A calibration-robust router for multi-model AI.
You have several models, cheap to expensive. Tropos corrects each model's self-reported confidence by an observable track record, then sends each task to the cheapest model that is actually reliable and escalates the rest. The longer it runs, the cheaper and more reliable it gets.
The whole loop step by step, in real code with the real terminal output: define a fleet, route, report outcomes, watch the routing improve.
open the tour →The hypotheses, figures, and results behind the method, including the real-agent pilots and the cost analysis.
view results →The full write-up of the framework, the experiments, and the honest limits, as a PDF.
open PDF →Open source, Apache-2.0. Install it as a Python library or run it as an ACP agent inside your editor.
browse the repo →