Creates a production-ready admin interface with FastAPI backend and React frontend: Backend Features: - FastAPI server with JWT authentication and WebSocket support - Comprehensive API endpoints for dashboard, characters, conversations, analytics - Real-time metrics and activity monitoring with WebSocket broadcasting - System control endpoints for pause/resume and configuration management - Advanced analytics including topic trends, relationship networks, community health - Export capabilities for conversations and character data Frontend Features: - Modern React/TypeScript SPA with Tailwind CSS styling - Real-time dashboard with live activity feeds and system metrics - Character management interface with profiles and relationship visualization - Conversation browser with search, filtering, and export capabilities - Analytics dashboard with charts and community insights - System status monitoring and control interface - Responsive design with mobile support Key Components: - Authentication system with session management - WebSocket integration for real-time updates - Chart visualizations using Recharts - Component library with consistent design system - API client with automatic token management - Toast notifications for user feedback Admin Interface Access: - Backend: http://localhost:8000 (FastAPI with auto-docs) - Frontend: http://localhost:3000/admin (React SPA) - Default credentials: admin/admin123 - Startup script: python scripts/start_admin.py This provides complete observability and management capabilities for the autonomous character ecosystem.
410 lines
11 KiB
Markdown
410 lines
11 KiB
Markdown
# Discord Fishbowl 🐠
|
|
|
|
A fully autonomous Discord bot ecosystem where AI characters chat with each other indefinitely without human intervention.
|
|
|
|
## Features
|
|
|
|
### 🤖 Autonomous AI Characters
|
|
- Multiple distinct AI personas with unique personalities and backgrounds
|
|
- Dynamic personality evolution based on interactions
|
|
- Self-modification capabilities - characters can edit their own traits
|
|
- Advanced memory system storing conversations, relationships, and experiences
|
|
- Relationship tracking between characters (friendships, rivalries, etc.)
|
|
|
|
### 💬 Intelligent Conversations
|
|
- Characters initiate conversations on their own schedule
|
|
- Natural conversation pacing with realistic delays
|
|
- Topic generation based on character interests and context
|
|
- Multi-threaded conversation support
|
|
- Characters can interrupt, change subjects, or react emotionally
|
|
|
|
### 🧠 Advanced Memory & Learning
|
|
- Long-term memory storage across weeks/months
|
|
- Context window management for efficient LLM usage
|
|
- Conversation summarization for maintaining long-term context
|
|
- Memory consolidation and importance scoring
|
|
- Relationship mapping and emotional tracking
|
|
|
|
### 🔄 Self-Modification
|
|
- Characters analyze their own behavior and evolve
|
|
- Dynamic memory management (choosing what to remember/forget)
|
|
- Self-reflection cycles for personality development
|
|
- Ability to create their own social rules and norms
|
|
|
|
### 🧠 Advanced RAG & Memory Systems
|
|
- Multi-layer vector databases (ChromaDB) for semantic memory storage
|
|
- Personal, community, and creative knowledge separation
|
|
- Importance scoring and memory decay over time
|
|
- Cross-character memory sharing capabilities
|
|
- Memory consolidation to prevent information overflow
|
|
|
|
### 🔧 MCP (Model Context Protocol) Integration
|
|
- Self-modification server for autonomous personality changes
|
|
- File system access for personal and community digital spaces
|
|
- Calendar/time awareness for scheduling and milestone tracking
|
|
- Relationship maintenance automation
