English | 简体中文

Current sponsors:

• ZenMux - Powers the core game flow, roleplay, and summary features with AI models
• Dashscope - Provides additional AI model support
• OpenCreator - Generates AI character portraits

---

Note: This project was born at the "Watcha + ModelScope Global Hackathon" as an AI-native game.

"Wolfcha" combines Wolf (Werewolf) + Cha (猹, a character from Chinese literature). It's a nod to the hackathon host while also capturing the fun of watching AI characters interact — like spectating a show.

After graduating, getting 8-12 people together for a proper Werewolf game became nearly impossible. While Werewolf is fundamentally a social game, its core appeal — logical deduction, verbal sparring, and reading between the lines — remains captivating even without the social element.

To enjoy Werewolf anytime, anywhere, we built this AI-powered version. As the name suggests, every player except you (Seer, Witch, Hunter, Guard, Werewolves, etc.) is controlled by AI.

Thanks to the growing context windows and instruction-following capabilities of large language models (LLMs), we've implemented a sophisticated dual-layer roleplay system:

• Layer 1: The AI plays a "virtual player" with a unique personality and background.
• Layer 2: This virtual player then takes on a Werewolf role (e.g., Seer) and speaks, bluffs, and reasons based on the game state.

Every conversation is generated in real-time, full of unpredictability and fun.

This isn't just Werewolf — it's a battleground for AI models.

We've integrated multiple top AI models to compete against each other. After each game, you can see which model powered each character. It's a hidden "Turing test" — observe which model reasons sharply, which one seems "adorably clueless," and which one sounds the most human.

Current built-in models (subject to project configuration):

• DeepSeek V3.2
• Qwen3-235B-A22B
• Kimi K2
• Gemini 3 Flash
• Seed 1.8 (ByteDance)

While we don't have a professional art team, we've crafted a polished UI/UX:

• Retro Design Style: Clean layouts with vintage color palettes.
• Dynamic Interactions:
  • Eye-blink transitions for day/night changes.
  • Character lip-sync animations during speech.
  • Unique character portraits for special roles during night actions.

We're continuing to improve:

• Mobile Optimization: Play seamlessly on any device.
• Flexible Player Count: Support 8-12 player custom games.
• Post-Game Review / Chat: Reflect on strategies and memorable moments.
• Special Abilities: Unique mechanics like time rewind and AI insight.
• Custom Model Selection: Choose which AI models join your game.
• Multiplayer Mode: Play with friends alongside AI characters.
• Character Ratings: Upvote standout personalities/models to find the best Werewolf players.

Built with modern web technologies:

• Framework: Next.js 16 (App Router)
• Language: TypeScript
• Styling: Tailwind CSS 4
• UI Components: Radix UI, Lucide React
• State Management: Jotai
• Editor: Tiptap (For rich text interactions)
• Animations: Framer Motion
• Avatar Generation: DiceBear (Notionists style)
• AI Integration: ZenMux (Unified interface for LLMs)

To run this project locally:

1. Clone the repository

git clone https://github.com/oil-oil/wolfcha.git
cd wolfcha

2. Install dependencies

# Using pnpm (recommended)
pnpm install

# Or using npm
npm install

3. Configure environment variables

You'll need to set up API keys (ZenMux, etc.) for full functionality. Refer to .env.example and create your .env.local.

4. Start the development server

pnpm dev

Open http://localhost:3000 in your browser.

MIT