BESSER

2026-07-25 · source · source ↗ · raw capture · wiki page

BESSER is an open-source low-code platform for building smart, AI-enhanced applications. It is led by LIST (Luxembourg Institute of Science and Technology) with SnT / University of Luxembourg, funded by an FNR PEARL grant from the Luxembourg National Research Fund. The project involves 11 researchers and engineers, has produced 53 peer-reviewed papers, and participates in 2 EU Horizon projects. Licensed under MIT.

The core paradigm is "model once, generate everywhere" — describe a system once, then generate working software across multiple tech stacks via 15+ code generators targeting Python, FastAPI, Django, SQLAlchemy, SQL, Java, React, and PyTorch.

Modeling covers structural (class diagrams), behavioral (state machines), object diagrams, agent specifications, and deployment specifications. User interfaces include a free online visual editor, image-to-model generation from diagram screenshots, and text-to-model via chatbot prompts — no local installation needed.

AI appears in both directions: AI assists the modeling process (image-to-model, text-to-model), and generated systems can embed AI components through the PyTorch generator.

The tagline is "Better Software, Faster."