# jayadev-n/desktop-ai-assistant architecture

> Architecture diagram of the GitHub repository jayadev-n/desktop-ai-assistant, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-10-03). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/jayadev-n/desktop-ai-assistant
- Repository: https://github.com/jayadev-n/desktop-ai-assistant

## Overview

Jarvis is a voice-operated desktop assistant. In the principal workflow, a user speaks a command; the main loop captures it, routes screen-analysis requests through screenshot capture, OCR and local Ollama, or routes desktop actions to automation, then speaks responses. A separate `alpha.py` script documents a broader voice assistant with web, system-app, media and system-control commands. No README is present; the graph reflects shown code and does not infer links for empty modules.

Main entry points: [`jarvis-ai-main/jarvis-ai-main/jarvis/main.py`](https://github.com/jayadev-n/desktop-ai-assistant/blob/main/jarvis-ai-main/jarvis-ai-main/jarvis/main.py) (Command router), [`jarvis-ai-main/jarvis-ai-main/jarvis ai/alpha.py`](https://github.com/jayadev-n/desktop-ai-assistant/blob/main/jarvis-ai-main/jarvis-ai-main/jarvis%20ai/alpha.py) (Alternate assistant), [`jarvis-ai-main/jarvis-ai-main/jarvis/ai_brain.py`](https://github.com/jayadev-n/desktop-ai-assistant/blob/main/jarvis-ai-main/jarvis-ai-main/jarvis/ai_brain.py) (Screen explanation), [`jarvis-ai-main/jarvis-ai-main/jarvis/automation.py`](https://github.com/jayadev-n/desktop-ai-assistant/blob/main/jarvis-ai-main/jarvis-ai-main/jarvis/automation.py) (Desktop automation)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_interaction["Voice interaction"]
  node_loop["Command router<br/>[main.py]"]
  node_voice["Speech I/O<br/>[voice.py]"]
end

subgraph group_analysis["Screen analysis"]
  node_screen["Capture and OCR<br/>[screen.py]"]
  node_ai["Screen explanation<br/>[ai_brain.py]"]
end

subgraph group_actions["Desktop actions"]
  node_automation["Desktop automation<br/>[automation.py]"]
end

subgraph group_alternate["Alternate assistant"]
  node_alpha["Alternate assistant<br/>[alpha.py]"]
end

node_user(("User"))
node_ollama["Ollama service"]
node_desktop["Desktop and apps"]
node_web["Web and Wikipedia"]
node_system["Windows system"]
node_email["SMTP server"]

node_user -->|"speaks commands"| node_loop
node_loop -->|"captures and speaks"| node_voice
node_loop -->|"requests screen text"| node_screen
node_loop -->|"sends extracted text"| node_ai
node_ai -->|"requests explanation"| node_ollama
node_loop -->|"dispatches actions"| node_automation
node_automation -->|"controls desktop"| node_desktop
node_alpha -->|"searches and opens"| node_web
node_alpha -->|"runs system commands"| node_system
node_alpha -->|"defines email sending"| node_email

click node_loop "https://github.com/jayadev-n/desktop-ai-assistant/blob/main/jarvis-ai-main/jarvis-ai-main/jarvis/main.py"
click node_voice "https://github.com/jayadev-n/desktop-ai-assistant/blob/main/jarvis-ai-main/jarvis-ai-main/jarvis/voice.py"
click node_screen "https://github.com/jayadev-n/desktop-ai-assistant/blob/main/jarvis-ai-main/jarvis-ai-main/jarvis/screen.py"
click node_ai "https://github.com/jayadev-n/desktop-ai-assistant/blob/main/jarvis-ai-main/jarvis-ai-main/jarvis/ai_brain.py"
click node_automation "https://github.com/jayadev-n/desktop-ai-assistant/blob/main/jarvis-ai-main/jarvis-ai-main/jarvis/automation.py"
click node_alpha "https://github.com/jayadev-n/desktop-ai-assistant/blob/main/jarvis-ai-main/jarvis-ai-main/jarvis%20ai/alpha.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_loop,node_voice,node_user toneBlue
class node_screen,node_ai toneAmber
class node_automation,node_email toneMint
class node_alpha toneRose
class node_ollama,node_desktop,node_web,node_system toneIndigo
```

## Components

### Voice interaction

- [Command router](https://github.com/jayadev-n/desktop-ai-assistant/blob/main/jarvis-ai-main/jarvis-ai-main/jarvis/main.py): `jarvis-ai-main/jarvis-ai-main/jarvis/main.py`
- [Speech I/O](https://github.com/jayadev-n/desktop-ai-assistant/blob/main/jarvis-ai-main/jarvis-ai-main/jarvis/voice.py): `jarvis-ai-main/jarvis-ai-main/jarvis/voice.py`

### Screen analysis

- [Capture and OCR](https://github.com/jayadev-n/desktop-ai-assistant/blob/main/jarvis-ai-main/jarvis-ai-main/jarvis/screen.py): `jarvis-ai-main/jarvis-ai-main/jarvis/screen.py`
- [Screen explanation](https://github.com/jayadev-n/desktop-ai-assistant/blob/main/jarvis-ai-main/jarvis-ai-main/jarvis/ai_brain.py): `jarvis-ai-main/jarvis-ai-main/jarvis/ai_brain.py`

### Desktop actions

- [Desktop automation](https://github.com/jayadev-n/desktop-ai-assistant/blob/main/jarvis-ai-main/jarvis-ai-main/jarvis/automation.py): `jarvis-ai-main/jarvis-ai-main/jarvis/automation.py`

### Alternate assistant

- [Alternate assistant](https://github.com/jayadev-n/desktop-ai-assistant/blob/main/jarvis-ai-main/jarvis-ai-main/jarvis%20ai/alpha.py): `jarvis-ai-main/jarvis-ai-main/jarvis ai/alpha.py`

### Other components

- **User**
- **Ollama service**
- **Desktop and apps**
- **Web and Wikipedia**
- **Windows system**
- **SMTP server**

## Connections

- User → Command router: speaks commands (evidence: `jarvis-ai-main/jarvis-ai-main/jarvis/main.py`)
- Command router → Speech I/O: captures and speaks (evidence: `jarvis-ai-main/jarvis-ai-main/jarvis/main.py`)
- Command router → Capture and OCR: requests screen text (evidence: `jarvis-ai-main/jarvis-ai-main/jarvis/main.py`)
- Command router → Screen explanation: sends extracted text (evidence: `jarvis-ai-main/jarvis-ai-main/jarvis/main.py`)
- Screen explanation → Ollama service: requests explanation (evidence: `jarvis-ai-main/jarvis-ai-main/jarvis/ai_brain.py`)
- Command router → Desktop automation: dispatches actions (evidence: `jarvis-ai-main/jarvis-ai-main/jarvis/main.py`)
- Desktop automation → Desktop and apps: controls desktop (evidence: `jarvis-ai-main/jarvis-ai-main/jarvis/automation.py`)
- Alternate assistant → Web and Wikipedia: searches and opens (evidence: `jarvis-ai-main/jarvis-ai-main/jarvis ai/alpha.py`)
- Alternate assistant → Windows system: runs system commands (evidence: `jarvis-ai-main/jarvis-ai-main/jarvis ai/alpha.py`)
- Alternate assistant → SMTP server: defines email sending (evidence: `jarvis-ai-main/jarvis-ai-main/jarvis ai/alpha.py`)
