Software

Claude-threads

Claude-threads brings Claude Code capabilities directly into team chat platforms like Mattermost and Slack. The bot enables collaborative AI pair programming by streaming Claude’s responses live to chat threads, allowing teams to work together on coding tasks in real-time. Each conversation thread maintains its own isolated Claude session with features like interactive approvals through emoji reactions, git integration with worktrees, and support for image analysis. As the tagline suggests, it’s “screen-sharing for AI pair programming, but everyone can type.”

The source code is available on GitHub.

peerpressure

Peerpressure is a social digital detox app that uses peer accountability to help users stay focused and avoid digital distractions. When you join a focus session with friends, they can see when you try to break focus - turning social pressure into your productivity superpower. The app blocks distracting apps in real-time, requires peer approval for emergency unlocks, and tracks focus streaks and session history. By making productivity a collaborative effort, peerpressure helps users break free from digital distractions together.

Learn more at peerpressure.social.

RegelRecht

RegelRecht is an exploration by the Dutch Ministry of the Interior (Bureau Architectuur Digitale Overheid) into machine-executable legislation. The project investigates how we can achieve transparent, unambiguous, and consistent execution of laws - enabling everyone to understand how decisions are made.

This initiative explores whether laws can be written as directly executable code, eliminating the gap between legislation and implementation. By creating machine-readable legal specifications, RegelRecht aims to:

• Provide one single source of truth for legal rules that all parties use
• Enable full transparency and traceability of government decisions
• Test new legislation before implementation to detect conflicts and inconsistencies
• Reduce interpretation differences across government organizations

The ecosystem includes NRML (Normalized Rule Model Language) as a JSON-based format for machine-executable laws, execution engines in multiple programming languages, an AI-powered converter for existing analog law, a visual law editor, and simulation environments for testing legislative impact.

Learn more at regelrecht.rijks.app or explore the source code on GitHub.

Algorithm Management Toolkit (AMT)

A comprehensive platform for the governance and oversight of algorithmic systems within organizations. Developed for the Dutch government, AMT provides a structured approach to documenting, testing, and managing both AI and non-AI algorithms used in public services and decision-making processes.

The toolkit features a bookkeeping system for algorithmic applications, technical validation tools, ethical assessment frameworks, and transparency reporting capabilities. It helps organizations maintain proper documentation, ensure regulatory compliance, and implement responsible AI practices. AMT represents an important step toward algorithmic accountability in governance and public service delivery.

The source code is available on GitHub.

Living Labs

The Living Labs for IR Evaluation (LL4IR) is a new evaluation paradigm. I implemented an API for participants ( researchers) and sites (search engines) that take part in this Living Lab (which is also run as a CLEF lab). The API allows participants (researchers) to evaluate their ranking systems on real users of real sites (search engines). On the flip site, it allows sites (search engines) to benefit from the knowledge of the research community.

The LL4IR API can be used by researchers to perform several actions such as obtaining queries, documents and feedback and to update runs. The API is RESTful, that is, everything is implemented as HTTP request, and we use the request types GET, PUT and DELETE.

The source code is available on GitHub.

It has mainly been developed by Anne Schuth and Krisztian Balog.

Related publications:

• OpenSearch. Anne Schuth. In Proceedings of DIR’15, 2015.
• Overview of the Living Labs for Information Retrieval Evaluation (LL4IR) CLEF Lab 2015. Anne Schuth and Krisztian Balog and Liadh Kelly. In Proceedings of CLEF’15, 2015.
• Extended Overview of the Living Labs for Information Retrieval Evaluation (LL4IR) CLEF Lab 2015. Anne Schuth and Krisztian Balog and Liadh Kelly. In Proceedings of CLEF’15, 2015.

Related talks:

• OpenSearch. Lightning Talk, DIR’15. Amsterdam, The Netherlands. Nov 27, 2015.
• TREC OpenSearch. ILPS Soos. Amsterdam, The Netherlands. Nov 3, 2015.
• LL4IR Introduction. CLEF LL4IR’15. Toulouse, France. Sep 10, 2015.
• Living Labs for IR Evaluation (LL4IR) Overview. CLEF’15. Toulouse, France. Sep 8, 2015.
• Living Labs for Search. Workshop: Towards networked Research Infrastructures for behavioral studies. Brussels, Belgium. May 7, 2015.

Lerot: an Online Learning to Rank Framework

Lerot is a framework, designed to run experiments on online learning to rank methods for information retrieval. It has mainly been developed by Katja Hofmann and Anne Schuth. The source code of Lerot is available from bitbucket.

