Initial commit: Desktop Waifu MVP foundation

- Project structure with modular architecture - State management system (emotion states, conversation history) - Transparent, draggable PyQt6 window - OpenGL rendering widget with placeholder cube - Discord bot framework (commands, event handlers) - Complete documentation (README, project plan, research findings) - Environment configuration template - Dependencies defined in requirements.txt MVP features working: - Transparent window appears at bottom-right - Window can be dragged around - Placeholder 3D cube renders and rotates - Emotion state changes on interaction - Event-driven state management Next steps: VRM model loading and rendering
2025-09-30 18:42:54 -04:00
commit a657979bfd
20 changed files with 1178 additions and 0 deletions
--- a/.env.example
+++ b/.env.example
@@ -0,0 +1,19 @@
+# Discord Bot Configuration
+DISCORD_BOT_TOKEN=your_bot_token_here
+
+# LLM Configuration
+LLM_API_URL=http://localhost:11434  # Ollama default
+LLM_MODEL_NAME=llama2
+
+# Waifu Configuration
+WAIFU_NAME=Waifu
+VRM_MODEL_PATH=./models/waifu.vrm
+
+# Audio Configuration
+TTS_VOICE_RATE=150
+TTS_VOICE_VOLUME=0.9
+
+# System Configuration
+ENABLE_VOICE_INPUT=true
+ENABLE_VOICE_OUTPUT=true
+ENABLE_SYSTEM_ACCESS=false  # Requires elevated permissions
--- a/.gitignore
+++ b/.gitignore
@@ -0,0 +1,54 @@
+# Python
+__pycache__/
+*.py[cod]
+*$py.class
+*.so
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+
+# Virtual Environment
+venv/
+env/
+ENV/
+.venv
+
+# IDE
+.vscode/
+.idea/
+.claude/
+*.swp
+*.swo
+*~
+
+# Environment
+.env
+
+# Models and Assets (optional - keep if you want to commit them)
+models/*.vrm
+assets/sounds/*.wav
+assets/sounds/*.mp3
+
+# Logs
+*.log
+
+# OS
+.DS_Store
+Thumbs.db
+
+# Build artifacts
+*.exe
+*.spec
--- a/CURRENT_STATUS.md
+++ b/CURRENT_STATUS.md
@@ -0,0 +1,174 @@
+# Current Development Status
+**Last Updated:** 2025-09-30
+
+## ✅ Completed
+
+### Project Setup
+- Project structure created with modular architecture
+- Dependencies defined in `requirements.txt`
+- Environment configuration (`.env.example`)
+- Documentation (`README.md`, `PROJECT_PLAN.md`, `RESEARCH_FINDINGS.md`)
+
+### Core Systems
+- **State Manager** (`src/core/state_manager.py`): Event-driven state synchronization
+  - Emotion states
+  - Conversation history
+  - Event listeners for state changes
+
+### UI Framework
+- **Waifu Window** (`src/ui/waifu_window.py`): Main transparent window
+  - Frameless, transparent, always-on-top
+  - Drag functionality with mouse events
+  - Window positioning (bottom-right by default)
+  - Integration with state manager
+
+- **VRM Widget** (`src/ui/vrm_widget.py`): OpenGL rendering widget
+  - Basic OpenGL setup with transparency support
+  - Placeholder rendering (rotating cube)
+  - Animation timer (60 FPS)
+  - Emotion state integration
+  - Ready for VRM model loading
+
+### Discord Integration (Stub)
+- **Bot Framework** (`src/discord_bot/bot.py`): Basic bot structure
+  - Command system (hello, status)
+  - Event handlers (on_ready, on_message)
+  - State manager integration
+  - Mention/DM detection
+
+## 🔄 Next Steps (In Priority Order)
+
+### 1. Test Basic Functionality
+```bash
+# Install dependencies
+pip install -r requirements.txt
+
+# Run the app (will show placeholder cube)
+python main.py
+```
+
+Expected result:
+- Transparent window appears at bottom-right
+- Rotating colored cube visible
+- Window can be dragged
+- Emotion changes when grabbed (check console)
+
+### 2. Add Your VRM Model
+- Place `.vrm` file in `models/` folder
+- Update `.env` with path: `VRM_MODEL_PATH=./models/your_model.vrm`
+
+### 3. Implement VRM Loading
+**File:** `src/ui/vrm_widget.py`
+
+Tasks:
+- [ ] Use `pygltflib` to parse VRM file
+- [ ] Extract mesh data (vertices, normals, UVs, indices)
+- [ ] Extract material data (textures, colors)
+- [ ] Extract blend shape data (facial expressions)
+- [ ] Load textures into OpenGL
+- [ ] Create VBO/VAO for mesh rendering
+
+**Reference:** `RESEARCH_FINDINGS.md` for VRM structure
+
+### 4. Implement MToon Shader
+**New files:** `src/rendering/shaders/`
+
+Tasks:
+- [ ] Create vertex shader (GLSL)
+- [ ] Create MToon fragment shader (GLSL)
+- [ ] Shader compilation and linking
+- [ ] Pass material parameters to shader
+- [ ] Render VRM mesh with shader
+
+**Reference:** https://github.com/Santarh/MToon
+
+### 5. Add Sound Effects
+**New file:** `src/audio/sound_manager.py`
+
+Tasks:
+- [ ] Initialize pygame mixer
+- [ ] Load sound files from `assets/sounds/`
+- [ ] Play squeak on grab/drag
