Keine Medien-Innovationen, Events und Startups mehr verpassen? Abonniere unseren Newsletter! Will ich haben!



Open Semantic Tagging

taggy is an open frontend tool that recognizes context and automatically assigns appropriate tags to texts. For example, incoming requests from contact forms, blog posts or other editorial content can be automatically categorized correctly.

As a lightweight frontend library, taggy can be quickly and easily integrated into existing web systems to then take over the normally tedious task of tagging.


Tagging content in web-based editorial systems, i.e. assigning content to a selection of topics, has not really evolved over the last few years. Many still tag manually and have problems with large amounts of data.


taggy is a standard component for web-based smart tagging, as an extension for common frontend technologies and CMS platforms. taggy recognizes what content a text contains and what the main topic is, and does so without (paid) external services and interfaces.


taggy as a freely available web component is simply integrated into the existing web system and fed with an existing glossary (list of keywords). Then taggy is immediately ready to use to assign any incoming texts to the right topics.


Assign form input by your users automatically to the right internal tracks


Johannes Busching

Johannes has a background in the media industry and combines it with his know-how as a computer scientist. His main topics are Natural Language Processing, automatic classification/indexing of content and the evaluation and (re-)usability of audio material.

LinkedIn | Johannes Busching


Glasskube enables automatic installation and updates for popular open source software solutions to help organisations reclaim their digital sovereignty.

Find out more

Content Lense

Content lense enables bloggers and publishers to analyse their digital content and generate exciting insights.

Find out more

Open Podcast

Open Podcast is building a free and open ecosystem for podcasts. In the first project the aim is to provide a better analytics data for podcast hosts.

Find out more

Open Recommendation Butler

Open Recommendation Butler (ORB) is building an AI language model designed specifically for the media industry that provides knowledge-based search results and thematic recommendations.



Speechcatcher develops an open source solution for translation, transcription and subtitling of any media files with German language content (audio/video).



SnipAId develops Artificial Intelligence generated teasers, summaries and social media posts.


Any questions on the Media Tech Lab?