oil-oil/wolfcha
AI-powered Werewolf (Mafia) social deduction game where every player is controlled by top LLMs like DeepSeek, Qwen, Gemini, and more
Implements a dual-layer roleplay system where LLMs first generate distinct virtual player personalities, then perform in-character gameplay with real-time reasoning based on game state. Built on Next.js with ZenMux as a unified LLM abstraction layer, enabling seamless model swapping across DeepSeek, Qwen, Gemini, and others. Includes post-game model attribution and comparative analysis—essentially a Turing test embedded in competitive social deduction gameplay.
538 stars. Actively maintained with 37 commits in the last 30 days.
Stars
538
Forks
36
Language
TypeScript
License
Apache-2.0
Category
Last pushed
Mar 12, 2026
Commits (30d)
37
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/oil-oil/wolfcha"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related agents
4thfever/cultivation-world-simulator
基于 AI Agent 工作流的修仙世界模拟器，旨在还原智能、开放的仙侠世界。| An open-source Cultivation World Simulator using...
nikmcfly/MiroFish-Offline
Offline multi-agent simulation & prediction engine. English fork of MiroFish with Neo4j + Ollama...
yasserfarouk/negmas
Negotiation Multi-Agent System (A negotiation library designed for situated negotiations within...
KsanaDock/Microverse
A god-simulation sandbox game built on Godot 4 as a multi-agent AI social simulation system. In...
cormas/cormas
CORMAS (COmmon pool Ressources and Multi-Agent Simulations)