KnowledgeGarden

gpt4all

GPT4All: Chat with Local LLMs on Any Device

FastChat

An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

gpt-researcher

GPT based autonomous agent that does online comprehensive research on any given topic

postgres

Postgres.js - The Fastest full featured PostgreSQL client for Node.js, Deno, Bun and CloudFlare

paradedb

Postgres for Search and Analytics

grobid

A machine learning software for extracting information from scholarly documents

terminusdb

TerminusDB is a distributed database with a collaboration model

croner

Trigger functions or evaluate cron expressions in JavaScript or TypeScript. No dependencies. Most features. Node. Deno. Bun. Browser.

LlamaChat

Chat with your favourite LLaMA models in a native macOS app

omnigres

Postgres as a Platform

minum

A minimalist Java web framework built from scratch

The-Oracle-of-Zotero

LLM Chain querying a scientific Zotero library, with citations

large_laguage_models

multi-doc-chatbot

A multi document reader and chatbot using LangChain and ChatGPT

adama-lang

A headless spreadsheet document container service.

ecohabit

EcoHabit is a web app project that aims to create awareness of the environment and help people build environmental friendly habits.

LIGHT

LIGHT is a platform for text-situated dialogue research. We originally hosted LIGHT as a live game with dialogue models in a grounded setting. This repo contains all of the code to get the LIGHT game running, as well as reproducible code for the research projects along the way of getting LIGHT to where it was.

mappa_mundi

Causal DAG Extraction from Text (DEFT)

frame-semantic-transformer

Frame Semantic Parser based on T5 and FrameNet

koza

Data transformation framework for LinkML data models

indie-microblogging

For drafts of the Indie Microblogging book.

monarch-ingest

Data ingest application for Monarch Initiative knowledge graph using Koza

lionlbd

Source code for the LION LBD Tool

Valmont-F

A open source Literature Based Discovery system, using Groovy & Grails, including a re-implementation of the Arrowsmith algorithm(s)

SKiM

Serial KinderMiner (or simply SKiM) is general literature-based discovery system for querying all ~30 million PubMed abstracts.

spa-vertx-vue

Basic Vert.x web application configured for a VueJS single page client application

NNLBD

Neural Network Architectures For Open and Closed Literature-Based Discovery

hyperknowledge

Hyperknowledge experiments

km_indexer

holons