Stars
A fast, portable (JS/JVM/native), and robust implementation of LinkML for cross-language data modeling
Repository storing technical specification and documentation for the CDOP schema.
Skills & reviewer agents for AI-first climate science — built and used by a PhD atmospheric scientist
Write OKF markdown, get a queryable knowledge graph for free.
Automated soil profile classification per WRB 2022 (4th ed.) and SiBCS 5 -- deterministic taxonomic key, VLM extraction (ellmer), SoilGrids prior, OSSL spectroscopy bridge
A Python library for extracting structured information from unstructured text using LLMs with precise source grounding and interactive visualization.
Self-contained UV scripts for data & ML tasks — OCR, vision, audio & more — run one in a command, locally or on Hugging Face Jobs. Built for humans and agents.
Academic Research Skills for Claude Code: research → write → review → revise → finalize
SDK for ASTRA — Agentic Schema for Transparent Research Analysis
Agentic layer for ASTRA — dedicated skills, workflow execution, and HPC/container management for reproducible research
A data standards initiative for ocean alkalinity enhancement projects, experiments, and field trails. This repository is a technical complement to the published OAE Data Protocol hosted by Carbon t…
R package to check compliance with a controlled vocabulary
Paperclip — search, read, and analyze 8M+ biomedical papers from the command line
Metadata and website for the Open Bio Ontologies Foundry Ontology Registry
A modular graph-based Retrieval-Augmented Generation (RAG) system
TorchGeo: datasets, samplers, transforms, and pre-trained models for geospatial data
Minimum Information about any (X) Sequence” (MIxS) specification
Analysis-ready Rocker RStudio Server-based Container for the USDA-NRCS-NCSS Kellogg Soil Survey Lab Data Mart 'SQLite' Snapshot
soilDB: Simplified Access to National Cooperative Soil Survey Databases
Linked Data MCP - A Python-based MCP server for QA over W3C semantic web and linked data standard specifications: RDF, RDFS, SPARQL, OWL, SHACL and more
Duckdb-based MCP server for datasets
Interactive wildfire visualization with DuckDB-WASM, Mosaic, and GeoArrow - all processing in-browser