A personal companion for planning, habits and focus. Daily check-ins meet a clear view of everyday life.
DRIVEN BY CURIOSITY Tübingen, Germany
Hi, I’m Matze.
Turning ideas
into reality.
I build apps, explore artificial intelligence and create things that make everyday life better.
01 / SELECTED WORK
Built from curiosity.
From a first small tool to an AI app.
A glimpse of what I’m working on.
Personal weekly meal plans, matching shopping lists and upcoming meals at a glance. Also known as V&M Fuel.
A dedicated interface for agentic development: projects, chats and multiple coding agents in one place.
Private source
Speak instead of typing: native voice input for Windows and Android, with separate meeting recording and transcription.
Private source
Which findings can vision-language models identify without task-specific training? Comparing BioMedCLIP and MedCLIP with different prompting strategies on chest X-rays.
Private source
A team project reconstructing 3D scenes from multiple calibrated camera images. A neural model produces a 3D Gaussian representation that can be rendered from new viewpoints.
Private source
A search engine for websites about Tübingen: crawling, indexing and ranking in a collaborative university project.
Developing and training reinforcement learning agents to face other agents in a provided hockey environment. The project concluded with a competition between teams.
Private source
It starts with a sketch.From a first sketch to an AI-generated image. A drawing canvas meets prompts, visual styles and creative experiments.
Survive waves of pirates on an island, collect loot and upgrade your equipment. The goal: build a ship and escape.
Open RepCounter, Gem Calculator, Card Manager and Egg Timer from one shared interface.
Count repetitions, track workout time and stay focused on your set. One of my first web and Android projects.
02 / THE PERSON BEHIND THE CODE
More than
just code.
Matze / aka matooo
I’m curious about how things work. And how to make them a little better.
I study computer science in Tübingen. My projects bring together software development, artificial intelligence and practical ideas — from workout tools to personal everyday companions.
Away from the screen, calisthenics, fitness and nutrition are part of my everyday life. My background as a paramedic adds another perspective: technology matters when it helps people.
Understand & build
Try out ideas and learn by building projects.
Keep going
In training and when tackling the next challenge.
03 / MY TOOLKIT
What I bring.
Technologies I work with in my
personal and collaborative projects.
Web & Apps
From a browser-based idea to a mobile application.
AI & Data
Selecting, exploring and integrating open-source LLMs and speech-to-text models into applications.
Backend & Tools
The foundation behind working software.
Agentic Engineering
Designing and orchestrating autonomous development workflows and integrated apps with Codex, Grok Build, Claude Code (app and CLI) and Antigravity (app and CLI). Strong focus on context management, structured agent instructions, MCP, plugins and API-based AI integration.
Linux, Servers & Networks
Setting up Linux servers, managing virtual machines and connecting services. Practical experience with Debian, Ubuntu and Proxmox, alongside foundations in subnets, firewall rules and VPNs.
04 / PROJECT DIRECTORY
The collection.
Apps, experiments and first steps.
Every project is part of the learning curve.
PROJECT / NAME18 projects
01MyLifeGraphApps & ToolsFlutter
02Pencil2PixelAI & ResearchPython
Draw in the browser, add a prompt and generate images through a Python backend. The project includes brushes, an eraser, undo/redo and adjustable generation parameters.
03NutriPilotApps & ToolsJavaScript
A nutrition project built around personal preferences, weekly planning and shopping lists. The original V&M Fuel project website remains available in the archive.
04Yapp AIPrivateAI & ResearchJava
A native application in development, featuring a microphone overlay, dictation history and configurable speech providers. Device validation is still part of ongoing development.
Private source
05Tübingen Search EngineAI & ResearchPython
Created in the Modern Search Engines course. A pipeline turns websites into a searchable index and presents results through a Streamlit interface.
06RepCounterApps & ToolsJavaScript
Count repetitions, track workout time and stay focused on your set. One of my first web and Android projects.
07Zero-Shot Chest X-RayPrivateAI & ResearchPython
Project in focus
- Challenge
- Explore how vision-language models identify multiple findings in chest X-rays without task-specific training.
- Research project
- We compared BioMedCLIP and MedCLIP and different prompting strategies across multiple datasets.
- Technical approach
- Positive and negative prompts, LLM-generated descriptions and composed strategies are evaluated through image-text similarity.
- Finding
- The benefit of a prompting strategy strongly depends on the model and dataset. This is a research comparison, not a clinical product.
Private source
08Codex UIPrivateWebTypeScript
A personal web app for orchestrating coding agents, managing projects and chats, and voice input. The visual preview is an illustrative demo with sample content.
Private source
09Card ManagerApps & ToolsJavaScript
10Gem CalculatorApps & ToolsJavaScript
Compare magic items: which purchase saves the most time per gem spent?
11AquaDefenderGamesC#
12Hockey RL AgentsPrivateAI & ResearchPython
Project in focus
- Challenge
- Train an agent for an existing hockey environment to compete against other teams.
- My contribution to the team
- Soft Actor-Critic, training against a pool of opponents and benchmarks to compare models.
- Technical approach
- The agent learns its strategy through reinforcement learning; different training opponents allow comparisons under different conditions.
- Outcome
- The trained agent participated in the final competition against agents from other teams.
Private source
133D Reconstruction with Gaussian SplattingPrivateAI & ResearchPython
Project in focus
- Challenge
- Reconstruct a 3D scene from multiple calibrated camera images and render new viewpoints.
- Team project
- We developed a pipeline that combines features from multiple cameras to predict a 3D representation.
- Technical approach
- A neural model produces a representation using 3D Gaussian Splatting. Model training and rendering are part of the same pipeline.
- Outcome
- Reconstructed scenes can be rendered from new viewpoints. Reconstruction quality was evaluated in the project.
Private source
14This PortfolioWebHTML
My projects, interests and progress in one place. The original website lives on in the archive.
15Egg TimerApps & ToolsJavaScript
A simple five-minute timer. A small experiment from the first version of my portfolio.
16Connect AppApps & ToolsJavaScript
Open RepCounter, Gem Calculator, Card Manager and Egg Timer from one shared interface.
17Routing TemplateWebJavaScript
A small example of modular routing with home, about and settings pages.
18Campfire StartpageWebHTML
An early start-page concept with a campfire video from my original repository.
Room for a new idea.
No projects match your search.
THE FIRST VERSION LIVES ON.
Every journey has a beginning.
My original website, the small apps and the complete original collection.
05 / LET’S TALK
From an idea to the next project.