CommunityJev Demos & Experiments
Field Advisory
An agricultural advisory demo that turns sensor readings, a forecast, and a crop stage into a next-action choice plus an urgency score, routing marginal readings to an agronomist instead of triggering an application.
- Published by
- Community
- Author
- Agriwise
- Last verified
- Oct 2026
- Languages
- Python
- Capabilities
- Open sourceRequires API key
Highlights
- Picks one next action from a short agronomic list and scores how urgent it is.
- Compares urgency against the forecast's own confidence so marginal fields go to a person.
- Ships a replay of a full season of readings for tuning without live sensors.
- Keeps the recommendation advisory, with a licensed agronomist as the sign-off.
Watch out
A triage and drafting aid, not an agronomic authority; the README requires a licensed sign-off before any chemical application and treats the recommendation as a starting point.
Questions about this entry
Short answers drawn from the linked project or page.
Given field sensor readings, a weather forecast, and a crop stage, it picks the next action from a short agronomic list and scores how urgent it is, so a grower gets one recommendation with a probability behind it.
The action space is small and the inputs are structured and noisy, which is a bounded choice rather than an open-ended question. The README frames it as triage, with an agronomist as the review path.
The forecast comes in with its own confidence, and the urgency Score is compared against that, so a marginal reading under a low-confidence forecast routes to a person rather than triggering a spray.
No. It prioritizes which fields need attention first and drafts the recommendation, and the README is explicit that a licensed agronomist signs off before any chemical application.
The evaluator ships with a replay of a season of readings, so the decision logic can be tested without sensors. Live use calls the hosted API, and a local model can be swapped behind the same base URL.
Python 3.11 or newer, a TypeSafe key, and sensor readings in a documented CSV shape. The repo includes the season replay and a notebook for threshold tuning.
Reactions & coverage
Posts, threads, and videos about this entry from around the web.
X: Field Advisory sends marginal readings to an agronomist instead of a spray.
This post couldn't be loaded here — read it on X.https://x.com/agriwisehq/status/2781000000000000003Hacker News: Show HN: Ad Spend Guard gates budget before the auction, not the creative after.
Show HN: Gating ad budget with a decision modelRead the thread on Hacker NewsMore Jev resources like this
36GitHub stars
A Clash Royale bot that turns a phone screenshot into JSON once a second and asks Jev for a strategy, a card, and a square.
Jev Demos & Experiments#community#python#gaming
Community
bytelabs-oss/clash-jevPython
bytelabs-oss/clash-jevPython29.3kGitHub stars
The Cua computer-use platform documents a jev-use recipe where TypeSafe Jev picks bounded action IDs and Cua Driver executes clicks and fills in the browser.
Jev Demos & Experiments#community#browser#computer-use
Community
trycua/cuaRust
trycua/cuaRust97GitHub stars
A Playwright-based CodexQA skill where Jev chooses indexed controls on a page-built index while the browser executes the action.
Jev Demos & Experiments#community#browser#playwright
Community
openqa-cn/jev-browserTypeScript
openqa-cn/jev-browserTypeScript4GitHub stars
A Craftax (Crafter) survival harness where deterministic code lists every feasible action with its facts and Jev picks one Choice per step, optionally guided by an LLM-written objective and standing rules; three-seed ablations are included.
Jev Demos & Experiments#community#craftax#games
Community
mansicer/jev-playsPython
mansicer/jev-playsPythonA travel rebooking demo that classifies a trip disruption, checks itinerary feasibility, and ranks concrete rebooking options against a traveler's ordered preferences, returning ordered choices with probabilities.
Jev Demos & Experiments#community#typescript#travel
Community
306GitHub stars
Local macOS computer-use automation on Apple silicon using on-device laya typed decisions and CUA-S1-FORMS for filling, via the Accessibility API.
Jev Demos & Experiments#community#browser#local
Community
FluidInference/FluidUseSwift
FluidInference/FluidUseSwiftFrom the Jev guides
Original write-ups on what this entry is for.
A game tick is a state plus a legal action list. How Clash Royale, Minecraft, and the earlier Mario, Pokémon, StarCraft, and drone loops ask Jev one step at a time.
Jev Demos & Experiments#gaming#agents#control
Read article
From the Jev community
Posts from builders shipping with Jev right now.