Self-Organizing Multi-Agent Systems for Continuous Software Development

TL;DR

This paper introduces TheBotCompany, an open-source framework for continuous multi-agent software development, featuring a three-phase process, self-organizing teams, and human oversight, evaluated on real-world projects.

Contribution

It presents a novel orchestration framework with dynamic agent teams and a milestone-driven process for persistent, long-term software development.

Findings

Effective long-term progress in continuous development

Self-organizing teams adapt to project needs

Verification catches persistent defects

Abstract

Large Language Model-based multi-agent systems have shown promise in automating software development tasks. However, most vibe code systems focus on completing small tasks and incremental code changes, leaving persistent, continuous software development largely unexplored. We present TheBotCompany, an open-source orchestration framework for continuous multi-agent software development. TheBotCompany introduces three key innovations: (1) a three-phase state machine (Strategy to Execution to Verification) for milestone-driven development, (2) self-organizing agent teams where manager agents dynamically hire, assign, and fire worker agents based on project needs, and (3) asynchronous human oversight. We evaluate TheBotCompany on real-world software projects over multiple days of continuous development, measuring team adaptation patterns, milestone completion rates, cost efficiency, and code quality. Our results demonstrate that the self-organizing approach enables effective long-term software development with measurable progress, while the verification phase catches defects that would otherwise persist.