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
mngr: run any coding agent in parallel anywhere
Bouncer: filter and heal your Twitter feed
Sculptor: manage parallel coding agents with UI
Blueprint: one-shot larger coding tasks
Vet: prevent AI coding agent mistakes
Latchkey: fine-grained HTTP permissions for agents
Ratchets: Rust tool for flexible style violation budgets
Open-source tools and community
Research publications on deep learning and ARC-AGI
Policy work for human-centric AI
Agent behavior auditing and control
Parallel agent orchestration across environments