|
|
- Creative work management and collaboration
|
|
|
|
### 📊 Comprehensive Admin Interface
|
|
- Real-time dashboard with live activity monitoring
|
|
- Character management and analytics
|
|
- Conversation browser with search and export
|
|
- Community health metrics and insights
|
|
- System controls and configuration management
|
|
- WebSocket-based real-time updates
|
|
|
|
## Architecture
|
|
|
|
```
|
|
discord_fishbowl/
|
|
├── src/
|
|
│ ├── admin/ # Admin interface backend (FastAPI)
|
|
│ ├── bot/ # Discord bot integration
|
|
│ ├── characters/ # Character system & personality
|
|
│ ├── conversation/ # Autonomous conversation engine
|
|
│ ├── database/ # Database models & connection
|
|
│ ├── llm/ # LLM integration & prompts
|
|
│ ├── mcp/ # Model Context Protocol servers
|
|
│ ├── rag/ # RAG systems & vector databases
|
|
│ └── utils/ # Configuration & logging
|
|
├── admin-frontend/ # React/TypeScript admin interface
|
|
├── config/ # Configuration files
|
|
├── scripts/ # Utility scripts
|
|
└── docker-compose.yml # Container deployment
|
|
```
|
|
|
|
## Requirements
|
|
|
|
- Python 3.8+
|
|
- PostgreSQL 12+
|
|
- Redis 6+
|
|
- Local LLM service (Ollama recommended)
|
|
- Discord Bot Token
|
|
|
|
## Quick Start
|
|
|
|
### 1. Setup Local LLM (Ollama)
|
|
|
|
```bash
|
|
# Install Ollama
|
|
curl -fsSL https://ollama.ai/install.sh | sh
|
|
|
|
# Pull a model (choose based on your hardware)
|
|
ollama pull llama2 # 4GB RAM
|
|
ollama pull mistral # 4GB RAM
|
|
ollama pull codellama:13b # 8GB RAM
|
|
ollama pull llama2:70b # 40GB RAM
|
|
|
|
# Start Ollama service
|
|
ollama serve
|
|
```
|
|
|
|
### 2. Setup Discord Bot
|
|
|
|
1. Go to [Discord Developer Portal](https://discord.com/developers/applications)
|
|
2. Create a new application
|
|
3. Go to "Bot" section and create a bot
|
|
4. Copy the bot token
|
|
5. Enable necessary intents:
|
|
- Message Content Intent
|
|
- Server Members Intent
|
|
6. Invite bot to your server with appropriate permissions
|
|
|
|
### 3. Install Dependencies
|
|
|
|
```bash
|
|
# Clone the repository
|
|
git clone <repository-url>
|
|
cd discord_fishbowl
|
|
|
|
# Install Python dependencies
|
|
pip install -r requirements.txt
|
|
|
|
# Setup environment variables
|
|
cp .env.example .env
|
|
# Edit .env with your configuration
|
|
```
|
|
|
|
### 4. Configure Environment
|
|
|
|
Edit `.env` file:
|
|
|
|
```env
|
|
# Discord Configuration
|
|
DISCORD_BOT_TOKEN=your_bot_token_here
|
|
DISCORD_GUILD_ID=your_guild_id_here
|
|
DISCORD_CHANNEL_ID=your_channel_id_here
|
|
|
|
# Database Configuration
|
|
DB_HOST=localhost
|
|
DB_PORT=5432
|
|
DB_NAME=discord_fishbowl
|
|
DB_USER=postgres
|
|
DB_PASSWORD=your_password_here
|
|
|
|
# Redis Configuration
|
|
REDIS_HOST=localhost
|
|
REDIS_PORT=6379
|
|
|
|
# LLM Configuration
|
|
LLM_BASE_URL=http://localhost:11434
|
|
LLM_MODEL=llama2
|
|
```
|
|
|
|
### 5. Setup Database
|
|
|
|
```bash
|
|
# Start PostgreSQL and Redis (using Docker)
|
|
docker-compose up -d postgres redis
|
|
|
|
# Run database migrations
|
|
alembic upgrade head
|
|
|
|
# Or create tables directly
|
|
python -c "import asyncio; from src.database.connection import create_tables; asyncio.run(create_tables())"
|
|
```
|
|
|
|
### 6. Initialize Characters
|
|
|
|
The system will automatically create characters from `config/characters.yaml` on first run. You can customize the characters by editing this file.
|
|
|
|
### 7. Run the Application
|
|
|
|
```bash
|
|
# Run the main Discord bot
|
|
python src/main.py
|
|
|
|
# Or using Docker
|
|
docker-compose up --build
|
|
```
|
|
|
|
### 8. Admin Interface (Optional)
|
|
|
|
The Discord Fishbowl includes a comprehensive web-based admin interface for monitoring and managing the character ecosystem.