+- [ ] Play click on double-click
+- [ ] Integrate with state manager events
+
+### 6. Create Chat Interface
+**New file:** `src/ui/chat_window.py`
+
+Tasks:
+- [ ] Create chat window (QDialog or QWidget)
+- [ ] Text input field
+- [ ] Message history display
+- [ ] Show/hide on double-click
+- [ ] Integration with LLM backend
+
+### 7. Integrate LLM
+**New file:** `src/llm/llm_backend.py`
+
+Tasks:
+- [ ] Abstract LLM interface
+- [ ] Ollama implementation
+- [ ] llama.cpp implementation
+- [ ] Message processing
+- [ ] Emotion detection from responses
+- [ ] Update state based on LLM output
+
+### 8. Complete Discord Bot
+**File:** `src/discord_bot/bot.py`
+
+Tasks:
+- [ ] Connect Discord bot to LLM backend
+- [ ] Implement proper message responses
+- [ ] Add more commands
+- [ ] Sync desktop emotion with Discord messages
+- [ ] Handle async communication with desktop app
+
+### 9. Package as .exe
+Tasks:
+- [ ] Test with PyInstaller
+- [ ] Create spec file
+- [ ] Bundle assets (models, sounds)
+- [ ] Test standalone .exe
+
+## 🐛 Known Issues
+None yet - basic structure is in place
+
+## 📝 Notes
+
+### VRM Model Requirements
+- Format: `.vrm` (based on glTF 2.0)
+- Should contain blend shapes for expressions
+- MToon material support needed
+
+### LLM Integration Options
+1. **Ollama** (easiest): `ollama pull llama2` then use API
+2. **llama.cpp**: Faster, more control
+3. **Custom**: Your own model server
+
+### Discord Bot Token
+- Get from: https://discord.com/developers/applications
+- Enable Message Content Intent
+- Add to `.env`: `DISCORD_BOT_TOKEN=your_token_here`
+
+## 🔗 Important Files to Review
+
+- `PROJECT_PLAN.md`: Overall project plan and architecture
+- `RESEARCH_FINDINGS.md`: Technical research on VRM rendering
+- `README.md`: Setup and usage instructions
+- `main.py`: Application entry point
+- `src/core/state_manager.py`: Central state system
+- `src/ui/vrm_widget.py`: Where VRM rendering happens
+
+## 🎯 Testing Checklist
+
+- [ ] Window appears and is transparent
+- [ ] Window can be dragged
+- [ ] Placeholder renders correctly
+- [ ] Console shows emotion changes
+- [ ] Install dependencies works
+- [ ] .env configuration works
+- [ ] (After VRM) Model loads without errors
+- [ ] (After VRM) Model renders correctly
+- [ ] (After sound) Sound plays on interaction
+- [ ] (After LLM) Chat works
+- [ ] (After Discord) Bot connects and responds
--- a/PROJECT_PLAN.md
+++ b/PROJECT_PLAN.md
@@ -0,0 +1,130 @@
+# Desktop Waifu Project
+
+## Overview
+Desktop companion application controlled by LLM that can interact both on desktop and Discord.
+
+## Tech Stack
+- **Language**: Python
+- **Character Model**: VRM format
+- **LLM**: Local (TBD which model)
+- **Distribution**: .exe packaging
+- **Platforms**: Desktop app + Discord bot
+
+## Core Features
+
+### Desktop Visuals
+- VRM model rendering in transparent window
+- Draggable character
+- Sound effects on interaction (squeaks, touch sounds)
+- Multiple poses/expressions controlled by LLM
+- Always on top unless asked to hide
+- VRM animations (TBD - see notes below)
+
+### AI & Interaction
+- Local LLM (custom/TBD)
+- Memory/context persistence
+- AI-chosen personality
+- Always-on chat interface
+- Voice input (STT)
+- Voice output (TTS - local)
+
+### Discord Integration
+- Respond in servers/channels and DMs
+- Proactive messaging
+- Desktop-Discord state sync
+
+### System Integration
+- System access (notifications, apps, searches, etc.)
+- Designed for cross-platform deployment
+- Future: OS-level integration
+
+## VRM Animation Notes
+VRM models support:
+- **Blend shapes** (facial expressions): smile, blink, surprised, angry, sad, etc.
+- **Bone animations**: waving, pointing, head tilts, body movements
+- **Presets**: if your VRM has animation clips embedded
+- **IK (Inverse Kinematics)**: dynamic movements like looking at cursor
+
+We can trigger these based on:
+- LLM emotional state (happy → smile + wave)
+- User interaction (grabbed → surprised expression + squeak)
+- Idle states (occasional blinks, breathing animation)
+- Context (thinking → hand on chin pose)
+
+## MVP (Phase 1)
+1. VRM model renders on screen
+2. Transparent, draggable window
+3. Basic sound on interaction
+4. Simple chat interface (text only)
+5. Basic LLM connection (local)
+6. Simple expression changes (happy/neutral/sad)
+7. **Discord bot integration** (respond in servers/DMs, basic sync with desktop)
+
+## Post-MVP Features
+- Voice I/O (STT/TTS)
+- Advanced animations
+- Full system integration (notifications, app control, etc.)
