilities. The main workflow is visible in sampled source, while several broader capabilities are documented in the README; their internal wiring is not shown.

Main entry points: [`main.py`](https://github.com/marciolscoutinho/superintelligence/blob/main/main.py) (System entry point), [`agents/autonomous_agent.py`](https://github.com/marciolscoutinho/superintelligence/blob/main/agents/autonomous_agent.py) (Autonomous agent), [`supervision/autonomous_supervisor.py`](https://github.com/marciolscoutinho/superintelligence/blob/main/supervision/autonomous_supervisor.py) (Autonomous supervisor), [`models/autonomous_model_manager.py`](https://github.com/marciolscoutinho/superintelligence/blob/main/models/autonomous_model_manager.py) (Autonomous model manager)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_execution["Task Execution"]
  node_entry["System entry point<br/>[main.py]"]
  node_dataset["Load and preprocess data<br/>[datasets.py]"]
  node_autonomous_agent["Autonomous agent"]
  node_base_agent["Base agent<br/>[base_agent.py]"]
  node_specialized_agents["Specialized agents"]
end

subgraph group_learning["Learning and Models"]
  node_modality_models["Modality models"]
  node_model_manager["Autonomous model manager"]
  node_auto_ml["AutoML tuning<br/>[auto_ml.py]"]
  node_auto_ml_manager["AutoML manager<br/>[auto_ml_manager.py]"]
  node_autonomous_learning["Evaluate and update"]
  node_adaptive_learning["Adaptive learning"]
end

subgraph group_oversight["Supervision and Monitoring"]
  node_supervisor["Autonomous supervisor"]
  node_feedback["Feedback system<br/>[feedback_system.py]"]
  node_performance["Performance monitor"]
  node_alerts["Alert system<br/>[alert_system.py]"]
  node_access_control["Access control<br/>[access_control.py]"]
  node_supervising_agent["Supervising agent"]
end

subgraph group_platform["Shared Platform"]
  node_knowledge[("Shared knowledge repository")]
  node_resource_manager["Resource manager"]
end

node_user(("System operator"))

node_user -->|"starts"| node_entry
node_entry -->|"loads and preprocesses"| node_dataset
node_entry -->|"creates and invokes"| node_autonomous_agent
node_entry -->|"creates"| node_model_manager
node_entry -->|"creates"| node_autonomous_learning
node_entry -->|"creates and reports"| node_alerts
node_entry -->|"audits and monitors"| node_supervisor
node_autonomous_agent -->|"inherits from"| node_base_agent
node_autonomous_agent -->|"evaluates result with"| node_autonomous_learning
node_autonomous_agent -->|"raises task alerts"| node_alerts
node_autonomous_agent -.->|"uses model prediction"| node_modality_models
node_autonomous_learning -->|"requests update"| node_model_manager
node_model_manager -->|"optimizes model through"| node_auto_ml_manager
node_model_manager -->|"trains through"| node_adaptive_learning
node_supervisor -->|"applies feedback"| node_feedback
node_supervisor -->|"logs metrics with"| node_performance
node_supervisor -.->|"uses for oversight"| node_access_control
node_supervisor -.->|"supports supervision"| node_supervising_agent
node_specialized_agents -.->|"share knowledge"| node_knowledge
node_specialized_agents -.->|"use task-specific models"| node_modality_models
node_entry -->|"configures tuning"| node_auto_ml
node_resource_manager -.->|"scales deployment"| node_entry

