1. Farm Management & Precision Agriculture
Farm Management Information Systems (FMIS)
farmOS:
Modular farm management platform (fields, livestock, equipment, workers)
Drupal-based, extensible architecture
Mobile app, map-based interface
AgroSense: Czech precision agriculture platform
OpenFarm: Knowledge database for growing plants (like Wikipedia for farming)
CropTracker: Farm management for specialty crops
Decision Support Systems
DSSATÂ (Decision Support System for Agrotechnology Transfer):
Crop simulation models for 40+ crops
Yield prediction, climate impact analysis
APSIMÂ (Agricultural Production Systems Simulator):
Modeling agricultural systems
Widely used in research and farming
AquaCrop: FAO’s crop water productivity model
2. IoT & Sensor Networks
Hardware Platforms
Arduino/Raspberry Pi: Foundation for custom agricultural sensors
ESP32/ESP8266: Low-cost WiFi-enabled microcontrollers
Mycodo: Environmental monitoring and regulation system
Sensor Networks & Data Collection
OpenMote: Open hardware for wireless sensor networks
The Things Network: LoRaWAN network server
Node-RED: Flow-based programming for IoT (connects sensors, APIs, databases)
Grafana: Visualization for sensor data
Specific Monitoring Solutions
OpenSprinkler: Open source sprinkler/irrigation controller
ChickenMonitor: Poultry house monitoring
OpenGreenhouse: Greenhouse automation system
3. Drone & Satellite Imagery
Drone Software
OpenDroneMap: Processes drone imagery into maps, 3D models
Dronecode/PX4: Autopilot software for agricultural drones
QGroundControl: Ground control station software
WebODM: User-friendly interface for OpenDroneMap
Satellite Data Processing
QGISÂ with agriculture plugins:
Semi-Automatic Classification Plugin
Orfeo Toolbox
Sen2Agri: System for agricultural monitoring with Sentinel-2
Google Earth Engine: Not fully open but free for research/analysis
4. Data Management & Analysis
Geospatial Analysis
QGIS: Leading open source GIS with agricultural extensions
GRASS GIS: Advanced geospatial analysis
WhiteboxTools: Geospatial analysis library
RÂ with agricultural packages:
agricolae,Âaqp (soil science),Âphenology
Statistical Analysis & Modeling
RStudio/RShiny: For creating agricultural dashboards
Python libraries:
scikit-learn,ÂTensorFlow for crop yield predictionPandas,ÂNumPy for data processingGeoPandas for spatial data
Jupyter Notebooks: For reproducible research
5. Livestock Management
Monitoring & Management
Herdly: Cattle herd management
Open Livestock Tracker: Animal tracking and health monitoring
MilkMaid: Dairy herd management
Genetics & Breeding
BLUPF90: Breeding value estimation
QU-GENE: Simulation platform for quantitative genetics
R/gaston: Genetic data analysis in R
6. Supply Chain & Marketplace
Traceability Systems
Open Food Network: Connects producers and consumers
Farm to Fork: Supply chain traceability
Provenance: Blockchain-based traceability (open components)
Marketplace Platforms
OpenOlitor: Community-supported agriculture (CSA) management
FoodCoop: Online ordering for food cooperatives
Biodiversity Inventory: For seed sharing networks
7. Climate & Environmental Tools
Weather & Climate
pyMETRIC: Mapping evapotranspiration with Landsat
SPUDS: Software for Processing UAV Data Sets
AgroClimate: Tools for climate risk management
Water Management
SWATÂ (Soil & Water Assessment Tool):
River basin-scale model for water quality
MODFLOW: Groundwater flow modeling
CUAHSI-HIS: Hydrologic information system
Soil Health
Soil Health Assessment Tool (open research implementations)
ROSETTA: Predicts soil hydraulic properties
Open Soil Spectral Library: Global soil spectroscopy database
8. Robotics & Automation
Agricultural Robots
ROSÂ (Robot Operating System): Standard for agricultural robotics
FarmBot: Open source CNC farming machine
Tractor automation projects:
Open Source Tractor: Various initiatives for autonomous tractors
Weed detection/removal robots: Multiple academic/open projects
Harvesting Automation
Open harvesting robotics: Various research projects
Bee hive monitoring: OpenApis and similar projects
9. Knowledge Sharing & Education
Agricultural Knowledge Bases
Wikipedia/OpenStreetMap: For agricultural knowledge
PlantVillage: AI-driven plant disease diagnosis
Open Tree of Life: Taxonomic framework
Learning Platforms
Moodle with agricultural courses
Open edXÂ agriculture courses
Akvo tools for agricultural training
10. Specialized Crops & Systems
Vitaculture (Wine)
VitiCanopy: Vineyard canopy analysis
OpenVineyards: Vineyard management
Aquaculture
FishID: Fish species identification
Aquaculture management systems: Various open projects
Permaculture & Agroforestry
Permaculture design tools: Digital implementations of permaculture principles
Agroforestry design tools: Spatial planning for tree-crop systems
11. Mobile Applications
Field Data Collection
ODKÂ (Open Data Kit): Customizable data collection forms
Kobo Toolbox: Field data collection