+- Memory persistence (database)
+- Proactive messaging
+- .exe packaging
+- Cross-platform support
+
+## Architecture
+
+### Components
+1. **VRM Renderer** (PyOpenGL + VRM loader)
+2. **LLM Backend** (local inference)
+3. **Audio System** (TTS, STT, sound effects)
+4. **Discord Client** (discord.py)
+5. **State Manager** (sync between desktop/Discord)
+6. **System Interface** (OS interactions)
+7. **GUI Framework** (PyQt/tkinter with transparency)
+
+### Data Flow
+```
+User Input (voice/text/click)
+    ↓
+State Manager
+    ↓
+LLM Processing
+    ↓
+Output (animation + voice + text + actions)
+    ↓
+Desktop Display + Discord Bot
+```
+
+## Tech Stack Candidates
+
+### VRM Rendering
+- PyVRM (if available)
+- PyOpenGL + custom VRM parser
+- Unity Python wrapper (heavy)
+- Godot Python binding (alternative)
+
+### LLM
+- llama.cpp Python bindings
+- Ollama API
+- Custom model server
+- Transformers library
+
+### Voice
+- **TTS**: pyttsx3, Coqui TTS, XTTS
+- **STT**: Whisper (local), Vosk
+
+### Discord
+- discord.py
+
+### Packaging
+- PyInstaller
+- Nuitka (better performance)
+
+## Current Status
+- Phase: Planning
+- Last Updated: 2025-09-30
+
+## Next Steps
+1. Research VRM rendering in Python
+2. Create basic window with transparency
+3. Load and display VRM model
+4. Implement dragging
+5. Add sound effects
--- a/README.md
+++ b/README.md
@@ -0,0 +1,182 @@
+# Desktop Waifu 🎀
+
+An AI-powered desktop companion with VRM model rendering and Discord integration.
+
+## Features
+
+### Current (MVP)
+- ✅ Transparent desktop widget
+- ✅ Draggable VRM character
+- ✅ Always-on-top window
+- ✅ Basic state management
+- ⏳ VRM model rendering (in progress)
+- ⏳ Sound effects on interaction
+- ⏳ Text chat interface
+- ⏳ Local LLM integration
+- ⏳ Expression changes based on emotion
+- ⏳ Discord bot integration
+
+### Planned
+- Voice input/output (STT/TTS)
+- Advanced animations
+- System integration (notifications, app control)
+- Memory persistence
+- Proactive messaging
+- Cross-platform support
+
+## Setup
+
+### Prerequisites
+- Python 3.10+
+- VRM model file (`.vrm`)
+- Local LLM (Ollama, llama.cpp, etc.) - optional for testing
+
+### Installation
+
+1. **Clone/Download the project**
+
+2. **Install dependencies:**
+```bash
+pip install -r requirements.txt
+```
+
+3. **Configure environment:**
+```bash
+cp .env.example .env
+# Edit .env with your settings
+```
+
+4. **Add your VRM model:**
+   - Place your `.vrm` file in the `models/` folder
+   - Update `VRM_MODEL_PATH` in `.env`
+
+5. **Add sound effects (optional):**
+   - Place `.wav` files in `assets/sounds/`
+   - Examples: `squeak.wav`, `click.wav`
+
+### Discord Setup (Optional)
+
+1. Create a Discord bot at https://discord.com/developers/applications
+2. Enable these intents:
+   - Message Content Intent
+   - Server Members Intent
+3. Copy bot token to `DISCORD_BOT_TOKEN` in `.env`
+4. Invite bot to your server with permissions:
+   - Send Messages
+   - Read Message History
+   - Use Slash Commands
+
+### LLM Setup (Optional)
+
+#### Using Ollama:
+```bash
+# Install Ollama from https://ollama.ai
+ollama pull llama2
+# Update .env: LLM_API_URL=http://localhost:11434
+```
+
+#### Using llama.cpp:
+```bash
+pip install llama-cpp-python
+# Configure model path in code
+```
+
+## Running
+
+```bash
+python main.py
+```
+
+## Usage
+
+### Desktop Interactions
+- **Click and drag**: Move the waifu around your screen
+- **Double-click**: Open chat interface (coming soon)
+- **Right-click**: Context menu (coming soon)
+
+### Discord Commands
+- `!hello`: Greet the waifu
+- `!status`: Check current mood/status
+- `@mention`: Talk to the waifu in any channel
+- **DM**: Send direct messages
+
+## Project Structure
+
+```
+Waifu/
+├── main.py                 # Entry point
+├── requirements.txt        # Dependencies
+├── .env                    # Configuration (create from .env.example)
+├── PROJECT_PLAN.md         # Development plan
+├── RESEARCH_FINDINGS.md    # Technical research
+├── models/                 # VRM model files
+│   └── .gitkeep
+├── assets/
+│   └── sounds/             # Sound effects
+│       └── .gitkeep
+└── src/
+    ├── core/
+    │   └── state_manager.py    # State synchronization
+    ├── ui/