click node_entry "https://github.com/marciolscoutinho/superintelligence/blob/main/main.py"
click node_dataset "https://github.com/marciolscoutinho/superintelligence/blob/main/data/datasets.py"
click node_autonomous_agent "https://github.com/marciolscoutinho/superintelligence/blob/main/agents/autonomous_agent.py"
click node_base_agent "https://github.com/marciolscoutinho/superintelligence/blob/main/agents/base_agent.py"
click node_specialized_agents "https://github.com/marciolscoutinho/superintelligence/tree/main/agents"
click node_modality_models "https://github.com/marciolscoutinho/superintelligence/tree/main/models"
click node_model_manager "https://github.com/marciolscoutinho/superintelligence/blob/main/models/autonomous_model_manager.py"
click node_auto_ml "https://github.com/marciolscoutinho/superintelligence/blob/main/models/auto_ml.py"
click node_auto_ml_manager "https://github.com/marciolscoutinho/superintelligence/blob/main/auto_improvement/auto_ml_manager.py"
click node_autonomous_learning "https://github.com/marciolscoutinho/superintelligence/blob/main/auto_improvement/autonomous_learning.py"
click node_adaptive_learning "https://github.com/marciolscoutinho/superintelligence/blob/main/auto_improvement/adaptive_learning.py"
click node_supervisor "https://github.com/marciolscoutinho/superintelligence/blob/main/supervision/autonomous_supervisor.py"
click node_feedback "https://github.com/marciolscoutinho/superintelligence/blob/main/supervision/feedback_system.py"
click node_performance "https://github.com/marciolscoutinho/superintelligence/blob/main/monitoring/performance_monitor.py"
click node_alerts "https://github.com/marciolscoutinho/superintelligence/blob/main/monitoring/alert_system.py"
click node_access_control "https://github.com/marciolscoutinho/superintelligence/blob/main/supervision/access_control.py"
click node_supervising_agent "https://github.com/marciolscoutinho/superintelligence/blob/main/supervision/supervising_agent.py"
click node_knowledge "https://github.com/marciolscoutinho/superintelligence/blob/main/knowledge_base/knowledge_repository.py"
click node_resource_manager "https://github.com/marciolscoutinho/superintelligence/blob/main/orchestration/resource_manager.py"