Related publications:

• Search Engines that Learn from Their Users. Anne Schuth. 2016.
• Probabilistic Multileave Gradient Descent. Harrie Oosterhuis and Anne Schuth and Maarten de Rijke. In Proceedings of ECIR’16, 2016.
• Multileave Gradient Descent for Fast Online Learning to Rank. Anne Schuth and Harrie Oosterhuis and Shimon Whiteson and Maarten de Rijke. In Proceedings of WSDM’16, 2016.
• Probabilistic Multileave for Online Retrieval Evaluation. Anne Schuth and Robert-Jan Bruintjes and Fritjof Büttner and Joost van Doorn and Carla Groenland and Harrie Oosterhuis and Cong-Nguyen Tran and Bas Veeling and Jos van der Velde and Roger Wechsler and David Woudenberg and Maarten de Rijke. In Proceedings of SIGIR’15, 2015.
• A comparative analysis of interleaving methods for aggregated search. Aleksander Chuklin and Anne Schuth and Ke Zhou and Maarten de Rijke. In ACM Transactions on Information Systems, 2015.
• Multileaved Comparisons for Fast Online Evaluation. Anne Schuth and Floor Sietsma and Shimon Whiteson and Damien Lefortier and Maarten de Rijke. In Proceedings of CIKM’14, 2014.
• Evaluating Intuitiveness of Vertical-Aware Click Models. Alexandr Chuklin and Ke Zhou and Anne Schuth and Floor Sietsma and Maarten de Rijke. In Proceedings of SIGIR’14, 2014.
• Optimizing Base Rankers Using Clicks: A Case Study using BM25. Anne Schuth and Floor Sietsma and Shimon Whiteson and Maarten de Rijke. In Proceedings of ECIR’14, 2014.
• Effects of Position Bias on Click-Based Recommender Evaluation. Katja Hofmann and Anne Schuth and Alejandro Bellogin and Maarten de Rijke. In Proceedings of ECIR’14, 2014.
• Lerot: an Online Learning to Rank Framework. Anne Schuth and Katja Hofmann and Shimon Whiteson and Maarten de Rijke. In Proceedings of Living Labs for Information Retrieval Evaluation workshop at CIKM’13, 2013.
• Evaluating Aggregated Search Using Interleaving. Alexandr Chuklin and Anne Schuth and Katja Hofmann and Pavel Serdyukov and Maarten de Rijke. In Proceedings of CIKM’13, 2013.
• Reusing Historical Interaction Data for Faster Online Learning to Rank for IR. Katja Hofmann and Anne Schuth and Shimon Whiteson and Maarten de Rijke. In Proceedings of WSDM’13, 2013.

Related talks:

• Search Engines that Learn from Their Users. Aula UvA. Amsterdam, The Netherlands. Apr 27, 2016.
• Multileave Gradient Descent for Fast Online Learning to Rank. WSDM’16. San Francisco, USA. Feb 24, 2016.
• Multileave Gradient Descent for Fast Online Learning to Rank. ILPS Soos. Amsterdam, The Netherlands. Nov 3, 2015.
• Predicting Search Satisfaction Metrics with Interleaved Comparisons. Beer&Tech, Criteo. Paris, France. Oct 28, 2015.
• Probabilistic Multileave for Online Retrieval Evaluation. SIGIR’15. Santiago, Chile. Aug 9, 2015.
• Probabilistic Multileave for Online Retrieval Evaluation. ILPS Soos. Amsterdam, The Netherlands. Jul 28, 2015.
• Multileaved Comparisons for Fast Online Evaluation. IAS Colloquium. Amsterdam, The Netherlands. Mar 17, 2015.
• Multileaved Comparisons for Fast Online Evaluation. ILPS Soos. Amsterdam, The Netherlands. Oct 21, 2014.
• Online Learning to Rank. Textkernel Tech Talks. Amsterdam, The Netherlands. Jun 26, 2014.
• Optimizing Base Rankers Using Clicks: A Case Study using BM25. ECIR’14. Amsterdam, The Netherlands. Apr 14, 2014.
• Effects of Position Bias on Click-Based Recommender Evaluation. ECIR’14. Amsterdam, The Netherlands. Apr 14, 2014.
• Lerot: an Online Learning to Rank Framework. Living Labs workshop at CIKM’13. San Francisco, USA. Nov 1, 2013.
• Evaluating Aggregated Search Using Interleaving. ILPS Soos. Amsterdam, The Netherlands. Oct 1, 2013.
• Doing a PhD in Artificial Intelligence: Search Engines that Learn. Information day BSc Artificial Intelligence. Amsterdam, The Netherlands. Mar 23, 2013.
• Reusing Historical Interaction Data for Faster Online Learning to Rank for IR. IR group of the University of Glasgow. Glasgow, Scotland, UK. Mar 10, 2013.