Skip to content
Listed in Berlin·Rank earned, never paid·How rankings work →
Is this your agency? Claim profile to verify details or update information.

ontolux

Berlin, Germany

10-49Contact for rates
Visit Website

About

ontolux is a Berlin NLP and semantic-search team within Neofonie, building German-language text analysis, tagging and search systems for public-sector, media and enterprise knowledge collections.

Who They Work With

German public bodies, broadcasters and publishers that need tagging and search over large German-language text collections.

Based on 13 client engagements with a source URL · researched 27 Sept 2026

Our Take

ontolux's case pages name 13 clients, and the text-analysis work carries the production weight: its TXTWerk framework tags the PMG press database (170,000+ articles a day, client since 2012) and suggests keywords and linked entities inside the ZDFmediathek's CMS, and a 2024 platform for Humboldt-Universität's H-Soz-Kult runs Llama-based semantic search on the university's own GPUs.

Three of the 13 are Elasticsearch site-search projects (HUK-COBURG, Bechtle, Creditreform), and several older ones were commissioned from parent company Neofonie, including a 2014 holiday-rental crawl for Bezirksamt Berlin-Mitte.

Few case pages report outcome numbers, and the LLM work beyond Humboldt is published as prototypes—one of which, a pharma RAG prototype, says plainly that its approach had too little impact.

The weaker fit is buyers who need a generative-AI or agent system with a production reference: the published LLM record is one local-model research platform and three prototypes.

Key strengths

  • Long client tenures stated on the case pages: Creditreform since 2009, PMG since 2012, Bechtle since 2017, ZDF and BSI since 2021
  • Stack named per project—TXTWerk, Haystack, Elastic Stack, PoolParty and Doccano for the BSI threat-report system; Llama, Elasticsearch and Solr on local hardware for Humboldt-Universität
  • Prototype write-ups report what did not work: the pharma comparator-therapy prototype concludes its data source had too little impact, and the client moved to a process survey before the next round

Good to know

  • Most case pages report no outcome figures—ask for usage and quality numbers on the ZDF and PMG tagging, the systems closest to production evidence
  • The legal entity behind the brand is Neofonie GmbH and several projects were commissioned from Neofonie—ask whether your project is staffed from the 20-person ontolux team or the parent's 180 staff
  • If you are buying LLM or RAG delivery, ask for a production reference beyond the Humboldt-Universität platform; the other LLM pages are prototypes
Gabor Kiss

Reviewed by Gabor Kiss

Founder & Curator, AIAgencies.eu · 24 Sept 2026

Based on the agency's publicly available portfolio. Own this agency? Claim your profile to provide additional context or request a review update.


How we evaluate agencies

Notable Clients

Every engagement documented in a published case study

Documented engagements: PMG Presse-Monitor, ZDF, Humboldt-Universität zu Berlin (H-Soz-Kult), BSI (Federal Office for Information Security), DEval (German Institute for Development Evaluation), Gruner + Jahr Digital Products, HUK-COBURG, Bechtle, Creditreform, Thüringer Landesrechenzentrum, and Bezirksamt Berlin-Mitte. All 11 carry a source URL on file.

PMG Presse-MonitorTXTWerk entity tagging and IPTC classification feeding the relevance ranking of Germany's largest daily press database (170,000+ articles a day); client since 2012Source
ZDFTagging service for the ZDFmediathek: keyword extraction, named-entity recognition and Wikidata entity linking, integrated into the editors' CMS via REST; client since 2021Source
Humboldt-Universität zu Berlin (H-Soz-Kult)Semantic search and topic generation for a history research platform, with Llama models run on the university's own GPUs (2024)Source
BSI (Federal Office for Information Security)Research-oriented NLP system extracting and clustering cyber-threat reports, built on TXTWerk, Haystack and Elastic Stack; client since 2021Source
DEval (German Institute for Development Evaluation)Scraping, segmentation and rule-based classification of two decades of Bundestag documentsSource
Gruner + Jahr Digital ProductsContent curation engine applying NER and quality scoring across about 1,500 web sources for newsroom research (2018, commissioned from Neofonie)Source
HUK-COBURGRebuilt Elasticsearch site search on huk.de with personalization for logged-in customers; client since 2019Source
BechtleIT-shop search tuning, autosuggest and gold-standard search evaluation on Elasticsearch; client since 2017Source
CreditreformSearch and autosuggest for a portal of four million company profiles; client since 2009Source
Thüringer LandesrechenzentrumAdvisory: market analysis of about 20 open-source search engines and an outline concept with a product recommendation (2022)Source
Bezirksamt Berlin-MitteCrawl and deduplication of holiday-rental listings across 15 portals, counting 23,103 apartments city-wide (2014, commissioned from Neofonie)Source

Get Matched with Agencies

Recommended

Tell us your needs and we'll connect you with 3 vetted agencies—including ontolux if it's a fit.

Get Matched →

Curator shortlist within 3 business days

Visit ontolux's website →

Own this agency? Claim your profile to verify info & receive leads directly.

Have an AI agency in Berlin?

Get listed for free and start receiving project inquiries.

Submit Your Agency