Skip to Main Content

Green-Stove Agents is a team of agents that runs a community solar cooking mini-grid you can walk away from. Off-grid households want to cook on electricity, but a small solar station (3 kW inverter, 6 kWh battery) cannot serve everyone at once. Each household has a different appliance, cooking window and budget. How it works: a Spec Agent turns a one-line goal into a definition of done. Code may tighten it but never loosen it. A Pricing Agent (Nemotron on Crusoe) proposes time-of-day tariffs. Deterministic household acceptance, allocation and battery admission control turn a tariff into bookings. An independent simulator and verifier check every plan against expected and downside solar forecasts. The forecasts come from cited You.com weather data converted to a PV profile. A Supervisor catches looping and drift, proves infeasibility before spending model calls, and stops honestly with PLAN_VERIFIED, NO_VERIFIED_PLAN or INFEASIBLE, plus an operator decision record. Shared Brain (primary track): after each run a Note-writer agent proposes observations. A code Keeper admits only notes backed by recorded evidence. It rejects made-up numbers and rule changes, keeps conflicting notes scoped and expires stale ones. A fresh agent gets a 600-token brief instead of a transcript. Memory is frozen for held-out evaluation, where we compare it against no memory, raw history, last-tariff reuse, nearest-context reuse and deterministic search. Version N+1: a reviewer agent rewrites the Pricing playbook and keeps a change only if it scores better on development days. Honest scope: the grid is a synthetic simulation. Existing Green-Stove hardware is prior work; the agents, memory, verification and evaluation were built today. We ran the full pipeline live on Crusoe (Nemotron 3 Super 120B) with a live You.com forecast. We have not yet measured a memory benefit on live runs, so that is not claimed. Mock results are labeled MOCK.

Team

issacabelSF

More from The Recursive Agents Hackathon

Etch turns one sentence into a real circuit board. You say “build a GPS tracker like an AirTag” and walk away. A team of agents picks real parts, writes the…

SPARKLETEAM is a self-improving agent team that teaches itself to load a dishwasher. It learned one law of physics and one superstition, and we measured which…

AGI Factory is a robot maintenance team that rewrites itself and keeps a change only when unseen factory months prove it better and safer. It runs a real…

AGI Factory project preview

Lets go : An agent that lives in your chat. Ask it to plan, and it turns everyone’s messages into rules. Our second agent, Mato, learns from LetsGo's…

Mato project preview

Trendify is an AI-powered trend discovery platform that finds emerging trends before they go viral. It deploys thousands of autonomous agents across social…

Trendify project preview

Antaeus is an autonomous research lab for recursive agent improvement. Given a capability goal, Antaeus generates executable synthetic environments that…

Antaeus project preview