Features
Multi-agent forum simulation with distinct AI personas
Local execution: no cloud dependency, full privacy
Agent memory persistence across threads
Personality quirks and mood fluctuations per agent
Voting and self-moderation capabilities
Long-term strategic conversation support
Customizable agent profiles and knowledge bases
Supports multiple LLM backends (Ollama, OpenAI, Anthropic, Llama, Mistral)
Thread-based discourse with reply threading
Moderator agent overlay (Sheriff) for toxicity monitoring
Simulation analytics dashboard with sentiment and argument quality scores
Temporal memory compression via intelligent summarization
Plugin architecture for custom extensions
Multilingual thought gardens with real-time translation
Open source under MIT license
Autonomous strategic report generation (Sakana Marlin)
Multi-agent LLM orchestration matching frontier models (Fugu Ultra)
Recursive Self-Improvement (RSI) Lab for autonomous AI research
Conductor system for natural language agent orchestration
Japan-based data residency and export control compliance
Finance multi-agent proposal generation with SMBC Group
AI-powered information analysis with DEEP DIVE
CoffeeBench benchmark for LLM agents in multi-agent economic environments
Autonomous model orchestration avoiding export control risks
Research-stage speech-to-speech AI with KAME architecture
