# suresh93-pro/maya-ai-v100 architecture

> Architecture diagram of the GitHub repository suresh93-pro/maya-ai-v100, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-10-04). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/suresh93-pro/maya-ai-v100
- Repository: https://github.com/suresh93-pro/maya-ai-v100

## Overview

MAYA is a Windows desktop voice assistant. Its main workflow is voice or text input through the Tkinter app, command interpretation, then speech feedback or Windows/web actions; optional Ollama answers are used for otherwise-unhandled requests. The README also describes an animated HUD and telemetry, represented alongside the command workflow. The excerpts show the main wiring and core runtime behavior; feature coverage beyond those excerpts is based on README statements, so undocumented internal links are omitted.

Main entry points: [`main.py`](https://github.com/suresh93-pro/maya-ai-v100/blob/main/main.py) (MAYA App and HUD), [`core/commands.py`](https://github.com/suresh93-pro/maya-ai-v100/blob/main/core/commands.py) (Command Engine), [`core/listener.py`](https://github.com/suresh93-pro/maya-ai-v100/blob/main/core/listener.py) (Voice Listener), [`core/launcher.py`](https://github.com/suresh93-pro/maya-ai-v100/blob/main/core/launcher.py) (Windows Launcher)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_interface["Desktop Interface"]
  node_maya_app["MAYA App and HUD<br/>[main.py]"]
  node_telemetry["System Telemetry<br/>[main.py]"]
  node_config["Configuration<br/>[config.py]"]
end

subgraph group_interaction["Voice Interaction"]
  node_listener["Voice Listener<br/>[listener.py]"]
  node_speaker["Voice Speaker<br/>[speaker.py]"]
end

subgraph group_commands["Command Handling"]
  node_engine["Command Engine<br/>[commands.py]"]
  node_launcher["Windows Launcher<br/>[launcher.py]"]
  node_desktop_controls["Desktop Controls<br/>[commands.py]"]
end

subgraph group_integrations["System Integrations"]
  node_brain["Local AI Brain<br/>[brain.py]"]
end

node_user(("User"))
node_microphone(("Microphone"))
node_speech_service["Google Speech Recognition"]
node_windows["Windows System"]
node_web["Web Browser"]
node_ollama["Ollama Service"]

node_user -->|"enters text"| node_maya_app
node_maya_app -->|"loads settings"| node_config
node_maya_app -->|"starts listening"| node_listener
node_listener -->|"captures audio"| node_microphone
node_listener -->|"recognizes speech"| node_speech_service
node_maya_app -->|"submits commands"| node_engine
node_listener -->|"returns transcript"| node_maya_app
node_maya_app -->|"speaks startup"| node_speaker
node_engine -->|"speaks replies"| node_speaker
node_engine -->|"routes app and web requests"| node_launcher
node_engine -->|"executes controls"| node_desktop_controls
node_desktop_controls -->|"sends shortcuts"| node_windows
node_launcher -->|"opens and closes apps"| node_windows
node_launcher -->|"opens URLs"| node_web
node_engine -->|"asks fallback question"| node_brain
node_brain -->|"requests generation"| node_ollama
node_maya_app -->|"updates status"| node_telemetry
node_maya_app -->|"passes configuration"| node_engine
node_maya_app -->|"passes configuration"| node_launcher
node_maya_app -->|"passes configuration"| node_brain