+    │   ├── waifu_window.py     # Main window
+    │   └── vrm_widget.py       # VRM renderer
+    ├── discord_bot/
+    │   └── bot.py              # Discord integration
+    ├── llm/                    # LLM integration (TODO)
+    └── audio/                  # Audio system (TODO)
+```
+
+## Development Status
+
+### Phase 1: MVP (In Progress)
+- [x] Project structure
+- [x] State management system
+- [x] Transparent window framework
+- [x] Drag functionality
+- [x] Basic OpenGL setup
+- [ ] VRM model loading
+- [ ] VRM rendering with MToon shader
+- [ ] Sound effects
+- [ ] Chat interface
+- [ ] LLM integration
+- [ ] Discord bot
+- [ ] Expression control
+
+### Phase 2: Enhancement (Planned)
+- [ ] Voice I/O
+- [ ] Advanced animations
+- [ ] System integration
+- [ ] Memory/database
+- [ ] .exe packaging
+
+## Technical Details
+
+### Architecture
+- **UI**: PyQt6 with transparent windows
+- **Rendering**: OpenGL via QOpenGLWidget
+- **VRM Parsing**: pygltflib
+- **State Management**: Custom event-driven system
+- **Discord**: discord.py
+- **LLM**: Flexible (Ollama, llama.cpp, custom)
+
+### VRM Rendering
+- VRM models are glTF 2.0 with extensions
+- Custom MToon shader implementation needed
+- Blend shapes for facial expressions
+- Bone animations for gestures
+
+See `RESEARCH_FINDINGS.md` for detailed technical research.
+
+## Contributing
+
+This is a personal project, but suggestions and feedback are welcome!
+
+## License
+
+TBD
+
+## Acknowledgments
+
+- VRM Consortium for the VRM specification
+- PyQt project for the excellent GUI framework
+- discord.py for Discord integration
--- a/RESEARCH_FINDINGS.md
+++ b/RESEARCH_FINDINGS.md
@@ -0,0 +1,105 @@
+# VRM Rendering Research Findings
+
+## Date: 2025-09-30
+
+## Problem
+Need to render VRM 3D model in a transparent desktop window using Python.
+
+## VRM Format
+- VRM is based on glTF 2.0 with VRM-specific extensions
+- Uses MToon shader for toon/cel-shaded rendering
+- Contains blend shapes for facial expressions
+- Contains bone data for animations
+
+## Python VRM/glTF Libraries
+
+### pygltflib (RECOMMENDED)
+- **Pros**: Can parse VRM files, read extension data, well-maintained
+- **Cons**: Parsing only, doesn't handle rendering
+- **Use**: Load VRM data, extract meshes/materials/animations
+
+### Alternatives
+- `gltflib`: Fork of pygltflib with divergent features
+- `pyrender`: Can render glTF but **doesn't support MToon shader properly** (produces holes)
+
+## Rendering Solutions
+
+### ✅ CHOSEN: PyQt6 + QOpenGLWidget
+**Best fit for desktop widget**
+
+**Pros:**
+- Native transparent window support (`WA_TranslucentBackground`)
+- Always-on-top windows (`WindowStaysOnTopHint`)
+- Frameless windows (`FramelessWindowHint`)
+- Direct OpenGL rendering via QOpenGLWidget
+- Excellent for desktop widgets/mascots
+- Can implement custom MToon shader in GLSL
+
+**Implementation:**
+```python
+class VRMWidget(QOpenGLWidget):
+    def initializeGL(self):
+        # Setup OpenGL state, load shaders
+    def resizeGL(self, w, h):
+        # Handle window resize
+    def paintGL(self):
+        # Render VRM model
+```
+
+**Window Setup:**
+```python
+window.setAttribute(Qt.WA_TranslucentBackground)
+window.setWindowFlags(Qt.FramelessWindowHint | Qt.WindowStaysOnTopHint)
+```
+
+### Alternative: Panda3D
+**Not chosen due to:**
+- Limited transparent window support
+- Requires embedding in another GUI framework anyway
+- More complexity for our use case
+
+### Alternative: Blender Python API
+**Not chosen due to:**
+- Too heavyweight for a desktop widget
+- Not designed for real-time desktop applications
+
+## MToon Shader Implementation
+Since Python libraries don't support MToon, we need to:
+1. Parse VRM using pygltflib to get material properties
+2. Implement custom GLSL MToon shader in OpenGL
+3. Apply shader during rendering
+
+MToon shader resources:
+- Reference: https://github.com/Santarh/MToon
+- Can port GLSL version to PyQt's OpenGL context
+
+## Recommended Tech Stack
+
+### Core
+- **PyQt6**: Window management, transparency, always-on-top
+- **QOpenGLWidget**: OpenGL rendering context
+- **pygltflib**: VRM/glTF parsing
+- **PyOpenGL**: OpenGL bindings for Python
+
+### Audio
+- **pygame**: Sound effects (squeaks, etc.)