Epicollect5: Mobile/web data collection
Specialized Apps
Pest identification apps: Various open source implementations
Soil sampling apps: GPS-guided soil sampling
Scouting apps: For crop assessment
12. Government & Research Initiatives
National/International Projects
FAO’s Open Source Initiatives:
WaPOR: Water productivity data
Hand-in-Hand Geospatial Platform
USAID’s Digital Development tools
EU’s CAP (Common Agricultural Policy) monitoring tools
Open Data Initiatives
Global Open Data for Agriculture & Nutrition (GODAN)
Agricultural Model Intercomparison and Improvement Project (AgMIP)
Open Soil Data initiatives
13. Blockchain & Smart Contracts
Traceability & Payments
Hyperledger implementations for supply chains
Ethereum smart contracts for:
Crop insurance
Fair trade verification
Land registry
Open Source Oracle Networks: For connecting real-world data to blockchains
14. Development Frameworks & APIs
Agricultural APIs
Open APIs from agricultural services
FIWAREÂ for smart agriculture contexts
SensorThings APIÂ for IoT in agriculture
Integration Platforms
Apache Kafka: For data streaming from sensors
PostgreSQL/PostGIS: For spatial agricultural data
InfluxDB: Time-series data from sensors
15. Notable Projects & Case Studies
Impactful Implementations
farmOS in Vermont USA: Used by small to medium farms
Digital Green: Video-based agricultural extension (open components)
PlantVillage in Kenya: AI-assisted disease diagnosis
OpenTEAMÂ (Open Technology Ecosystem for Agricultural Management): Collaborative project
Innovative Research Projects
PhenoApps: Mobile phenotyping
CyVerse: Cyberinfrastructure for life sciences (includes agriculture)
TERRA-REF: High-resolution agricultural field data
1. Generative AI & Digital Agronomy
These tools use Large Language Models (LLMs) and foundation models to act as "24/7 agronomists," synthesizing complex farm data into plain-language advice.
Jeevn AI (by Farmonaut):
Function: An advanced AI advisory system.
Capability: It ingests satellite data, local weather sensors, and soil reports to deliver real-time, plain-language farming advice. Instead of just showing a graph of moisture levels, it tells the farmer: "Irrigate Field B tomorrow at 4 PM to prevent heat stress."
Cropway GenAI:
Function: A "system connector" for agribusiness.
Capability: It translates unstructured data—like machine logs, handwritten field notes, and drone images—into structured reports. It connects the entire supply chain, predicting market demand and suggesting optimal harvest windows to maximize profit.
Microsoft FarmVibes.AI:
Function: An open-source suite of AI algorithms running on Microsoft Azure.
Capability: It enables "precision agriculture" for developers. It includes tools to predict yield, detect pests from drone imagery, and even determine the best mix of fertilizers to reduce carbon footprint while maintaining output.
2. Autonomous Robotics (Field Operations)
Hardware platforms that use computer vision (Edge AI) to perform physical tasks, addressing the global labor shortage.
Carbon Robotics LaserWeeder:
Function: Chemical-free weed control.
Capability: It uses high-speed cameras and AI to identify weeds among crops in milliseconds, then zaps them with thermal lasers. In 2025, it has expanded its training data to handle dozens of crop types (onions, carrots, leafy greens) with sub-millimeter accuracy.
AgBot (by AgXeed):
Function: Autonomous tractor ecosystem.
Capability: A driverless vehicle that can change its own tools. It creates a digital "path plan" of the field and uses AI to detect obstacles and monitor implement performance (e.g., if a plow is stuck) without an operator in the cab.
Ecorobotix ARA:
Function: Ultra-precision smart sprayer.
Capability: Instead of spraying an entire field, its cameras identify individual plants. It sprays herbicide only on the weed and fertilizer only on the crop, reducing chemical use by up to 95%.
3. Livestock Monitoring & Animal Health
AI tools that treat every animal as an individual data point, moving from "herd management" to "precision livestock farming."
CattleEye:
Function: Camera-based autonomous monitoring (no wearable collars needed).
Capability: It uses security cameras overhead to monitor cow movement. The AI analyzes the gait (walking pattern) of each cow to detect "lameness" or injury weeks before a human would notice, allowing for early treatment.
AIHERD:
Function: Behavioral analysis for dairy cows.
Capability: It tracks vital signs and social behavior to detect health issues like mastitis or estrus (heat). It alerts farmers to specific anomalies, such as a cow spending too much time lying down or not eating enough.
701x:
Function: "Smart Ear Tags" for cattle.
Capability: GPS-enabled tags that function like a Fitbit for cows. They use AI to track grazing patterns and location, helping ranchers manage rotational grazing effectively and prevent theft.
