OpenDerisk: An Industrial Framework for AI-Driven SRE, with Design, Implementation, and Case Studies

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Di, Peng, Chen, Faqiang, Bai, Xiao, Yang, Hongjun, Li, Qingfeng, Wei, Ganglin, Mou, Jian, Shi, Feng, Chen, Keting, Tang, Peng, Shen, Zhitao, Li, Zheng, Shi, Wenhui, Guo, Junwei, Yu, Hang
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866918312619802624
author Di, Peng
Chen, Faqiang
Bai, Xiao
Yang, Hongjun
Li, Qingfeng
Wei, Ganglin
Mou, Jian
Shi, Feng
Chen, Keting
Tang, Peng
Shen, Zhitao
Li, Zheng
Shi, Wenhui
Guo, Junwei
Yu, Hang
author_facet Di, Peng
Chen, Faqiang
Bai, Xiao
Yang, Hongjun
Li, Qingfeng
Wei, Ganglin
Mou, Jian
Shi, Feng
Chen, Keting
Tang, Peng
Shen, Zhitao
Li, Zheng
Shi, Wenhui
Guo, Junwei
Yu, Hang
contents The escalating complexity of modern software imposes an unsustainable operational burden on Site Reliability Engineering (SRE) teams, demanding AI-driven automation that can emulate expert diagnostic reasoning. Existing solutions, from traditional AI methods to general-purpose multi-agent systems, fall short: they either lack deep causal reasoning or are not tailored for the specialized, investigative workflows unique to SRE. To address this gap, we present OpenDerisk, a specialized, open-source multi-agent framework architected for SRE. OpenDerisk integrates a diagnostic-native collaboration model, a pluggable reasoning engine, a knowledge engine, and a standardized protocol (MCP) to enable specialist agents to collectively solve complex, multi-domain problems. Our comprehensive evaluation demonstrates that OpenDerisk significantly outperforms state-of-the-art baselines in both accuracy and efficiency. This effectiveness is validated by its large-scale production deployment at Ant Group, where it serves over 3,000 daily users across diverse scenarios, confirming its industrial-grade scalability and practical impact. OpenDerisk is open source and available at https://github.com/derisk-ai/OpenDerisk/
format Preprint
id arxiv_https___arxiv_org_abs_2510_13561
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle OpenDerisk: An Industrial Framework for AI-Driven SRE, with Design, Implementation, and Case Studies
Di, Peng
Chen, Faqiang
Bai, Xiao
Yang, Hongjun
Li, Qingfeng
Wei, Ganglin
Mou, Jian
Shi, Feng
Chen, Keting
Tang, Peng
Shen, Zhitao
Li, Zheng
Shi, Wenhui
Guo, Junwei
Yu, Hang
Software Engineering
Artificial Intelligence
68N30
The escalating complexity of modern software imposes an unsustainable operational burden on Site Reliability Engineering (SRE) teams, demanding AI-driven automation that can emulate expert diagnostic reasoning. Existing solutions, from traditional AI methods to general-purpose multi-agent systems, fall short: they either lack deep causal reasoning or are not tailored for the specialized, investigative workflows unique to SRE. To address this gap, we present OpenDerisk, a specialized, open-source multi-agent framework architected for SRE. OpenDerisk integrates a diagnostic-native collaboration model, a pluggable reasoning engine, a knowledge engine, and a standardized protocol (MCP) to enable specialist agents to collectively solve complex, multi-domain problems. Our comprehensive evaluation demonstrates that OpenDerisk significantly outperforms state-of-the-art baselines in both accuracy and efficiency. This effectiveness is validated by its large-scale production deployment at Ant Group, where it serves over 3,000 daily users across diverse scenarios, confirming its industrial-grade scalability and practical impact. OpenDerisk is open source and available at https://github.com/derisk-ai/OpenDerisk/
title OpenDerisk: An Industrial Framework for AI-Driven SRE, with Design, Implementation, and Case Studies
topic Software Engineering
Artificial Intelligence
68N30
url https://arxiv.org/abs/2510.13561