+- **pyttsx3** or **Coqui TTS**: Text-to-speech
+- **whisper.cpp Python bindings**: Speech-to-text
+
+### LLM
+- **llama-cpp-python**: Local LLM inference
+- **ollama-python**: Alternative if using Ollama
+
+### Discord
+- **discord.py**: Discord bot
+
+### Packaging
+- **PyInstaller** or **Nuitka**: .exe compilation
+
+## Next Steps
+1. Install PyQt6, PyOpenGL, pygltflib
+2. Create basic transparent window
+3. Load VRM using pygltflib
+4. Implement basic OpenGL renderer
+5. Port MToon shader to GLSL
+6. Add interactivity (drag, click)
--- a/assets/sounds/.gitkeep
+++ b/assets/sounds/.gitkeep
@@ -0,0 +1,2 @@
+# Place sound effect files here
+# Example: squeak.wav, click.wav, etc.
--- a/main.py
+++ b/main.py
@@ -0,0 +1,41 @@
+"""
+Desktop Waifu - Main Entry Point
+A VRM-based AI desktop companion with Discord integration
+"""
+import sys
+import asyncio
+from PyQt6.QtWidgets import QApplication
+from PyQt6.QtCore import Qt
+from dotenv import load_dotenv
+
+# Load environment variables
+load_dotenv()
+
+# Import application modules
+from src.ui.waifu_window import WaifuWindow
+from src.discord_bot.bot import WaifuBot
+from src.core.state_manager import StateManager
+
+def main():
+    """Main application entry point"""
+    # Create Qt Application
+    app = QApplication(sys.argv)
+    app.setApplicationName("Desktop Waifu")
+
+    # Initialize state manager (shared between desktop and Discord)
+    state_manager = StateManager()
+
+    # Create main window
+    window = WaifuWindow(state_manager)
+    window.show()
+
+    # Start Discord bot in background (if configured)
+    # TODO: Implement Discord bot integration
+    # discord_bot = WaifuBot(state_manager)
+    # asyncio.create_task(discord_bot.start())
+
+    # Run application
+    sys.exit(app.exec())
+
+if __name__ == "__main__":
+    main()
--- a/models/.gitkeep
+++ b/models/.gitkeep
@@ -0,0 +1,2 @@
+# Place your .vrm model file here
+# Example: waifu.vrm
--- a/requirements.txt
+++ b/requirements.txt
@@ -0,0 +1,25 @@
+# Core GUI and Rendering
+PyQt6>=6.6.0
+PyOpenGL>=3.1.7
+PyOpenGL-accelerate>=3.1.7
+
+# VRM/glTF Loading
+pygltflib>=1.16.1
+numpy>=1.24.0
+pillow>=10.0.0
+
+# Audio
+pygame>=2.5.0
+pyttsx3>=2.90
+
+# LLM (choose one or install as needed)
+# llama-cpp-python>=0.2.0
+# ollama>=0.1.0
+
+# Discord
+discord.py>=2.3.0
+python-dotenv>=1.0.0
+
+# Utilities
+aiohttp>=3.9.0
+asyncio-mqtt>=0.16.0
--- a/src/init.py
+++ b/src/init.py
@@ -0,0 +1,2 @@
+"""Desktop Waifu - Source Package"""
+__version__ = "0.1.0"
--- a/src/audio/init.py
+++ b/src/audio/init.py
@@ -0,0 +1 @@
+"""Audio system for Desktop Waifu (TTS, STT, sound effects)"""
--- a/src/core/init.py
+++ b/src/core/init.py
@@ -0,0 +1 @@
+"""Core functionality for Desktop Waifu"""
--- a/src/core/state_manager.py
+++ b/src/core/state_manager.py
@@ -0,0 +1,99 @@
+"""
+State Manager - Synchronizes state between desktop and Discord
+"""
+import asyncio
+from typing import Optional, Callable, Dict, Any
+from enum import Enum
+from dataclasses import dataclass
+from datetime import datetime
+
+class EmotionState(Enum):
+    """Waifu emotional states"""
+    NEUTRAL = "neutral"
+    HAPPY = "happy"
+    SAD = "sad"
+    SURPRISED = "surprised"
+    THINKING = "thinking"
+    EXCITED = "excited"
+    ANNOYED = "annoyed"
+
+@dataclass
+class WaifuState:
+    """Current state of the waifu"""
+    emotion: EmotionState = EmotionState.NEUTRAL
+    is_speaking: bool = False
+    is_listening: bool = False
+    current_animation: Optional[str] = None
+    last_interaction: Optional[datetime] = None
+    conversation_context: list = None
+
+    def __post_init__(self):
+        if self.conversation_context is None:
+            self.conversation_context = []
+
+class StateManager:
+    """Manages and synchronizes waifu state across components"""
+
+    def __init__(self):
+        self.state = WaifuState()
+        self._listeners: Dict[str, list[Callable]] = {
+            'emotion_change': [],
