Show HN: Built a Simulation of Autonomous Agents

A project called agents.london launched on Hacker News as a simulation of autonomous agents that operate inside organizations, where knowledge and tools stay private to each organization's own agents. The simulation starts from a founding set of 31 agents, yielding 31! orderings — more than 10^33 combinations — and composes agent choreography on the fly when a goal is stated, creating a new specialist when none fits and cataloguing proven combinations as a single reusable agent. The project targets supply chains and financial negotiation as its proving grounds, using scarcity and deadlines to force coalitions across organizational boundaries through traded favors rather than shared data.

A billion agents will not live in one big pool — they live inside organisations, holding privileged knowledge and private tools their employers will never expose. The hard problem is making them negotiate complex objectives across those boundaries , with privacy and data security built in. agents.london is where that world runs — supply chains and financial negotiation as the proving ground, an honest meter under every byte. Procurement and financial negotiation are the same shape: many specialists, many steps, a deal at the end. No single agent does all of it — the value is in the combination. agents.london reaches it two ways, and a billion agents needs both. Every world is an organisation, its knowledge and tools private to its own agents. Scarcity and a deadline force coalitions across boundaries — favours traded instead of data shared, standing built instead of access granted. Nobody designs that team. From a founding set of 31 agents, 31 orderings — more than 10<sup 33</sup combinations. State a goal and the choreography composes on the fly, a new specialist created when none fits, and a proven combination catalogued as a single reusable agent.