Software and AI β built here, not bought in.
The umbrella over everything Simon van de Loo builds: an AI assistant with its own finetunes, writing software with an embedded language model, and web projects on a consistent design system. All of it runs locally.
- 5own language-model finetunesopen on Hugging Face
- 6LoRA adapters3Γ image, 3Γ music
- 100 %local inferenceApple Silicon, MLX
- 0third-party model APIsnot a wrapper
The approach
Runs locally
Language models, image and music generation run on Apple Silicon via MLX β no cloud dependency, no data that leaves the machine.
Own finetunes
Rather than wrapping someone else's API: five finetunes of my own on Gemma 4, Ministral 3 and Qwen-Coder β trained on datasets I built myself, not on off-the-shelf material. Model cards and data are public on Hugging Face.
nCAI alignment
A training approach of my own: the persona takes the place of a rulebook. Refusal behaviour, tone, tool use and coding style all follow from the character β alignment of a whole agent through who it is.
Labelled
What A!ley produces carries her name and is marked as AI-generated β watermarks and machine-readable metadata under the EU AI Act. Taking a persona seriously means naming her as the author, and saying plainly what she is anyway.
The whole stack
From model weights to UI pixel: training, inference backend, desktop app and web interface all come from one pair of hands.
Projects
What comes next
Two plans with nothing running yet β here so the direction is visible.
- planned
A!am
An open offshoot of A!ley β the name from AI, βI amβ and the exclamation mark. Same base models, but trained to take on a character, name included, from a handful of XML triggers in the system prompt instead of from page-long character bibles. Building a persona should require neither training nor programming knowledge. The idle thinker and the RAG memory come along; code, image, song and video can be loaded in as needed. It runs on people's own machines.
- planned
H!ve
A standalone product on related foundations: a suite for media design with image, video and audio generation. In place of the idle thinker's autonomy, Team Thinker v1 works here β several models finetuned for specific tasks that work towards one goal instead of roaming on their own.
What runs here
The stack behind A!ley β from the model layer up to the interface.
Own finetunes
- A!ley Core β Gemma 4 12B
- A!ley Tempest β Ministral 3 14B
- A!ley Nitro β Gemma 4 E2B
- Code A!ley β Qwen 3.6 Coder 9B
- Linting Hamster β Qwen2.5-Coder 1.5B
Generative
- MFLUX Z-Image-Turbo β 3 LoRA
- ACE-Step 1.5 β 3 LoRA
- PiperTTS
- WAN 2.1
Memory & runtime
- LanceDB (RAG)
- MLX on Apple Silicon
- Flask backend
- Polling architecture
Interfaces
- Tauri desktop app
- Next.js frontend
- PHP web portal
- Monaco editor
About me
Behind openM!nded Labs is Simon van de Loo β Digital Media Designer (IHK), graded βvery goodβ, with the best practical examination in the Koblenz district. My first computer still ran Windows 3.11 β what I mostly learned from it was how to get along with awkward systems. Programming came a few Windows versions later by way of an RPG Maker: I wanted to build worlds and had to learn Ruby for it. Python and the web stack followed, Rust only during my retraining, because a teacher put it under my nose.
Professionally it went differently for a long time β twelve years in elderly care, then the retraining. What stayed throughout was writing: I am a published author several times over, focused on world- and character-building. Behind my Martyria universe stand over 600 pages of concept work since 2015 β currencies, calendars, a timeline, a glossary of people.
That is not a collection of interests but a chain β and it starts with worldbuilding, not with code. Whoever writes characters can build personas. Whoever programs can train them. In AI the two meet, and that is why my training data looks like manuscripts rather than tables.
The full CV, references and ways to get in touch are in the job-application portfolio.

Interested in a project?
Whether it's working together, a technical detail or plain curiosity about locally running models β write to me.




