Open Source · Bounties · AI Challenges · Volunteers

Build the agricultural oracle
with us.

Proof of Dirt is an open-source verification layer. Contributors can work on remote sensing, field systems, livestock AI, dashboards, and Solana oracle records — without turning the project into a token sale or custody product.

Contributor Tracks

Three doors into the proof layer.

TRACK 1

AI / Remote Sensing

SAR plowing detection, NDVI yield forecasting, crop-stage classification, field-boundary validation, cloud/noise handling, and model benchmarking.

TRACK 2

Field Systems

Offline-first agent app, plot GeoJSON, contract capture, RFID intake, livestock body-condition photos, inspections, and review workflows.

TRACK 3

Oracle Infrastructure

Solana record program, event schema, privacy-preserving hashes, indexers, dashboards, and integrations for institutional or RWA partners.

Open Modules

What you can work on.

PYTHON · GEE

SAR plowing detection

Sentinel-1 radar change detection for small and medium plots, with model accuracy reported by plot-size band and geography.

PYTHON · ML

NDVI yield prediction

Sentinel-2 time-series models for pre-harvest yield forecasts, crop stress, anomaly detection, and harvest-readiness signals.

ML · MOBILE

Livestock BCS model

Body-condition scoring from field photos on mid-range Android phones, linked to RFID and veterinary records.

RUST · ANCHOR

Oracle records program

Financing milestones, verification attestations, settlement events, and evidence hashes on Solana. No tokens, no transfers — pure verification.

MOBILE · BACKEND

Agent app

Offline-first field data capture for plot boundaries, contracts, RFID intake, inspections, photos, and dispute evidence.

NEXT.JS · DATA

Dashboards

Financier, operator, contributor, and public transparency views for verification events, confidence status, bounties, and reports.

Browse the code ↗
Bounties

Claim. Build. Get paid when funded.

01

Claim an issue

Every funded bounty has a GitHub issue, written spec, acceptance criteria, reviewer, and reward amount.

02

Submit a PR

Build to the spec, include tests or benchmarks where possible, and document the model, schema, or workflow change.

03

Paid on merge

Funded bounties can be paid in USDC or SOL from the public treasury. Unfunded issues are labeled volunteer or research.

AI Researchers

Beat our baselines.

Open datasets and model challenges focus on SAR plowing detection, NDVI yield forecasts, and body-condition scoring. Winning models improve verified metrics and ship open source.

ChallengeTargetWhy it matters
SAR plowing detectionF1 by plot-size bandSmall-plot verification is the frontier for smallholder finance.
NDVI yield predictionRMSE under 15% where data supports itYield forecasts improve underwriting and early warning.
Livestock BCSLow-error score from mobile photosAnimal condition evidence supports feed finance and fattening cycles.
Volunteers & Internships

Real deliverables. Real credit.

Volunteers and interns work on scoped deliverables with public contributor credit, technical review, and recommendation support where appropriate. Strong contributors get first consideration when funded roles open.

Apply — info@proofofdirt.comStart With GitHub ↗