+            'speech_start': [],
+            'speech_end': [],
+            'interaction': [],
+        }
+
+    def register_listener(self, event: str, callback: Callable):
+        """Register a callback for state changes"""
+        if event in self._listeners:
+            self._listeners[event].append(callback)
+
+    def unregister_listener(self, event: str, callback: Callable):
+        """Unregister a callback"""
+        if event in self._listeners and callback in self._listeners[event]:
+            self._listeners[event].remove(callback)
+
+    def _notify_listeners(self, event: str, *args, **kwargs):
+        """Notify all listeners of an event"""
+        for callback in self._listeners.get(event, []):
+            try:
+                callback(*args, **kwargs)
+            except Exception as e:
+                print(f"Error in listener callback: {e}")
+
+    def set_emotion(self, emotion: EmotionState):
+        """Change waifu's emotional state"""
+        if self.state.emotion != emotion:
+            old_emotion = self.state.emotion
+            self.state.emotion = emotion
+            self._notify_listeners('emotion_change', old_emotion, emotion)
+
+    def start_speaking(self):
+        """Mark waifu as speaking"""
+        self.state.is_speaking = True
+        self._notify_listeners('speech_start')
+
+    def stop_speaking(self):
+        """Mark waifu as not speaking"""
+        self.state.is_speaking = False
+        self._notify_listeners('speech_end')
+
+    def add_to_conversation(self, role: str, message: str):
+        """Add message to conversation history"""
+        self.state.conversation_context.append({
+            'role': role,
+            'message': message,
+            'timestamp': datetime.now()
+        })
+        # Keep only last 20 messages
+        if len(self.state.conversation_context) > 20:
+            self.state.conversation_context = self.state.conversation_context[-20:]
+
+    def record_interaction(self):
+        """Record that an interaction occurred"""
+        self.state.last_interaction = datetime.now()
+        self._notify_listeners('interaction')
+
+    def get_conversation_history(self, limit: int = 10) -> list:
+        """Get recent conversation history"""
+        return self.state.conversation_context[-limit:]
--- a/src/discord_bot/init.py
+++ b/src/discord_bot/init.py
@@ -0,0 +1 @@
+"""Discord bot integration for Desktop Waifu"""
--- a/src/discord_bot/bot.py
+++ b/src/discord_bot/bot.py
@@ -0,0 +1,79 @@
+"""
+Discord Bot - Waifu Discord integration
+"""
+import discord
+from discord.ext import commands
+import os
+from typing import Optional
+
+from src.core.state_manager import StateManager, EmotionState
+
+class WaifuBot(commands.Bot):
+    """Discord bot for waifu interactions"""
+
+    def __init__(self, state_manager: StateManager):
+        intents = discord.Intents.default()
+        intents.message_content = True
+        intents.guilds = True
+        intents.dm_messages = True
+
+        super().__init__(command_prefix='!', intents=intents)
+
+        self.state_manager = state_manager
+        self.setup_commands()
+        self.setup_event_handlers()
+
+    def setup_commands(self):
+        """Setup bot commands"""
+
+        @self.command(name='hello')
+        async def hello(ctx):
+            """Say hello to the waifu"""
+            self.state_manager.set_emotion(EmotionState.HAPPY)
+            self.state_manager.record_interaction()
+            await ctx.send("Hello! 👋 I'm here!")
+
+        @self.command(name='status')
+        async def status(ctx):
+            """Check waifu status"""
+            emotion = self.state_manager.state.emotion.value
+            await ctx.send(f"Current mood: {emotion}")
+
+    def setup_event_handlers(self):
+        """Setup Discord event handlers"""
+
+        @self.event
+        async def on_ready():
+            print(f'{self.user} has connected to Discord!')
