TomatoFarm

A real indoor tomato farm where code, sensors and AI help six plants grow — safely.

Sense, reason, validate, act.

Sensors (live readings) → Context (3-layer memory) → Council (4 LLMs) → Safety Gate (Pre-publish check) → Hardware (via MQTT)

Before the Council even speaks, the Context Builder assembles a full snapshot: live sensor readings with 6h trends, plant lifecycle stage, current safety state per pod, recent council decisions, and three layers of farm-specific memory: established rules (high-confidence priors auto-promoted from observation), operational matrix (what works in conditions like now), and weekly drift (what's different about this week). Only then do the LLMs enter the dialogue.

The pre-trained LLMs already know more about tomatoes than any external knowledge base would add — we feed them this farm's evidence instead. No RAG, no vector store; just memory that grows with experience.

Ten modules, one farm

Watering, lighting, airflow, climate, vision — every function is its own module with its own hardware and its own microcontroller. They all talk over MQTT to the Raspberry Pi gateway that holds the bus together.