click node_maya_app "https://github.com/suresh93-pro/maya-ai-v100/blob/main/main.py"
click node_telemetry "https://github.com/suresh93-pro/maya-ai-v100/blob/main/main.py"
click node_config "https://github.com/suresh93-pro/maya-ai-v100/blob/main/core/config.py"
click node_listener "https://github.com/suresh93-pro/maya-ai-v100/blob/main/core/listener.py"
click node_speaker "https://github.com/suresh93-pro/maya-ai-v100/blob/main/core/speaker.py"
click node_engine "https://github.com/suresh93-pro/maya-ai-v100/blob/main/core/commands.py"
click node_launcher "https://github.com/suresh93-pro/maya-ai-v100/blob/main/core/launcher.py"
click node_desktop_controls "https://github.com/suresh93-pro/maya-ai-v100/blob/main/core/commands.py"
click node_brain "https://github.com/suresh93-pro/maya-ai-v100/blob/main/core/brain.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_maya_app,node_telemetry,node_config,node_user,node_web toneBlue
class node_listener,node_speaker toneAmber
class node_engine,node_launcher,node_desktop_controls toneMint
class node_brain toneRose
class node_microphone,node_speech_service,node_windows,node_ollama toneIndigo
```

## Components

### Desktop Interface

- [MAYA App and HUD](https://github.com/suresh93-pro/maya-ai-v100/blob/main/main.py): `main.py`
- [System Telemetry](https://github.com/suresh93-pro/maya-ai-v100/blob/main/main.py): `main.py`
- [Configuration](https://github.com/suresh93-pro/maya-ai-v100/blob/main/core/config.py): `core/config.py`

### Voice Interaction

- [Voice Listener](https://github.com/suresh93-pro/maya-ai-v100/blob/main/core/listener.py): `core/listener.py`
- [Voice Speaker](https://github.com/suresh93-pro/maya-ai-v100/blob/main/core/speaker.py): `core/speaker.py`

### Command Handling

- [Command Engine](https://github.com/suresh93-pro/maya-ai-v100/blob/main/core/commands.py): `core/commands.py`
- [Windows Launcher](https://github.com/suresh93-pro/maya-ai-v100/blob/main/core/launcher.py): `core/launcher.py`
- [Desktop Controls](https://github.com/suresh93-pro/maya-ai-v100/blob/main/core/commands.py): `core/commands.py`

### System Integrations

- [Local AI Brain](https://github.com/suresh93-pro/maya-ai-v100/blob/main/core/brain.py): `core/brain.py`

### Other components

- **User**
- **Microphone**
- **Google Speech Recognition**
- **Windows System**
- **Web Browser**
- **Ollama Service**

## Connections

- User → MAYA App and HUD: enters text (evidence: `main.py`)
- MAYA App and HUD → Configuration: loads settings (evidence: `main.py`)
- MAYA App and HUD → Voice Listener: starts listening (evidence: `main.py`)
- Voice Listener → Microphone: captures audio (evidence: `core/listener.py`)
- Voice Listener → Google Speech Recognition: recognizes speech (evidence: `core/listener.py`)
- MAYA App and HUD → Command Engine: submits commands (evidence: `main.py`)
- Voice Listener → MAYA App and HUD: returns transcript (evidence: `main.py`)
- MAYA App and HUD → Voice Speaker: speaks startup (evidence: `main.py`)
- Command Engine → Voice Speaker: speaks replies (evidence: `core/commands.py`)
- Command Engine → Windows Launcher: routes app and web requests (evidence: `core/commands.py`)
- Command Engine → Desktop Controls: executes controls (evidence: `core/commands.py`)
- Desktop Controls → Windows System: sends shortcuts (evidence: `core/commands.py`)
- Windows Launcher → Windows System: opens and closes apps (evidence: `core/launcher.py`)
- Windows Launcher → Web Browser: opens URLs (evidence: `core/launcher.py`)
- Command Engine → Local AI Brain: asks fallback question (evidence: `core/commands.py`)
- Local AI Brain → Ollama Service: requests generation (evidence: `core/brain.py`)
- MAYA App and HUD → System Telemetry: updates status (evidence: `main.py`)
- MAYA App and HUD → Command Engine: passes configuration (evidence: `main.py`)
- MAYA App and HUD → Windows Launcher: passes configuration (evidence: `main.py`)
- MAYA App and HUD → Local AI Brain: passes configuration (evidence: `main.py`)
