# atharva-shinde7/jarvis-ai architecture

> Architecture diagram of the GitHub repository atharva-shinde7/jarvis-ai, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-10-02). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/atharva-shinde7/jarvis-ai
- Repository: https://github.com/atharva-shinde7/jarvis-ai

## Overview

Jarvis AI is a desktop, voice-controlled assistant. The user speaks a request; Main coordinates speech recognition, query classification, task routing, and presenting and speaking answers. Requests branch to general chat, real-time search, automation, or image generation, while screen and camera analysis provide separate vision capabilities. Chat history is shared local state. The README documents media control and other capabilities that are not all visible in the sampled source. Edges follow shown Main routing, source references, or README statements; unsampled internals are not inferred.

Main entry points: [`Main.py`](https://github.com/atharva-shinde7/jarvis-ai/blob/master/Main.py) (Assistant runtime), [`Data/ChatLog.json`](https://github.com/atharva-shinde7/jarvis-ai/blob/master/Data/ChatLog.json) (Chat history), [`Backend/screen_analysis.py`](https://github.com/atharva-shinde7/jarvis-ai/blob/master/Backend/screen_analysis.py) (Screen analysis), [`Backend/CameraAnalysis.py`](https://github.com/atharva-shinde7/jarvis-ai/blob/master/Backend/CameraAnalysis.py) (Camera analysis)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_interface["Desktop interface"]
  node_gui["Desktop GUI<br/>[GUI.py]"]
  node_speech["Speech recognition<br/>[SpeechToText.py]"]
end

subgraph group_orchestration["Request orchestration"]
  node_main["Assistant runtime<br/>[Main.py]"]
  node_classifier["Query classifier<br/>[Model.py]"]
end

subgraph group_assistant["Assistant capabilities"]
  node_automation["Automation and media<br/>[Automation.py]"]
  node_chatbot["General conversation<br/>[Chatbot.py]"]
  node_search["Real-time search"]
  node_imagegen["Image generation<br/>[ImageGeneration.py]"]
  node_screen["Screen analysis<br/>[screen_analysis.py]"]
  node_camera["Camera analysis<br/>[CameraAnalysis.py]"]
  node_tts["Speech output<br/>[TextToSpeech.py]"]
  node_visiontts["Vision speech output<br/>[TTS_B.py]"]
end

subgraph group_state["Conversation state"]
  node_chatlog[("Chat history<br/>[ChatLog.json]")]
end

node_user(("User"))

node_user -->|"gives requests"| node_main
node_main -->|"runs interface"| node_gui
node_main -->|"gets speech input"| node_speech
node_main -->|"classifies queries"| node_classifier
node_main -->|"dispatches tasks"| node_automation
node_main -->|"sends general queries"| node_chatbot
node_main -->|"sends live queries"| node_search
node_main -->|"starts generation"| node_imagegen
node_main -->|"routes analysis"| node_screen
node_main -->|"routes analysis"| node_camera
node_main -->|"speaks answers"| node_tts
node_chatbot -->|"reads and writes"| node_chatlog
node_search -->|"reads and writes"| node_chatlog
node_screen -->|"records analysis"| node_chatlog
node_camera -->|"records analysis"| node_chatlog
node_screen -->|"speaks analysis"| node_visiontts
node_camera -->|"speaks analysis"| node_visiontts

click node_main "https://github.com/atharva-shinde7/jarvis-ai/blob/master/Main.py"
click node_gui "https://github.com/atharva-shinde7/jarvis-ai/blob/master/Frontend/GUI.py"
click node_speech "https://github.com/atharva-shinde7/jarvis-ai/blob/master/Backend/SpeechToText.py"
click node_classifier "https://github.com/atharva-shinde7/jarvis-ai/blob/master/Backend/Model.py"
click node_automation "https://github.com/atharva-shinde7/jarvis-ai/blob/master/Backend/Automation.py"
click node_chatbot "https://github.com/atharva-shinde7/jarvis-ai/blob/master/Backend/Chatbot.py"
click node_search "https://github.com/atharva-shinde7/jarvis-ai/blob/master/Backend/RealtimeSearchEngine.py"
click node_imagegen "https://github.com/atharva-shinde7/jarvis-ai/blob/master/Backend/ImageGeneration.py"
click node_screen "https://github.com/atharva-shinde7/jarvis-ai/blob/master/Backend/screen_analysis.py"
click node_camera "https://github.com/atharva-shinde7/jarvis-ai/blob/master/Backend/CameraAnalysis.py"
click node_tts "https://github.com/atharva-shinde7/jarvis-ai/blob/master/Backend/TextToSpeech.py"
click node_visiontts "https://github.com/atharva-shinde7/jarvis-ai/blob/master/Backend/TTS_B.py"
click node_chatlog "https://github.com/atharva-shinde7/jarvis-ai/blob/master/Data/ChatLog.json"

