Fully open-source command-line AI assistant inspired by OpenAI Codex, supporting local language models.

📜 Dagster datacontract extension for loading asset metadata and context information from data contracts.

Official inference framework for 1-bit LLMs

A python library to define and validate data types in Docling.

𝗗𝗮𝘁𝗮, 𝗔𝗻𝗮𝗹𝘆𝘁𝗶𝗰𝘀 & 𝗔𝗜. Modern alternative to Snowflake. Cost-effective and simple for massive-scale analytics. https://databend.com

A collection of RBIR projects and posts for anyone interested in joining this journey.

Gumloop Unified Model Context Protocol (guMCP)

A Python toolkit for fine-tuning Geospatial Foundation Models (GFMs).

An implementation of Pregel framework and graph algorithms on top of it with Ibis project DataFrames.

Web UI for Unternehmensdaten gemäß Anhang 5. der DV (EU) 2023/138 der EC vom 21. Dezember 2022 zur Festlegung bestimmter hochwertiger Datensätze und der Modalitäten ihrer Veröffentlichung und Weite…

A sample dataset for data vault and testing data vault based data warehouse automation.

Playwright MCP server

DuckDB-powered Postgres for high performance apps & analytics.

🪄 Create rich visualizations with AI

deferred computational framework for multi-engine pipelines

Robust Molecular Structure Recognition with Image-to-Graph Generation

DuckDB for streaming data

Explainer for black box models that predict molecule properties

Modern, fast, document parser written in 🦀

Graph neural networks for molecular machine learning. Implemented and compatible with TensorFlow and Keras.

MolGrapher: Graph-based Visual Recognition of Chemical Structures

DeepEP: an efficient expert-parallel communication library

A lightweight data processing framework built on DuckDB and 3FS.

DocLayout-YOLO: Enhancing Document Layout Analysis through Diverse Synthetic Data and Global-to-Local Adaptive Perception

intuitive and declarative web framework for Rust

FlashMLA: Efficient MLA decoding kernels