4. Indoor Farming & Controlled Environment (CEA)
Tools for vertical farms and greenhouses where AI manages the climate.
IGS (Intelligent Growth Solutions) AI:
Function: "Total Control" environment management.
Capability: Uses AI to manipulate weather. It dynamically adjusts LED lighting spectrum, humidity, and airflow to speed up or slow down plant growth based on when the market needs the produce (e.g., slowing down growth if prices are low).
Koidra:
Function: Autonomous greenhouse control.
Capability: It uses "Physics-Informed AI" (similar to aerospace tools) to make decisions. It outperforms human growers by continuously tweaking setpoints (temperature, CO2) to maximize yield per kilowatt of energy used.
Summary of Key Trends
| Trend | Description | Key Benefit |
| Generative Biology | AI designing new seed traits or growing recipes. | Higher resilience to climate change. |
| See & Spray | Robots that spray only weeds, not soil. | Massive reduction in chemical costs (up to 95%). |
| Edge AI | Data processing happens on the tractor, not in the cloud. | Works in rural areas with poor internet. |
| Gamification | Interfaces that look like video games (e.g., Farm-ng). | Easier for younger, non-expert workers to operate. |
1. Geospatial & Farm Management (Remote Sensing)
These tools allow developers to build "digital twins" of farms using free satellite data, offering an alternative to expensive commercial platforms.
Microsoft FarmVibes.AI:
What it is: An open-source suite of algorithms running on Azure (code available on GitHub).
Capability: It democratizes "data fusion." It automatically combines optical satellite imagery (Sentinel-2) with radar data (Sentinel-1) and weather forecasts.
Use Case: Developers use it to build apps that can "see" through clouds to monitor crop growth or predict soil carbon sequestration levels without needing physical sensors in the ground.
NASA Harvest "Prithvi" (Ag Fine-tunes):
What it is: While "Prithvi" is a general Earth foundation model, 2024–2025 saw the release of specific fine-tuned versions for agriculture.
Capability: It serves as a pre-trained "brain" for crop mapping. Users can take this open model and train it on a tiny dataset (e.g., just 100 labeled images of local cassava fields) to create a highly accurate crop classifier for their specific region.
OpenMapFlow:
What it is: A Python library often used in conjunction with NASA Harvest data.
Capability: It simplifies the creation of crop maps. It standardizes the chaotic workflow of downloading satellite data, labeling it, and training a model, allowing a single developer to generate a country-scale crop map.
2. Plant Phenotyping & Computer Vision
Tools used by researchers and breeders to measure plant traits (phenotypes) automatically, speeding up the development of climate-resilient crops.
PlantCV v4 (2025 Updates):
What it is: The standard open-source image analysis package for plant science.
Development: Recent updates have expanded beyond standard cameras to support hyperspectral and thermal image analysis.
Use Case: Instead of manually measuring leaf width, a researcher can run a PlantCV script to process thousands of thermal drone images, automatically identifying which plants in a test plot are genetically resistant to heat stress.
AgML:
What it is: A specialized framework (similar to PyTorch) but built specifically for agriculture.
Capability: It solves the "data problem" in ag AI. It provides standardized "data loaders" for common agricultural tasks (like grape bunch detection or weed segmentation). It allows developers to benchmark their new AI models against standard baselines without writing custom code to handle messy agricultural image formats.
3. Robotics & Autonomy (Field Operations)
Software stacks that allow generic hardware (like a modified wheelchair or a custom frame) to act as an intelligent farm robot.
ROS 2 Agriculture (ROS-Ag):
What it is: A community-driven collection of packages for the Robot Operating System (ROS 2).
Development: In 2025, the focus has shifted to navigation in feature-poor environments. New open-source nodes allow robots to navigate down crop rows using only Lidar or visual SLAM (cameras), removing the need for expensive RTK-GPS subscriptions.
OpenCV AI Kit (OAK) for Weed Detection:
What it is: While OAK is hardware, the open-source software ecosystem around it has exploded.
Capability: Developers share pre-trained "blob" files (AI models) that run directly on OAK cameras. A popular use case is "Green-on-Green" detection—identifying a green weed growing inside a green crop (like clover in wheat) and triggering a relay to spray it.
4. Community Datasets (The "Fuel" for Open AI)
AI tools are useless without data. These open initiatives provide the training ground for new algorithms.
WeedCOCO / CropDeep: Open-source datasets enabling the training of "Spot Spraying" robots.
Global Wheat Head Detection (GWHD): A massive collaborative dataset used to train AI to count wheat heads (yield estimation) from simple smartphone photos.
Summary of Open Source Stacks
| If you want to build... | Use this Open Source stack: |
| A Weed-Killing Robot | ROS 2 (Navigation) + OAK/OpenCV (Vision) + AgML (Training Data) |
| A Yield Prediction App | FarmVibes.AI (Data Fusion) + Prithvi (Model Base) |
| A Plant Breeding Tool | PlantCV (Analysis) + Python |