+            print(f'Bot is in {len(self.guilds)} guilds')
+
+        @self.event
+        async def on_message(message):
+            # Don't respond to self
+            if message.author == self.user:
+                return
+
+            # Check if bot is mentioned or in DM
+            if self.user.mentioned_in(message) or isinstance(message.channel, discord.DMChannel):
+                # TODO: Process message with LLM
+                self.state_manager.add_to_conversation('user', message.content)
+                self.state_manager.record_interaction()
+
+                # Placeholder response
+                response = "I heard you! (LLM integration coming soon)"
+                await message.channel.send(response)
+
+            # Process commands
+            await self.process_commands(message)
+
+    async def start_bot(self):
+        """Start the Discord bot"""
+        token = os.getenv('DISCORD_BOT_TOKEN')
+        if not token:
+            print("Warning: DISCORD_BOT_TOKEN not set in .env file")
+            return
+
+        try:
+            await self.start(token)
+        except Exception as e:
+            print(f"Error starting Discord bot: {e}")
--- a/src/llm/init.py
+++ b/src/llm/init.py
@@ -0,0 +1 @@
+"""LLM integration for Desktop Waifu"""
--- a/src/ui/init.py
+++ b/src/ui/init.py
@@ -0,0 +1 @@
+"""UI components for Desktop Waifu"""
--- a/src/ui/vrm_widget.py
+++ b/src/ui/vrm_widget.py
@@ -0,0 +1,151 @@
+"""
+VRM Widget - OpenGL widget for rendering VRM models
+"""
+from PyQt6.QtOpenGLWidgets import QOpenGLWidget
+from PyQt6.QtCore import Qt, QTimer
+from PyQt6.QtGui import QSurfaceFormat
+from OpenGL.GL import *
+from OpenGL.GLU import *
+import numpy as np
+
+from src.core.state_manager import StateManager, EmotionState
+
+class VRMWidget(QOpenGLWidget):
+    """OpenGL widget for rendering VRM character model"""
+
+    def __init__(self, state_manager: StateManager, parent=None):
+        # Configure OpenGL format with alpha channel for transparency
+        fmt = QSurfaceFormat()
+        fmt.setVersion(2, 1)  # Use OpenGL 2.1 for compatibility with fixed-function pipeline
+        fmt.setAlphaBufferSize(8)
+        QSurfaceFormat.setDefaultFormat(fmt)
+
+        super().__init__(parent)
+        self.state_manager = state_manager
+        self.vrm_model = None
+        self.current_emotion = EmotionState.NEUTRAL
+
+        # Setup state change listener
+        self.state_manager.register_listener('emotion_change', self.on_emotion_change)
+
+        # Animation timer
+        self.animation_timer = QTimer(self)
+        self.animation_timer.timeout.connect(self.update_animation)
+        self.animation_timer.start(16)  # ~60 FPS
+
+    def initializeGL(self):
+        """Initialize OpenGL state"""
+        # Enable depth testing
+        glEnable(GL_DEPTH_TEST)
+
+        # Enable blending for transparency
+        glEnable(GL_BLEND)
+        glBlendFunc(GL_SRC_ALPHA, GL_ONE_MINUS_SRC_ALPHA)
+
+        # Set clear color (transparent)
+        glClearColor(0.0, 0.0, 0.0, 0.0)
+
+        # TODO: Load VRM model
+        # self.load_vrm_model()
+
+        # TODO: Setup shaders (MToon shader)
+        # self.setup_shaders()
+
+        print("OpenGL initialized")
+
+    def resizeGL(self, w: int, h: int):
+        """Handle window resize"""
+        glViewport(0, 0, w, h)
+
+        # Setup projection matrix
+        glMatrixMode(GL_PROJECTION)
+        glLoadIdentity()
+        aspect = w / h if h != 0 else 1
+        gluPerspective(45, aspect, 0.1, 100.0)
+
+        glMatrixMode(GL_MODELVIEW)
+
+    def paintGL(self):
+        """Render the VRM model"""
+        # Clear buffers
+        glClear(GL_COLOR_BUFFER_BIT | GL_DEPTH_BUFFER_BIT)
+
+        # Reset modelview matrix
+        glLoadIdentity()
+
+        # Move camera back
+        glTranslatef(0.0, -0.5, -3.0)
+
+        # TODO: Render VRM model
+        # For now, render a placeholder
+        self.render_placeholder()
+
+    def render_placeholder(self):
+        """Render a placeholder (cube) until VRM is loaded"""
+        # Rotate for animation
+        import time
+        angle = (time.time() % 4) * 90
+        glRotatef(angle, 0, 1, 0)
+
+        # Draw a simple cube as placeholder
+        glBegin(GL_QUADS)
+
+        # Front face (red)
+        glColor4f(1.0, 0.0, 0.0, 0.8)
+        glVertex3f(-0.5, -0.5,  0.5)
+        glVertex3f( 0.5, -0.5,  0.5)
+        glVertex3f( 0.5,  0.5,  0.5)
+        glVertex3f(-0.5,  0.5,  0.5)
+
+        # Back face (green)
+        glColor4f(0.0, 1.0, 0.0, 0.8)
+        glVertex3f(-0.5, -0.5, -0.5)
+        glVertex3f(-0.5,  0.5, -0.5)
+        glVertex3f( 0.5,  0.5, -0.5)
+        glVertex3f( 0.5, -0.5, -0.5)
+
+        # Other faces (blue)
+        glColor4f(0.0, 0.0, 1.0, 0.8)
+        # Top
+        glVertex3f(-0.5,  0.5, -0.5)
+        glVertex3f(-0.5,  0.5,  0.5)
+        glVertex3f( 0.5,  0.5,  0.5)
+        glVertex3f( 0.5,  0.5, -0.5)
+        # Bottom
+        glVertex3f(-0.5, -0.5, -0.5)
+        glVertex3f( 0.5, -0.5, -0.5)
+        glVertex3f( 0.5, -0.5,  0.5)
+        glVertex3f(-0.5, -0.5,  0.5)
+
+        # Right face (yellow)
+        glColor4f(1.0, 1.0, 0.0, 0.8)
