Train, inspect, edit, automate, and export 3D Gaussian Splatting scenes from a single native application.

HTRflow is the underlying engine for our HTR-pipeline

Browser-based OCR/HTR workbench with LLM-powered transcription, hybrid validation, and illuminated manuscript description. Built for digital humanists -- no server required.

coOCR/HTR is a browser-based experimentation environment for integrating domain experts into OCR and HTR pipelines. It combines vision-language models with hybrid validation (deterministic rules + …

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

The open source coding agent.

Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.

Get your documents ready for gen AI

Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.

Contexts Optical Compression

Automated containerized pipline for Gaussian Splatting

[SIGGRAPH'25] Official implementation for the paper "Deformable Beta Splatting"

In-depth tutorials on LLMs, RAGs and real-world AI agent applications.

Ray tracing and hybrid rasterization of Gaussian particles

GraphER: A Structure-aware Text-to-Graph Model for Entity and Relation Extraction

Convert PDF to markdown + JSON quickly with high accuracy

OCR, layout analysis, reading order, table recognition in 90+ languages

Generalist and Lightweight Model for Named Entity Recognition (Extract any entity types from texts)

Toolbox designed to facilitate interaction with Zenodo using Python, including various functionalities for multimodal data processing operations.

Reichsanzeiger-NLP: NER/NEL corpus for the German historical newspaper "Deutscher Reichsanzeiger und Preußischer Staatsanzeiger" (1819–1939)

Detect and Parse Historic Dates in R

A parser to convert textual dates into EDTF

Natural language date and interval parsing for cultural heritage applications.

Using LLMs for Named Entity Recognition (NER)

The official repository for paper "LLMaAA: Making Large Language Models as Active Annotators"

This repo contains files downloaded from Transkribus with corresponding suggested OCR improvements (performed using ChatGPT AI).