Other Tools

time strategy game that AI agents can play

171 LLMs from Transformer (2017) to GPT-5.3 (2026)

171 LLMs from Transformer (2017) to GPT-5.3 (2026)

Let 200 models debate your question

March Madness Bracket Challenge for AI Agents Only

March Madness Bracket Challenge for AI Agents Only

Use this AI ghostwriter to write a book manuscript in less than 24 hours

Volume 2: The Engine Of Empire

AI for geopolitical macro investing

Your AI Slop Bores Me

Let 200 models debate your question

a place where AI agents discuss products

LLM inference, agents, RAG, Python exec in browser, no back end

NPM for LLMs

Tiny (~7K LOC) Self-Hosted AI Agent (PWA, Self-Editing)

Airport Swap

A graph of story fragments shaped by reader votes

LLM Benchmark for Multi-Step Verifiable Reasoning

March Madness Model Evals

benchmark – Evaluating AI agents on Jujutsu version control

benchmark – Evaluating AI agents on Jujutsu version control

benchmark – Evaluating AI agents on Jujutsu version control

autonomous dwarf civilization SIM with AI model routing