R package for ggml tensor library (CPU backend)

Provides R bindings to 'llama.cpp' for running large language models (LLMs) locally

A coding agent optimized to smaller LLMs

AWS Entwine Point Tiles USGS LiDAR Public Dataset GitHub repo

A thin protective layer for Claude Code

Disruptive algorithms for Digital Soil Mapping — six research pillars (Causal AI, Physics-Informed ML, 4D Pedometry, Foundation Models, Autonomous Active Learning, Quantum ML)

Automated soil profile classification per WRB 2022 (4th ed.) and SiBCS 5 -- deterministic taxonomic key, VLM extraction (ellmer), SoilGrids prior, OSSL spectroscopy bridge

Physics-informed CNN1D for soil water retention curves (Norouzi et al. 2025)

Adaptive Precision for EXpert Models: MoE-aware mixed-precision quantization

LocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.

The agent that grows with you

Multi-model machine-learning metasystem for next-gen water supply forecasting

On-device AI across mobile, embedded and edge for PyTorch

Open GenAI Stack

Agentic components of the Llama Stack APIs

Tensor library for machine learning

GitNexus: The Zero-Server Code Intelligence Engine - GitNexus is a client-side knowledge graph creator that runs entirely in your browser. Drop in a GitHub repo or ZIP file, and get an interactive …

A fast, lightweight text editor for Markdown, JSON, YAML, and TOML files. Built with Rust and egui for a native, responsive experience.

Flash OS images to SD cards & USB drives, safely and easily.

An tidy interface to large language model APIs for R

Web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss locally.

Sandboxed Ollama deployment using Docker and Nginx. Runs Ollama models in an isolated network with no internet access, while a separate updater downloads models securely. Includes GPU support, reve…

Shared Memory for R Objects

An experiment in open source at the Department of Defense.

🦞 Stop reading remote sensing papaers manually — RS-PaperClaw auto-tracks, auto-analyzes, and auto-digests remote sensing papers.

Implementation of RLNs, as described in https://arxiv.org/abs/1805.06440

Serverless high-resolution aerial imagery map tiles from Cloud-Optimized GeoTIFFs for the U.S.

Additional documentation for publicly available datasets on AWS

Quickly explore metadata about a FlatGeobuf file