LLAMOSC: LLM Agent-Based Modeling for Open Source Communities
A framework that pairs Large Language Models with agent-based modeling to simulate and sustain open-source communities.
LLAMOSC (LLM-Powered Agent-Based Model for Open Source Communities) is a framework for simulating open-source community dynamics using LLM-driven agents. It integrates AutoCodeRover for code-aware behavior, models the full pull-request lifecycle between contributor and maintainer agents, and supports both authoritarian (benevolent dictator) and decentralized (meritocratic) governance algorithms. The framework was developed during GSoC ‘24 under OREL/INCF and builds on prior GSoC ‘22 and ‘23 work.
Associated Working Groups & Programs
Joint Open Source Summer Cohort
A collaborative summer cohort across OREL, DevoWorm, and JOPRO — open-source contribution, instruction, and professional development, anchored by Google Summer of Code.
ProgramOpen-source Sustainability
A multi-year initiative investigating the long-term health and sustainability of open-source communities through agent-based modeling, active inference, and cybernetic approaches.