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_gui,node_speech,node_user toneBlue
class node_main,node_classifier toneAmber
class node_automation,node_chatbot,node_search,node_imagegen,node_screen,node_camera,node_tts,node_visiontts toneMint
class node_chatlog toneRose
```

## Components

### Desktop interface

- [Desktop GUI](https://github.com/atharva-shinde7/jarvis-ai/blob/master/Frontend/GUI.py): `Frontend/GUI.py`
- [Speech recognition](https://github.com/atharva-shinde7/jarvis-ai/blob/master/Backend/SpeechToText.py): `Backend/SpeechToText.py`

### Request orchestration

- [Assistant runtime](https://github.com/atharva-shinde7/jarvis-ai/blob/master/Main.py): `Main.py`
- [Query classifier](https://github.com/atharva-shinde7/jarvis-ai/blob/master/Backend/Model.py): `Backend/Model.py`

### Assistant capabilities

- [Automation and media](https://github.com/atharva-shinde7/jarvis-ai/blob/master/Backend/Automation.py): `Backend/Automation.py`
- [General conversation](https://github.com/atharva-shinde7/jarvis-ai/blob/master/Backend/Chatbot.py): `Backend/Chatbot.py`
- [Real-time search](https://github.com/atharva-shinde7/jarvis-ai/blob/master/Backend/RealtimeSearchEngine.py): `Backend/RealtimeSearchEngine.py`
- [Image generation](https://github.com/atharva-shinde7/jarvis-ai/blob/master/Backend/ImageGeneration.py): `Backend/ImageGeneration.py`
- [Screen analysis](https://github.com/atharva-shinde7/jarvis-ai/blob/master/Backend/screen_analysis.py): `Backend/screen_analysis.py`
- [Camera analysis](https://github.com/atharva-shinde7/jarvis-ai/blob/master/Backend/CameraAnalysis.py): `Backend/CameraAnalysis.py`
- [Speech output](https://github.com/atharva-shinde7/jarvis-ai/blob/master/Backend/TextToSpeech.py): `Backend/TextToSpeech.py`
- [Vision speech output](https://github.com/atharva-shinde7/jarvis-ai/blob/master/Backend/TTS_B.py): `Backend/TTS_B.py`

### Conversation state

- [Chat history](https://github.com/atharva-shinde7/jarvis-ai/blob/master/Data/ChatLog.json): `Data/ChatLog.json`

### Other components

- **User**

## Connections

- User → Assistant runtime: gives requests (evidence: `README.md`)
- Assistant runtime → Desktop GUI: runs interface (evidence: `Main.py`)
- Assistant runtime → Speech recognition: gets speech input (evidence: `Main.py`)
- Assistant runtime → Query classifier: classifies queries (evidence: `Main.py`)
- Assistant runtime → Automation and media: dispatches tasks (evidence: `Main.py`)
- Assistant runtime → General conversation: sends general queries (evidence: `Main.py`)
- Assistant runtime → Real-time search: sends live queries (evidence: `Main.py`)
- Assistant runtime → Image generation: starts generation (evidence: `Main.py`)
- Assistant runtime → Screen analysis: routes analysis (evidence: `Main.py`)
- Assistant runtime → Camera analysis: routes analysis (evidence: `Main.py`)
- Assistant runtime → Speech output: speaks answers (evidence: `Main.py`)
- General conversation → Chat history: reads and writes (evidence: `Backend/Chatbot.py`)
- Real-time search → Chat history: reads and writes (evidence: `Backend/RealtimeSearchEngine.py`)
- Screen analysis → Chat history: records analysis (evidence: `Backend/screen_analysis.py`)
- Camera analysis → Chat history: records analysis (evidence: `Backend/CameraAnalysis.py`)
- Screen analysis → Vision speech output: speaks analysis (evidence: `Backend/screen_analysis.py`)
- Camera analysis → Vision speech output: speaks analysis (evidence: `Backend/CameraAnalysis.py`)