+        glVertex3f( 0.5, -0.5, -0.5)
+        glVertex3f( 0.5,  0.5, -0.5)
+        glVertex3f( 0.5,  0.5,  0.5)
+        glVertex3f( 0.5, -0.5,  0.5)
+
+        # Left face (magenta)
+        glColor4f(1.0, 0.0, 1.0, 0.8)
+        glVertex3f(-0.5, -0.5, -0.5)
+        glVertex3f(-0.5, -0.5,  0.5)
+        glVertex3f(-0.5,  0.5,  0.5)
+        glVertex3f(-0.5,  0.5, -0.5)
+
+        glEnd()
+
+    def update_animation(self):
+        """Update animation frame"""
+        # Trigger repaint
+        self.update()
+
+    def on_emotion_change(self, old_emotion: EmotionState, new_emotion: EmotionState):
+        """Handle emotion state changes"""
+        self.current_emotion = new_emotion
+        # TODO: Update blend shapes/expressions based on emotion
+        print(f"VRM Widget: Emotion changed to {new_emotion.value}")
+
+    def load_vrm_model(self, model_path: str):
+        """Load VRM model from file"""
+        # TODO: Implement VRM loading using pygltflib
+        print(f"Loading VRM model from {model_path}")
+        pass
--- a/src/ui/waifu_window.py
+++ b/src/ui/waifu_window.py
@@ -0,0 +1,108 @@
+"""
+Waifu Window - Main transparent desktop widget
+"""
+from PyQt6.QtWidgets import QMainWindow, QWidget, QVBoxLayout
+from PyQt6.QtCore import Qt, QPoint
+from PyQt6.QtGui import QPalette, QColor
+
+from src.core.state_manager import StateManager, EmotionState
+from src.ui.vrm_widget import VRMWidget
+
+class WaifuWindow(QMainWindow):
+    """Main window for desktop waifu"""
+
+    def __init__(self, state_manager: StateManager):
+        super().__init__()
+        self.state_manager = state_manager
+        self.dragging = False
+        self.drag_position = QPoint()
+
+        self.init_ui()
+        self.setup_event_listeners()
+
+    def init_ui(self):
+        """Initialize user interface"""
+        # Window properties
+        self.setWindowTitle("Desktop Waifu")
+        self.setFixedSize(400, 600)  # Adjust based on VRM model size
+
+        # Make window frameless and transparent
+        self.setWindowFlags(
+            Qt.WindowType.FramelessWindowHint |
+            Qt.WindowType.WindowStaysOnTopHint |
+            Qt.WindowType.Tool  # Prevents taskbar icon
+        )
+        self.setAttribute(Qt.WidgetAttribute.WA_TranslucentBackground)
+
+        # Create central widget
+        central_widget = QWidget()
+        self.setCentralWidget(central_widget)
+
+        # Layout
+        layout = QVBoxLayout()
+        layout.setContentsMargins(0, 0, 0, 0)
+        central_widget.setLayout(layout)
+
+        # VRM rendering widget
+        self.vrm_widget = VRMWidget(self.state_manager)
+        layout.addWidget(self.vrm_widget)
+
+        # Position window (bottom-right corner by default)
+        self.position_window()
+
+    def position_window(self):
+        """Position window at bottom-right of screen"""
+        from PyQt6.QtGui import QScreen
+        screen: QScreen = self.screen()
+        screen_geometry = screen.availableGeometry()
+
+        x = screen_geometry.width() - self.width() - 50
+        y = screen_geometry.height() - self.height() - 50
+        self.move(x, y)
+
+    def setup_event_listeners(self):
+        """Setup state manager event listeners"""
+        self.state_manager.register_listener('emotion_change', self.on_emotion_change)
+
+    def on_emotion_change(self, old_emotion: EmotionState, new_emotion: EmotionState):
+        """Handle emotion state changes"""
+        print(f"Emotion changed: {old_emotion.value} -> {new_emotion.value}")
+        # VRM widget will handle animation changes
+
+    def mousePressEvent(self, event):
+        """Handle mouse press - start dragging"""
+        if event.button() == Qt.MouseButton.LeftButton:
+            self.dragging = True
+            self.drag_position = event.globalPosition().toPoint() - self.frameGeometry().topLeft()
+
+            # Play squeak sound
+            # TODO: Implement sound effects
+            self.state_manager.record_interaction()
+            self.state_manager.set_emotion(EmotionState.SURPRISED)
+
+            event.accept()
+
+    def mouseMoveEvent(self, event):
+        """Handle mouse move - dragging"""
+        if self.dragging:
+            self.move(event.globalPosition().toPoint() - self.drag_position)
+            event.accept()
+
+    def mouseReleaseEvent(self, event):
+        """Handle mouse release - stop dragging"""
+        if event.button() == Qt.MouseButton.LeftButton:
+            self.dragging = False
+
+            # Return to neutral emotion after a moment
+            # TODO: Add delay before returning to neutral
+            self.state_manager.set_emotion(EmotionState.NEUTRAL)
+
+            event.accept()
+
+    def mouseDoubleClickEvent(self, event):
+        """Handle double-click - open chat"""
+        if event.button() == Qt.MouseButton.LeftButton:
+            # TODO: Open chat interface
+            print("Double-click detected - open chat")
+            self.state_manager.record_interaction()
+            event.accept()
				`@@ -0,0 +1 @@`
				`"""Audio system for Desktop Waifu (TTS, STT, sound effects)"""`
				`@@ -0,0 +1 @@`
				`"""Discord bot integration for Desktop Waifu"""`