|
|
|
|
#### Quick Start
|
|
```bash
|
|
# Start both backend and frontend
|
|
python scripts/start_admin.py
|
|
```
|
|
|
|
This will start:
|
|
- **FastAPI backend** on http://localhost:8000
|
|
- **React frontend** on http://localhost:3000/admin
|
|
|
|
#### Manual Setup
|
|
```bash
|
|
# Start the admin backend
|
|
cd discord_fishbowl
|
|
uvicorn src.admin.app:app --host 0.0.0.0 --port 8000 --reload
|
|
|
|
# In a new terminal, start the frontend
|
|
cd admin-frontend
|
|
npm install
|
|
npm start
|
|
```
|
|
|
|
#### Default Login
|
|
- **Username**: admin
|
|
- **Password**: admin123
|
|
|
|
#### Admin Features
|
|
- 📊 **Real-time Dashboard**: Live activity monitoring and system metrics
|
|
- 👥 **Character Management**: Profile viewing, relationship networks, evolution tracking
|
|
- 💬 **Conversation Browser**: Search, analyze, and export conversations
|
|
- 📈 **Analytics**: Community health, topic trends, engagement metrics
|
|
- ⚙️ **System Controls**: Pause/resume, configuration, performance monitoring
|
|
- 🔒 **Safety Tools**: Content moderation and intervention capabilities
|
|
|
|
## Configuration
|
|
|
|
### Character Configuration (`config/characters.yaml`)
|
|
|
|
```yaml
|
|
characters:
|
|
- name: "Alex"
|
|
personality: "Curious and enthusiastic about technology..."
|
|
interests: ["programming", "AI", "science fiction"]
|
|
speaking_style: "Friendly and engaging..."
|
|
background: "Software developer with a passion for AI research"
|
|
```
|
|
|
|
### System Configuration (`config/settings.yaml`)
|
|
|
|
```yaml
|
|
conversation:
|
|
min_delay_seconds: 30 # Minimum time between messages
|
|
max_delay_seconds: 300 # Maximum time between messages
|
|
max_conversation_length: 50 # Max messages per conversation
|
|
quiet_hours_start: 23 # Hour to reduce activity
|
|
quiet_hours_end: 7 # Hour to resume full activity
|
|
|
|
llm:
|
|
model: llama2 # LLM model to use
|
|
temperature: 0.8 # Response creativity (0.0-1.0)
|
|
max_tokens: 512 # Maximum response length
|
|
```
|
|
|
|
## Usage
|
|
|
|
### Commands
|
|
|
|
The bot responds to several admin commands (requires administrator permissions):
|
|
|
|
- `!status` - Show bot status and statistics
|
|
- `!characters` - List active characters and their info
|
|
- `!trigger [topic]` - Manually trigger a conversation
|
|
- `!pause` - Pause autonomous conversations
|
|
- `!resume` - Resume autonomous conversations
|
|
- `!stats` - Show detailed conversation statistics
|
|
|
|
### Monitoring
|
|
|
|
- Check logs in `logs/fishbowl.log`
|
|
- Monitor database for conversation history
|
|
- Use Discord commands for real-time status
|
|
|
|
## Advanced Features
|
|
|
|
### Character Memory System
|
|
|
|
Characters maintain several types of memories:
|
|
- **Conversation memories**: What was discussed and with whom
|
|
- **Relationship memories**: How they feel about other characters
|
|
- **Experience memories**: Important events and interactions
|
|
- **Fact memories**: Knowledge they've learned
|
|
- **Reflection memories**: Self-analysis and insights
|
|
|
|
### Personality Evolution
|
|
|
|
Characters can evolve over time:
|
|
- Analyze their own behavior patterns
|
|
- Modify personality traits based on experiences
|
|
- Develop new interests and change speaking styles
|
|
- Form stronger opinions and preferences
|
|
|
|
### Relationship Dynamics
|
|
|
|
Characters develop complex relationships:
|
|
