# yobo-dance/wisdom-cowork-agent architecture

> Architecture diagram of the GitHub repository yobo-dance/wisdom-cowork-agent, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-10-06). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/yobo-dance/wisdom-cowork-agent
- Repository: https://github.com/yobo-dance/wisdom-cowork-agent

## Overview

Wisdom Cowork Agent is an unfinished desktop-assistance project; the README describes helping with daily desktop tasks but does not specify a complete end-to-end workflow. The clearest implemented path is push-to-talk speech capture and transcription in `src/core/STT.py`. The repository also has speech output, a brain module, and tool modules for apps, browsing, files, and system control, but their implementations or connections were not shown. Dashed edges mark this unverified intended integration; the learning exercises are excluded.

Main entry points: [`src/core/brain.py`](https://github.com/yobo-dance/wisdom-cowork-agent/blob/main/src/core/brain.py) (Agent brain), [`src/core/STT.py`](https://github.com/yobo-dance/wisdom-cowork-agent/blob/main/src/core/STT.py) (Speech recognition), [`src/main.py`](https://github.com/yobo-dance/wisdom-cowork-agent/blob/main/src/main.py) (Application entry), [`src/core/TTS.py`](https://github.com/yobo-dance/wisdom-cowork-agent/blob/main/src/core/TTS.py) (Speech output)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_runtime["Agent runtime"]
  node_entry["Application entry<br/>[main.py]"]
  node_brain["Agent brain<br/>[brain.py]"]
end

subgraph group_voice["Voice I/O"]
  node_stt["Speech recognition<br/>[STT.py]"]
  node_tts["Speech output<br/>[TTS.py]"]
end

subgraph group_tools["Desktop tools"]
  node_appcontrol["App control<br/>[app_control.py]"]
  node_browser["Browser tools<br/>[browser.py]"]
  node_filemanager["File management<br/>[file_manager.py]"]
  node_systemcontrol["System control<br/>[system_control.py]"]
end

node_user(("Desktop user"))
node_microphone["Audio input"]
node_whisper["Whisper model"]

node_user -->|"holds hotkey"| node_stt
node_stt -->|"captures audio"| node_microphone
node_stt -->|"transcribes audio"| node_whisper
node_entry -.->|"intended dispatch"| node_brain
node_brain -.->|"intended speech input"| node_stt
node_brain -.->|"intended speech output"| node_tts
node_brain -.->|"intended tool use"| node_appcontrol
node_brain -.->|"intended tool use"| node_browser
node_brain -.->|"intended tool use"| node_filemanager
node_brain -.->|"intended tool use"| node_systemcontrol

click node_entry "https://github.com/yobo-dance/wisdom-cowork-agent/blob/main/src/main.py"
click node_brain "https://github.com/yobo-dance/wisdom-cowork-agent/blob/main/src/core/brain.py"
click node_stt "https://github.com/yobo-dance/wisdom-cowork-agent/blob/main/src/core/STT.py"
click node_tts "https://github.com/yobo-dance/wisdom-cowork-agent/blob/main/src/core/TTS.py"
click node_appcontrol "https://github.com/yobo-dance/wisdom-cowork-agent/blob/main/src/tools/app_control.py"
click node_browser "https://github.com/yobo-dance/wisdom-cowork-agent/blob/main/src/tools/browser.py"
click node_filemanager "https://github.com/yobo-dance/wisdom-cowork-agent/blob/main/src/tools/file_manager.py"
click node_systemcontrol "https://github.com/yobo-dance/wisdom-cowork-agent/blob/main/src/tools/system_control.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_brain,node_user toneBlue
class node_stt,node_tts toneAmber
class node_appcontrol,node_browser,node_filemanager,node_systemcontrol toneMint
class node_microphone,node_whisper toneIndigo
```

## Components

### Agent runtime

- [Application entry](https://github.com/yobo-dance/wisdom-cowork-agent/blob/main/src/main.py): `src/main.py`
- [Agent brain](https://github.com/yobo-dance/wisdom-cowork-agent/blob/main/src/core/brain.py): `src/core/brain.py`

### Voice I/O

- [Speech recognition](https://github.com/yobo-dance/wisdom-cowork-agent/blob/main/src/core/STT.py): `src/core/STT.py`
- [Speech output](https://github.com/yobo-dance/wisdom-cowork-agent/blob/main/src/core/TTS.py): `src/core/TTS.py`

### Desktop tools

- [App control](https://github.com/yobo-dance/wisdom-cowork-agent/blob/main/src/tools/app_control.py): `src/tools/app_control.py`
- [Browser tools](https://github.com/yobo-dance/wisdom-cowork-agent/blob/main/src/tools/browser.py): `src/tools/browser.py`
- [File management](https://github.com/yobo-dance/wisdom-cowork-agent/blob/main/src/tools/file_manager.py): `src/tools/file_manager.py`
- [System control](https://github.com/yobo-dance/wisdom-cowork-agent/blob/main/src/tools/system_control.py): `src/tools/system_control.py`

### Other components

- **Desktop user**
- **Audio input**
- **Whisper model**

## Connections

- Desktop user → Speech recognition: holds hotkey (evidence: `src/core/STT.py`)
- Speech recognition → Audio input: captures audio (evidence: `src/core/STT.py`)
- Speech recognition → Whisper model: transcribes audio (evidence: `src/core/STT.py`)
- Application entry → Agent brain: intended dispatch
- Agent brain → Speech recognition: intended speech input
- Agent brain → Speech output: intended speech output
- Agent brain → App control: intended tool use
- Agent brain → Browser tools: intended tool use
- Agent brain → File management: intended tool use
- Agent brain → System control: intended tool use