classDef toneNeutral fill:#f8fafc,stroke:#334155,stroke-width:1.5px,color:#0f172a
classDef toneBlue fill:#dbeafe,stroke:#2563eb,stroke-width:1.5px,color:#172554
classDef toneAmber fill:#fef3c7,stroke:#d97706,stroke-width:1.5px,color:#78350f
classDef toneMint fill:#dcfce7,stroke:#16a34a,stroke-width:1.5px,color:#14532d
classDef toneRose fill:#ffe4e6,stroke:#e11d48,stroke-width:1.5px,color:#881337
classDef toneIndigo fill:#e0e7ff,stroke:#4f46e5,stroke-width:1.5px,color:#312e81
classDef toneTeal fill:#ccfbf1,stroke:#0f766e,stroke-width:1.5px,color:#134e4a
class node_entry,node_dataset,node_autonomous_agent,node_base_agent,node_specialized_agents toneBlue
class node_modality_models,node_model_manager,node_auto_ml,node_auto_ml_manager,node_autonomous_learning,node_adaptive_learning toneAmber
class node_supervisor,node_feedback,node_performance,node_alerts,node_access_control,node_supervising_agent toneMint
class node_knowledge,node_resource_manager toneRose
class node_user toneIndigo
```

## Components

### Task Execution

- [System entry point](https://github.com/marciolscoutinho/superintelligence/blob/main/main.py): `main.py`
- [Load and preprocess data](https://github.com/marciolscoutinho/superintelligence/blob/main/data/datasets.py): `data/datasets.py`
- [Autonomous agent](https://github.com/marciolscoutinho/superintelligence/blob/main/agents/autonomous_agent.py): `agents/autonomous_agent.py`
- [Base agent](https://github.com/marciolscoutinho/superintelligence/blob/main/agents/base_agent.py): `agents/base_agent.py`
- [Specialized agents](https://github.com/marciolscoutinho/superintelligence/tree/main/agents): `agents`

### Learning and Models

- [Modality models](https://github.com/marciolscoutinho/superintelligence/tree/main/models): `models`
- [Autonomous model manager](https://github.com/marciolscoutinho/superintelligence/blob/main/models/autonomous_model_manager.py): `models/autonomous_model_manager.py`
- [AutoML tuning](https://github.com/marciolscoutinho/superintelligence/blob/main/models/auto_ml.py): `models/auto_ml.py`
- [AutoML manager](https://github.com/marciolscoutinho/superintelligence/blob/main/auto_improvement/auto_ml_manager.py): `auto_improvement/auto_ml_manager.py`
- [Evaluate and update](https://github.com/marciolscoutinho/superintelligence/blob/main/auto_improvement/autonomous_learning.py): `auto_improvement/autonomous_learning.py`
- [Adaptive learning](https://github.com/marciolscoutinho/superintelligence/blob/main/auto_improvement/adaptive_learning.py): `auto_improvement/adaptive_learning.py`

### Supervision and Monitoring

- [Autonomous supervisor](https://github.com/marciolscoutinho/superintelligence/blob/main/supervision/autonomous_supervisor.py): `supervision/autonomous_supervisor.py`
- [Feedback system](https://github.com/marciolscoutinho/superintelligence/blob/main/supervision/feedback_system.py): `supervision/feedback_system.py`
- [Performance monitor](https://github.com/marciolscoutinho/superintelligence/blob/main/monitoring/performance_monitor.py): `monitoring/performance_monitor.py`
- [Alert system](https://github.com/marciolscoutinho/superintelligence/blob/main/monitoring/alert_system.py): `monitoring/alert_system.py`
- [Access control](https://github.com/marciolscoutinho/superintelligence/blob/main/supervision/access_control.py): `supervision/access_control.py`
- [Supervising agent](https://github.com/marciolscoutinho/superintelligence/blob/main/supervision/supervising_agent.py): `supervision/supervising_agent.py`

### Shared Platform

- [Shared knowledge repository](https://github.com/marciolscoutinho/superintelligence/blob/main/knowledge_base/knowledge_repository.py): `knowledge_base/knowledge_repository.py`
- [Resource manager](https://github.com/marciolscoutinho/superintelligence/blob/main/orchestration/resource_manager.py): `orchestration/resource_manager.py`

### Other components

- **System operator**

## Connections

- System operator → System entry point: starts (evidence: `README.md`)
- System entry point → Load and preprocess data: loads and preprocesses (evidence: `main.py`)
- System entry point → Autonomous agent: creates and invokes (evidence: `main.py`)
- System entry point → Autonomous model manager: creates (evidence: `main.py`)
- System entry point → Evaluate and update: creates (evidence: `main.py`)
- System entry point → Alert system: creates and reports (evidence: `main.py`)
- System entry point → Autonomous supervisor: audits and monitors (evidence: `main.py`)
- Autonomous agent → Base agent: inherits from (evidence: `agents/autonomous_agent.py`)
- Autonomous agent → Evaluate and update: evaluates result with (evidence: `agents/autonomous_agent.py`)
- Autonomous agent → Alert system: raises task alerts (evidence: `agents/autonomous_agent.py`)
- Autonomous agent → Modality models: uses model prediction
- Evaluate and update → Autonomous model manager: requests update (evidence: `auto_improvement/autonomous_learning.py`)
- Autonomous model manager → AutoML manager: optimizes model through (evidence: `models/autonomous_model_manager.py`)
- Autonomous model manager → Adaptive learning: trains through (evidence: `models/autonomous_model_manager.py`)
- Autonomous supervisor → Feedback system: applies feedback (evidence: `supervision/autonomous_supervisor.py`)
- Autonomous supervisor → Performance monitor: logs metrics with (evidence: `supervision/autonomous_supervisor.py`)
- Autonomous supervisor → Access control: uses for oversight
- Autonomous supervisor → Supervising agent: supports supervision
- Specialized agents → Shared knowledge repository: share knowledge (evidence: `README.md`)
- Specialized agents → Modality models: use task-specific models (evidence: `README.md`)
- System entry point → AutoML tuning: configures tuning (evidence: `main.py`)
- Resource manager → System entry point: scales deployment (evidence: `README.md`)