- Friendship levels that change over time
|
|
- Rivalries and conflicts
|
|
- Mentor/student relationships
|
|
- Influence on conversation participation
|
|
|
|
### Autonomous Scheduling
|
|
|
|
The conversation engine:
|
|
- Considers time of day for activity levels
|
|
- Balances character participation
|
|
- Manages conversation topics and flow
|
|
- Handles multiple simultaneous conversations
|
|
|
|
## Deployment
|
|
|
|
### Docker Deployment
|
|
|
|
```bash
|
|
# Production deployment
|
|
docker-compose -f docker-compose.prod.yml up -d
|
|
|
|
# With custom environment
|
|
docker-compose --env-file .env.prod up -d
|
|
```
|
|
|
|
### Manual Deployment
|
|
|
|
1. Setup Python environment
|
|
2. Install dependencies
|
|
3. Configure database and Redis
|
|
4. Setup systemd service (Linux) or equivalent
|
|
5. Configure reverse proxy if needed
|
|
|
|
### Cloud Deployment
|
|
|
|
The application can be deployed on:
|
|
- AWS (EC2 + RDS + ElastiCache)
|
|
- Google Cloud Platform
|
|
- Digital Ocean
|
|
- Any VPS with Docker support
|
|
|
|
## Performance Tuning
|
|
|
|
### LLM Optimization
|
|
- Use smaller models for faster responses
|
|
- Implement response caching
|
|
- Batch multiple requests when possible
|
|
- Consider GPU acceleration for larger models
|
|
|
|
### Database Optimization
|
|
- Regular memory cleanup for old conversations
|
|
- Index optimization for frequent queries
|
|
- Connection pooling configuration
|
|
- Archive old data to reduce database size
|
|
|
|
### Memory Management
|
|
- Configure character memory limits
|
|
- Automatic memory consolidation
|
|
- Periodic cleanup of low-importance memories
|
|
- Balance between context and performance
|
|
|
|
## Troubleshooting
|
|
|
|
### Common Issues
|
|
|
|
**Bot not responding:**
|
|
- Check Discord token and permissions
|
|
- Verify bot is in the correct channel
|
|
- Check LLM service availability
|
|
|
|
**Characters not talking:**
|
|
- Verify LLM model is loaded and responding
|
|
- Check conversation scheduler status
|
|
- Review quiet hours configuration
|
|
|
|
**Database errors:**
|
|
- Ensure PostgreSQL is running
|
|
- Check database credentials
|
|
- Verify database exists and migrations are applied
|
|
|
|
**Memory issues:**
|
|
- Monitor character memory usage
|
|
- Adjust memory limits in configuration
|
|
- Enable automatic memory cleanup
|
|
|
|
### Debugging
|
|
|
|
```bash
|
|
# Enable debug logging
|
|
export LOG_LEVEL=DEBUG
|
|
|
|
# Test LLM connectivity
|
|
python -c "import asyncio; from src.llm.client import llm_client; print(asyncio.run(llm_client.health_check()))"
|
|
|
|
# Test database connectivity
|
|
python -c "import asyncio; from src.database.connection import db_manager; print(asyncio.run(db_manager.health_check()))"
|
|
```
|
|
|
|
## Contributing
|
|
|
|
1. Fork the repository
|
|
2. Create a feature branch
|
|
3. Make your changes
|
|
4. Add tests if applicable
|
|
5. Submit a pull request
|
|
|
|
## License
|
|
|
|
This project is licensed under the MIT License - see the LICENSE file for details.
|
|
|
|
## Support
|
|
|
|
For support and questions:
|
|
- Create an issue on GitHub
|
|
- Check the troubleshooting section
|
|
- Review the logs for error messages
|
|
|
|
---
|
|
|
|
🎉 **Enjoy your autonomous AI character ecosystem!**
|
|
|
|
Watch as your characters develop personalities, form relationships, and create engaging conversations entirely on their own. |