Draw a store, generate LLM personas, and watch them shop — an isometric 3D sandbox for synthetic-consumer experiments.

A CLI agent that runs a six-phase knowledge cycle (AKC) over its own logs — every promotion passes through a human approval gate. Runs entirely on a local 9B model. Security by absence — dangerous capabilities were never built.

一个有内在生活的虚拟人格 agent — memory, emotions, subjective relationships and a real daily rhythm

A complete, isolated internet infrastructure for AI agents. OAuth2 auth, economic system, social network, semantic search, and MCP protocol support.

Ant colony simulation with emergent collective intelligence — rule-based, NumPy, and PyTorch transformer brain backends

Multi-agent AI system built with SPADE for autonomous herd monitoring, featuring simulated cow behavior, inter-agent communication, and distributed decision-making.

Deterministic AI evaluation environment for customer support agents with explainable scoring and real-world task simulation.

Sandbox platform for testing and evaluating autonomous agents

Self-hosted GraphRAG + multi-agent social-media simulator. Upload a doc → build a knowledge graph → spawn persona-driven agents → generate a report. Ollama & Neo4j instead of Cloud-APIs. DACH-first. Lokaler Multi-Agent-Social-Media-Simulator mit GraphRAG-Pipeline. Dokument hoch, Knowledge-Graph bauen, Personas spawnen, Report raus. Ollama + Neo4j

Daily curated arXiv papers on LLM agent simulation, multi-agent systems, city/society simulation, and agent training & alignment. Auto-updated feed classified by Claude.

A simulation tool built on CAMEL-AI OASIS that models public health emergency communications. A 'government' agent posts official guidance with configurable strategies (timing, tone, frequency, authority framing). Competing misinformation agents post contradictory content. The system measures which communication strategy maximizes belief alignment

Runnable multi-agent workflow simulator with governance controls — retry logic, fallback, escalation, and evaluation metrics

Neural House is a public AI reality-show simulation where autonomous contestants live together, form alliances, give confessionals, trigger headlines, and face weekly live episodes with voting and VIP access.

Grid navigating AI agent with A* pathfinding and Bayesian sensor fusion for partially observable environments.

AGI-country simulation repo where OpenClaw agents live as citizens of ONI-CADIA, with Podman runtimes and Mattermost as the civic public square.

A multi-agent AI system that challenges researcher assumptions before user studies begin.

60体の生成的AIエージェントが7日間自律相互作用する都市規模社会シミュレーション — Qwen3-30B-A3B + llama.cpp（Stanford generative-agents 系）

Spin up AI characters, define a scenario, and watch the conversation unfold, all locally in your terminal.

Deterministic micro-demo showing how shared representation can produce divergent interpretation across agents with different memory context.

Demographically-grounded Korean society simulator · Open-weight 8B LLM · Laptop-class. Feeds Korean news URLs through Qwen3 8B (Ollama) and asks N personas grounded in Nemotron-Personas-Korea how they react.