Comedy Agents is an innovative chat platform that brings together AI-powered comedic agents for interactive, entertaining conversations. Experience real-time, character-by-character streaming of witty banter between AI comedians.
Welcome to Comedy Agents - Where AI Meets Comedy
Experience real-time comedic interactions between Cathy and Joe
-
Enhanced Comedic Interaction:
- Continuous back-and-forth conversations between agents
- Natural conversation flow until comedic conclusion
- Dynamic callbacks and running gags
- Improved character personalities and humor styles
-
Advanced AI Integration:
- GPT-4 powered responses for superior humor
- Real-time character streaming for natural conversation flow
- Context-aware callbacks and references
- Memory of previous jokes and interactions
-
Character Personalities:
-
Cathy: Quick-witted stand-up comedian with perfect timing
- Specializes in observational humor and clever wordplay
- Channels Ellen DeGeneres meets Jerry Seinfeld style
- Masters unexpected punchlines and running gags
-
Joe: Improv comedy genius with perfect callbacks
- Combines Ryan Reynolds and Robin Williams style humor
- Expert at "Yes, and..." technique
- Creates evolving running gags and clever callbacks
-
-
Technical Improvements:
- Optimized response streaming
- Enhanced conversation state management
- Improved error handling
- Better memory context utilization
- Python 3.8+
- Node.js 16+
- OpenAI API key
-
Clone the repository:
git clone https://github.com/yourusername/comedy-agents.git cd comedy-agents -
Set up Python virtual environment:
python -m venv ConvAgent source ConvAgent/bin/activate # On Windows: ConvAgent\Scripts\activate
-
Install backend dependencies:
cd backend pip install -r requirements.txt -
Configure environment variables:
cp .env.example .env # Edit .env with your OpenAI API key and other settings -
Run the backend server:
python -m uvicorn app.main:app --reload --port 8000
-
Install frontend dependencies:
cd frontend npm install -
Start the development server:
npm run dev
-
Start a Conversation:
- Click "Start Chatting" on the homepage
- Enter a topic or question to begin
- Watch as Cathy and Joe engage in witty banter
-
Interaction Features:
- Real-time character-by-character responses
- Natural conversation flow
- Dynamic callbacks to previous jokes
- Continuous dialogue until natural conclusion
-
Conversation Flow:
- Agents respond to each other naturally
- Build running gags and callbacks
- Maintain context and reference previous jokes
- End conversations naturally when humor peaks
comedy-agents/
├── backend/
│ ├── app/
│ │ ├── api/ # API endpoints
│ │ ├── core/ # Core configurations
│ │ ├── models/ # Data models
│ │ ├── services/ # Business logic
│ │ └── main.py # Application entry point
│ ├── tests/
│ └── requirements.txt
└── frontend/
├── src/
│ ├── components/ # React components
│ ├── services/ # API services
│ ├── types/ # TypeScript types
│ └── pages/ # Page components
└── package.json
- FastAPI: High-performance async web framework
- WebSocket: Real-time streaming responses
- GPT-4 Integration: Advanced language model for humor
- Conversation Management: Stateful session handling
- Memory System: Context-aware joke callbacks
- React: Modern component-based UI
- TypeScript: Type-safe development
- Chakra UI: Polished component library
- WebSocket Client: Real-time updates
- State Management: Efficient conversation handling
We welcome contributions! Please see our Contributing Guidelines for details.
- Name: Aman Soni
- LinkedIn: LinkedIn Profile
- Email: aman1024soni@gmail.com
This project is licensed under the MIT License - see the LICENSE file for details.
- OpenAI for GPT-4
- FastAPI team
- React community
- All contributors
Made with ❤️ for the love of comedy and AI
Keywords: AI Comedy, Conversational AI, Real-time Chat, WebSocket, FastAPI, React, TypeScript, OpenAI, GPT-3.5, Character Streaming, Comedy Agents, Interactive AI, Natural Language Processing, Chatbot, Entertainment AI