F.A.R.M.E.R.

Name: F.A.R.M.E.R.
Author: nameershah

Multi-agent AI routing smallholder farmers' crop, weather and market queries, escalating uncertain cases to human extension officers.

By nameershahAdded 2 months ago · 1 review

Visit website

Upvote10

Source code

Why it exists

F.A.R.M.E.R. (Futuristic Agriculture & Resource Management Ecosystem Router) is a multi-agent AI system that routes smallholder farmers' queries, text and crop images, to the right specialist agent and escalates uncertain or high-severity cases to a human extension officer.

Smallholder farmers in rural Khyber Pakhtunkhwa have limited access to agricultural extension officers, which delays crop disease response and reduces yields. The system mirrors a routing problem the author documented in his own published research on AI routing for Lady Health Workers in the same region.

A deterministic router sends image queries to a Gemini-powered diagnosis agent, weather and market questions to an MCP-backed data agent, and everything else to an advisory agent. A confidence gate escalates any low-confidence or high-severity case to a human. The router and gate use no LLM calls, so routing decisions stay inspectable and stable across model versions.

Built for the Kaggle × Google AI Agents Intensive Vibe Coding Capstone, Agents for Good track.

1 Review

Community feedback

teo_buildsMember review2 months ago

I read the repo before trying the demo, which is the right order for this one. Routing is deterministic, a keyword and image check in router.ts rather than another LLM deciding where things go, and I respect that choice. Image queries land on a Gemini 2.5 Flash vision diagnosis agent, weather and market questions ride an MCP client into an in-process MCP server, everything else goes to a Groq LLaMA advisory agent, and a confidence gate with a plain threshold decides when a human extension officer needs to see the case. The query log to MongoDB is non-blocking, so logging trouble cannot take the answer path down. The part that stays with me is the provenance: the author published research on this same routing failure for Lady Health Workers in Khyber Pakhtunkhwa, then rebuilt the pattern for crop disease. Built for the Kaggle Agents for Good capstone. The mermaid diagram names the actual source files, which tells you the architecture came first, not the diagram.