simulation

Understudy is a scenario-driven testing framework for AI agents. It simulates multi-turn users, records traces of messages and tool calls, and evaluates agent behavior with deterministic checks, optional LLM judges, and reports.

An open robot football league where frontier AI models and open-source club code manage simulated Unitree G1 humanoids in daily matches, with live streams, match logs, and a public engine for teams to join.

Yogen is a self-hosted AI swarm that uses 500 agents to debate an idea and produce a verdict and written report. It targets decision support for startup ideas, product changes, and other uncertain choices, with both a hosted demo and local setup using an Anthropic API key.

A ProtoLink example that stages autonomous agents in a fictional liability tribunal to study how agent-to-agent communication changes decisions, with replayable traces and HTML reports.

A browser strategy game where you run a frontier AI lab, manage compute markets and research paths, and race rival labs to build AGI. It includes weekly Easy and Hard challenges plus a replay-verified leaderboard.

Marker is an AI testing and verification platform for voice agents, with a focus on simulation, transcripts, judgments, and versioned evidence across the workflow.

A Python CLI and research toolkit for simulating AI training math before model training. It estimates memory, training time, token budget, config risks, benchmark speed, and reliability, with optional native Rust and C backends.

Agora-1 is a multi-agent world model from Odyssey that simulates shared real-time environments for up to four participants, human or AI, with a focus on gaming, robotics, reinforcement learning, and foundation model research.

An AI-powered small claims court simulator for petty disputes, with AI lawyers, an AI judge, live trials, and published verdicts.

A bilingual satirical idle simulation where you run an AI startup from toy classifiers to near-AGI, managing data, compute, launches, crises, and rivals.

An open-source simulator that studies how GPT inference behaves under space radiation and cosmic-ray fault conditions, with CLI runs, comparisons, and self-contained HTML reports.

An interactive simulation about how inference providers ration access to stronger LLMs when demand spikes. Users can compare the default industry rule with their own policy and explore who gets the strong model.

A blog post about Idle Frontier, a clicker game about building a frontier language model in 1,000 days, and the author’s experience making it with Claude, Godot, and Aseprite.

A GitHub repository presenting VSE Engine (Velocity & Structure Encoding), a prototype for computing over transmission using pulse-position and duration modulation ideas. The README describes a byte-splitting pipeline, time-slot mapping, and decode/resynthesis flow, with supporting source files in the repo.