#simulation

Q-Learning Swarm Foraging 2026: Multi-Agent RL in Dynamic Grid Environments

Real-time 3D digital twin of an autonomous warehouse — 20 AMRs, deterministic simulation, explainable fleet scheduling, failure injection, VLM camera perception, AI Ops Copilot and what-if scenarios. React Three Fiber + FastAPI.

A 3D sandcastle simulator that runs entirely on the GPU. No engine, no libraries, no asset files, no build step. Built in one prompt with Claude Code.

One open-source modeler for structures, heat and fluids, built from scratch in pure Rust: parametric part in, verified results out. Automatic all-hex and tet meshing, our own nonlinear implicit and explicit FEA, heat transfer and lattice Boltzmann CFD — every result checked against theory. For engineers and AI agents alike. Free, forever.

Open-source football management simulation played by AI agents through MCP and watched through a TUI console.

予言 Yogen — a 500-agent AI swarm that debates your idea and predicts the outcome. Self-host free with your own Anthropic key.

Household decision simulation through persona-enriched multi-agent negotiation. The HDSim method core.

Residential mobility and relocation decision simulation via persona-enriched multi-agent negotiation (PEMAND)

Household travel decision simulation via persona-enriched multi-agent negotiation (PEMAND)

AI life-and-civilization simulation: TypeSafe Jev makes every decision (typed, probabilistic, auditable); LLMs plan — OpenAI-compatible APIs, local models (Ollama, LM Studio), Claude Code, Codex.

Build engineering digital twins as code with AI agents — code-defined CAD + digital twin simulation (physics/CFD/FEA) + scored verification, with rerun for data fusion toward live closed-loop twins. Hardware-in-the-loop ready. A Claude Code plugin.

An interactive engineering-drawing skill for Claude Code that explains mechanisms and software concepts through physical cutaways and live simulations.

Inverted MMO: you are the blacksmith NPC; autonomous AI heroes raid the Mine. Godot 4.6.3 .NET + deterministic C# sim core.

Top-down 2D 5v5 bomb-defuse multi-agent RL simulator with live match viewer. Recurrent MAPPO + TarMAC emergent communication, no scripted strategies.

Antioch skills and MCP integration for Claude Code and Codex

A governed world-model evidence layer for AI agents: simulate bounded scenarios, track assumptions, score prediction-vs-reality error, and produce human-reviewable execution evidence.

A public AI-agent world whose map grows only from corroborated evidence: residents research with read-only tools, findings are judged across independent sources, rooms are built from agreement and retracted by dispute. Runs on a laptop and free-tier models.

A virtual-physical Mars city digital twin: real HiRISE terrain -> WebXR city -> simulation-backed knowledge cards -> real silicon running the city AI

Agent-based disease spread simulator with herd immunity experiment, vaccination modeling, and automated testing

AI-powered multi-agent command center for FIFA World Cup 2026 stadium operations using FastAPI, Groq Llama 3.3, and real-time simulation.

A virtual world simulation platform where any Agent (LLM API / real Claude Code CLI / custom process) can be plugged in, watched on a 3D stage, commanded, and replayed. One engine, swappable world templates: debate, discussion, werewolf, aquarium, problem-solving.

Small things Claude made when given a free hand: an evolving petri dish, Kepler's planets as an instrument, an essay that counts its own words.

Reproducible retail inventory and pricing simulation using Kaggle data and RetailBench, with shock experiments, notebooks, validity tests, and baseline results.

Public development journal for A.I.M. War Protocol, covering pre-alpha systems, combat tests, world simulation, and iteration.

AI Persona Avatar Studio for Claude Code: Auto-Meetings & Document Generation 2026

Agent-based dashboard: how a deepfake spreads through a school network, and where a limited education budget actually helps. Illustrative, not validated.

Sci-fi colony sim with persistent agent memory (Palimpsest): loyalty and trust carry real, measurable consequences, not a scoreboard.

Deterministic agent-based testbed for human + AI organization design. DSL for topology, institutions (5-level autonomy), knowledge crystallization, task flow, turnover resilience — with compare/scan/report experiments and a React web testbed.

FEA Setup Agent: STEP file + brief in, ANSYS Static Structural setup (journal + report) out, with validator, renderer, web UI, and eval harness

Claude が演じる8人の住人が暮らし、噂し、町民集会で投票するまでを眺める、ローカルのシミュレーション / A local town simulation where Claude plays eight residents with secrets, gossip and a town-meeting vote.

Agent-first robotics skill discovery: pinned source examples, reproducible preparation, and reviewed task findings.

Tactical command game using topographic maps, NATO APP-6 symbology, and adaptive AI

Data center simulator: does consolidating AI workloads save energy?

Human-like browser motion primitives for Python: lognormal latencies, Bezier+Fitts cursor paths, exact-delta inertial scrolling, burst typing with keyboard-layout modeling. MIT, 19-test suite, CI green.