The Oxford Common File Layout (OCFL) specifications and website

E-ARK Python Information Package validation library

signature-based file format identification

A tool (and pre-commit hook) to automatically upgrade syntax for newer versions of the language.

Gorilla: Training and Evaluating LLMs for Function Calls (Tool Calls)

Automatically mock your HTTP interactions to simplify and speed up testing

FIDO signature update REST services

Format Identification for Digital Objects (FIDO) is a Python command-line tool to identify the file formats of digital objects. It is designed for simple integration into automated work-flows.

UniTable: Towards a Unified Table Foundation Model

Improved file parsing for LLM’s

Dataset and Code for our ACL 2024 paper: "Multimodal Table Understanding". We propose the first large-scale Multimodal IFT and Pre-Train Dataset for table understanding and develop a generalist tab…

structured outputs for llms

Finetune Llama 4, DeepSeek-R1, Gemma 3 & Reasoning LLMs 2x faster with 70% less memory! 🦥

update your ollama models to the latest

Axate VOD Demo

Documentation and examples, for developers integrating Axate.

Your Local Artificial Memory on your Device.

THE Copilot in Obsidian

Chat with your notes & see links to related content with AI embeddings. Use local models or 100+ via APIs like Claude, Gemini, ChatGPT & Llama 3

A collection of low-to-no dependency modules for building smart apps with JavaScript

llama3 implementation one matrix multiplication at a time

Chat with multiple PDFs locally

Jan is an open source alternative to ChatGPT that runs 100% offline on your computer

Python solutions to the 1 billion row challenge.

A Python library for programmatically generating Draw.io charts.

Deploy ML models with FastAPI, Docker, and Heroku