Low-code and no-code with BESSER to create and deploy smart web applications

2026-05-08

AI Summary

This work addresses the limitations of existing commercial low-code platforms—particularly vendor lock-in and insufficient extensibility—which hinder the flexible development of intelligent web applications, such as those integrating AI agents. To overcome these challenges, the authors propose and open-source BESSER, a transparent and extensible low-code/no-code development framework. Built upon model-driven abstractions, BESSER combines a web-based visual editor with automated code generation to enable users to efficiently design, generate, and deploy AI-enhanced intelligent web applications. As the first fully open-source low-code solution of its kind, BESSER significantly improves development efficiency and system controllability while eliminating proprietary constraints, thereby supporting deep customization and seamless AI integration.

Abstract

The increasing demand for web applications containing AI-agents, seen as smart web applications, has prompted the need for new techniques to facilitate their creation. Low-code has risen as an approach that reduces the amount of handwritten code by focusing on the abstraction of components in the form of models combined with automated generators to produce applications. Existing low-code platforms are commercial, leading to drawbacks such as the risk of vendor lock-in, limited extensibility, and more. We present the open-source BESSER low-code framework, which allows users to design, generate and deploy their application via a freely accessible web-based editor, while guaranteeing transparency and extensibility.

Problem

• low-code
• smart web applications
• vendor lock-in
• extensibility
• AI-agents

Innovation

• low-code
• open-source
• smart web applications
• AI agents
• model-driven development