Artificial Intelligence in Open Source Software Engineering: A Foundation for Sustainability

Open-source software (OSS) is foundational to modern digital infrastructure, yet this context for group work continues to struggle to ensure sufficient contributions in many critical cases. This literature review explores how artificial intelligence (AI) is being leveraged to address critical challenges to OSS sustainability, including maintaining contributor engagement, securing funding, ensuring code quality and security, fostering healthy community dynamics, and preventing project abandonment. Synthesizing recent interdisciplinary research, the paper identifies key applications of AI in this domain, including automated bug triaging, system maintenance, contributor onboarding and mentorship, community health analytics, vulnerability detection, and task automation. The review also examines the limitations and ethical concerns that arise from applying AI in OSS contexts, including data availability, bias and fairness, transparency, risks of misuse, and the preservation of human-centered values in collaborative development. By framing AI not as a replacement but as a tool to augment human infrastructure, this study highlights both the promise and pitfalls of AI-driven interventions. It concludes by identifying critical research gaps and proposing future directions at the intersection of AI, sustainability, and OSS, aiming to support more resilient and equitable open-source ecosystems.

💡 Research Summary

The paper presents a systematic literature review that investigates how artificial intelligence (AI) can be leveraged to address the persistent sustainability challenges faced by open‑source software (OSS) projects. It begins by outlining the fundamental problems that threaten OSS longevity: contributor attrition and onboarding difficulties, insufficient funding models, code quality degradation and technical debt, security vulnerabilities and patch‑management bottlenecks, governance weaknesses, and the risk of project abandonment. These issues are framed within the “tragedy of the commons” narrative, emphasizing that the collective benefits of OSS are not matched by proportional contributions.

Methodologically, the authors adopt a PRISMA‑based systematic review process. Searches were conducted across five major academic databases—Scopus, ACM Digital Library, IEEE Xplore, Web of Science, and arXiv—using Boolean combinations of terms related to AI (including large language models, machine learning, deep learning), OSS (FLOSS, open‑source projects), and sustainability (maintenance, longevity, green AI). Only peer‑reviewed English‑language papers from the last five years that explicitly connect AI techniques to OSS sustainability were retained, while non‑academic sources, duplicate records, and studies lacking a clear OSS‑AI link were excluded.

The review categorizes AI applications into several functional domains. Automated bug triaging employs natural‑language processing and static analysis to label, prioritize, and assign issues, reducing manual triage effort. Code quality and technical debt management utilizes large language model‑driven code‑review assistants that assess style consistency, cyclomatic complexity, and test coverage, and can suggest automated refactorings. Security is addressed through deep‑learning‑based vulnerability detection and auto‑patch generation, complemented by continuous scanning of dependency graphs to mitigate supply‑chain attacks. Contributor onboarding and mentorship are supported by AI‑powered chatbots, auto‑generated documentation, and recommendation systems that match newcomers with suitable mentors or tasks. Community health analytics combine social‑network analysis with sentiment analysis to detect “community smells” such as conflict or contributor burnout, while AI‑enabled governance tools provide transparent decision‑making simulations. Finally, task automation integrates AI into CI/CD pipelines and robotic process automation to handle repetitive maintenance chores.

The authors also discuss the limitations and ethical concerns inherent in these AI interventions. Data scarcity—particularly high‑quality labeled bug and vulnerability datasets—can impair model performance, and existing datasets often exhibit bias toward certain languages or platforms. The opacity of many AI models raises trust issues, especially when automated decisions affect contributor reputation or project governance. There is a risk of de‑humanizing OSS collaboration, potentially diminishing the sense of ownership and community spirit. Moreover, AI tools could inadvertently violate open‑source licenses, generate malicious code, or be weaponized for large‑scale attacks.

In the concluding section, the paper identifies four major research gaps: (1) a lack of long‑term empirical studies quantifying AI’s impact on OSS sustainability; (2) insufficient analysis of the operational and environmental costs associated with maintaining large AI models; (3) limited generalizability of AI solutions across multilingual, culturally diverse OSS communities; and (4) the absence of policy‑level guidelines governing AI use in open‑source ecosystems. To bridge these gaps, the authors recommend the creation of standardized, open OSS‑AI datasets, the development of human‑AI collaborative frameworks that preserve contributor agency, the formulation of ethical and legal standards for AI deployment, and interdisciplinary collaborations that integrate software engineering, social science, and policy research.

Overall, the paper offers a balanced perspective: AI holds significant promise for enhancing OSS resilience, quality, and security, but its deployment must be carefully managed to uphold the human‑centric values that define the open‑source movement.