IJLTEMAS International Journal of Latest Technology in Engineering, Management & Applied Science (IJLTEMAS) IJLTEMAS 2278-2540 IJLTEMAS 81 10.51583/IJLTEMAS.2026.150700076 Artificial Intelligence Repogent: An Autonomous Multi-Agent System for End-To-End Repository Maintenance Satya Santhi Somisetti Venkata Associate Professor, Department of Computer Science and Engineering (Data Science), Anil Neerukonda Institute of Technology and Sciences, Visakhapatnam, Andhra Pradesh, India India Bhaskar Santhuluri Vijaya Department of Computer Science and Engineering (Data Science), Anil Neerukonda Institute of Technology and Sciences, Visakhapatnam, Andhra Pradesh, India India Teja Pathivada Sai Department of Computer Science and Engineering (Data Science), Anil Neerukonda Institute of Technology and Sciences, Visakhapatnam, Andhra Pradesh, India India Jasmine Mohamed Hajiya Department of Computer Science and Engineering (Data Science), Anil Neerukonda Institute of Technology and Sciences, Visakhapatnam, Andhra Pradesh, India India Kuna Anitha Department of Computer Science and Engineering (Data Science), Anil Neerukonda Institute of Technology and Sciences, Visakhapatnam, Andhra Pradesh, India India 15 7 916 932 29 07 2026 03 08 2026 13 08 2026 Multi-Agent Systems Repository Automation Large Language Models CI/CD Integration Open-Source Sustainability. Abstract

Maintaining open-source repositories demands continuous attention to issue triage, code review, build monitoring, and community support—tasks that overwhelm individual maintainers when existing automation tools operate in isolation without shared context. Static analyzers check code quality, CI/CD systems run automated tests, and simple bots handle basic labeling, yet none of these tools share information with each other, leaving maintainers as the sole integration point between disconnected systems. We present Repogent, a multi-agent system where four specialized AI agents—Issue Manager, Pull Request Reviewer, CI/CD Maintainer, and Community Assistant—collaborate through event-driven coordination and persistent cross-task memory. Our GitHub webhook-driven architecture processes events through a priority queue, routes them to specialized agents via intelligent orchestration, and stores decisions in a persistent context layer that enables cross-task reasoning. Events are assigned CRITICAL, HIGH, or NORMAL priority, while a semantic memory module based on sentence-transformer embeddings supports code-level search, and all agents share a common LLM service using Qwen 3 32B accessed through the Groq API. Evaluation on a dataset of 150 issues, 100 pull requests, 80 CI/CD workflow executions, and 120 community queries collected from five active open-source Python repositories demonstrates that Repogent achieves 93.3% accuracy in issue classification, 69.0% combined review coverage for pull requests, 86.7% accuracy in CI/CD failure categorization with a macro F1-score of 0.884, and an average quality score of 3.96 out of 5 for community responses. These results establish a foundation for sustainable open-source maintenance through context-aware, multi-agent workflow automation. Furthermore, the proposed framework demonstrates that multi-agent orchestration with persistent shared memory can serve as an effective and scalable solution for automating repository maintenance activities, improving coordination across heterogeneous development workflows, reducing maintainer overhead, and enabling more consistent decision-making across repository events.

 References M. Baqar, S. Naqvi, and R. Khanda, “AI-augmented CI/CD pipelines: From code commit to production with autonomous decisions,” in Proceedings of the 3rd International Conference on Foundation and Large Language Models (FLLM), Vienna, Austria, 2025, doi: https://doi.org/10.1109/FLLM67465.2025.11391007. Z. Feng, D. Guo, D. Tang, N. Duan, X. Feng, M. Gong et al., “CodeBERT: A pre-trained model for programming and natural languages,” in Findings of the Association for Computational Linguistics: EMNLP 2020, 2020, pp. 1536–1547, doi: https://doi.org/10.18653/v1/2020.findings-emnlp.139. S. Hong, M. Zhuge, J. Chen, X. Zheng, Y. Cheng, C. Zhang et al., “MetaGPT: Meta programming for a multi-agent collaborative framework,” arXiv preprint arXiv:2308.00352, 2023, doi: https://doi.org/10.48550/arXiv.2308.00352. H. Husain, H.-H. Wu, T. Gazit, M. Allamanis, and M. Brockschmidt, “CodeSearchNet challenge: Evaluating the state of semantic code search,” arXiv:1909.09436, 2019, doi: https://doi.org/10.48550/arXiv.1909.09436. C. E. Jimenez, J. Yang, A. Wettig, S. Yao, K. Pei, O. Press et al., “SWE-bench: Can language models resolve real-world GitHub issues?” arXiv preprint arXiv:2310.06770, 2023, doi: https://doi.org/10.48550/arXiv.2310.06770. R. Kallis, A. Di Sorbo, G. Canfora, and S. Panichella, “Predicting issue types on GitHub,” Science of Computer Programming, vol. 205, art. 102598, 2021, doi: https://doi.org/10.1016/j.scico.2020.102598. Q. Luo, Y. Ye, S. Liang, Z. Zhang, Y. Qin, Y. Lu et al., “RepoAgent: An LLM-powered open-source framework for repository-level code documentation generation,” in Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, 2024, pp. 436–464, doi: https://doi.org/10.18653/v1/2024.emnlp-demo.46. M. Monperrus, “Automatic software repair: A bibliography,” ACM Computing Surveys, vol. 51, no. 1, art. 17, pp. 1–24, 2018, doi: https://doi.org/10.1145/3105906. R. A. Proma and P. Rosen, “Visual analysis of GitHub issues to gain insights,” arXiv:2407.20900, 2024, doi: https://doi.org/10.48550/arXiv.2407.20900. W. Tao, Y. Zhou, Y. Wang, W. Zhang, H. Zhang, and Y. Cheng, “MAGIS: LLM-based multi-agent framework for GitHub issue resolution,” arXiv preprint arXiv:2403.17927, 2024, doi: https://doi.org/10.48550/arXiv.2403.17927. H. Wang, Z. Ni, S. Zhang, S. Lu, S. Hu, Z. He et al., “RepoMaster: Autonomous exploration and understanding of GitHub repositories for complex task solving,” arXiv preprint arXiv:2505.21577, 2025, doi: https://doi.org/10.48550/arXiv.2505.21577. L. Wang, C. Ma, X. Feng, Z. Zhang, H. Yang, J. Zhang et al., “A survey on large language model based autonomous agents,” Frontiers of Computer Science, vol. 18, no. 6, art. 186345, 2024, doi: https://doi.org/10.1007/s11704-024-40231-1. Q. Wu, G. Bansal, J. Zhang, Y. Wu, B. Li, E. Zhu et al., “AutoGen: Enabling next-gen LLM applications via multi-agent conversation,” arXiv preprint arXiv:2308.08155, 2023, doi: https://doi.org/10.48550/arXiv.2308.08155. P. W. Zydroń and J. Protasiewicz, “Enhancing code review efficiency – Automated pull request evaluation using natural language processing and machine learning,” Advances in Science and Technology Research Journal, vol. 17, no. 4, pp. 162–167, 2023, doi: https://doi.org/10.12913/22998624/169576.