Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
2025 CCF International AIOps Challenge | Track 1: Microservice Root Cause Localization Based on Large Model Agents | "男团910" Solution · Top 5 in Final · Score: 48.52; (2025 CCF 国际 AIOps 挑战赛 | 赛道一：基于大模型智能体的微服务根因定位 | "男团910"方案 · 决赛Top5 · 48.52分)
| Date | Stars |
|---|---|
| 2026-07-31 | 260 |
| 2026-08-06 | 260 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# MicroRCA-Agent: LLM-Agent-Based Microservice Root Cause Analysis [](https://arxiv.org/abs/2509.15635) [](https://github.com/tangpan360/MicroRCA-Agent/stargazers) [](https://zhuanlan.zhihu.com/p/1952762182740711344) [](https://blog.csdn.net/weixin_51524504/article/details/151900832?spm=1001.2014.3001.5501) English | [中文](README_zh.md) ## 2025 International AIOps Challenge (Finals Top 5, 48.52 points) ## Project Overview This project is an intelligent operations solution based on multi-modal data analysis, capable of processing Log, Trace, and Metric data for fault analysis and root cause localization through large language models. It adopts a modular architecture design with five core modules: data preprocessing module, log fault extraction module, trace fault detection module, metric fault summarization module, and multi-modal root cause analysis module. The modules are designed with loose coupling through function encapsulation for data interaction, ensuring both system integrity and module independence and scalability. The output contains structured root cause analysis results including component, reason, and reasoning_trace, achieving a complete closed loop from phenomenon observation to root cause reasoning.  ## File Structure ``` ├── README.md # English project documentation ├── README_zh.md # Chinese project documentation ├── domain.conf # External domain configuration ├── src/ # Source code directory │ ├── agent/ # Intelligent agent module │ │ ├── __init__.py # Package initialization file │ │ ├── agents.py # Agent implementation │ │ ├── llm_config.py # LLM configuration for agent model list │ │ └── prompts.py # Prompt templates │ ├── utils/ # Utility modules │ │ ├── drain/ # Drain log template extraction │ │ │ ├── drain_template_extractor.py # Drain template extractor │ │ │ ├── drain3.ini # Drain3 configuration file │ │ │ ├── error_log-drain.pkl # Pre-trained template extraction model │ │ │ └── error_log-template.csv # Log template file │ │ ├── __init__.py # Package initialization file │ │ ├── file_utils.py # File processing utilities │ │ ├── io_util.py # IO utilities │ │ ├── llm_record_utils.py # LLM record utilities │ │ ├── log_template_extractor.py # Log template extractor (for training error_log-drain.pkl) │ │ ├── log_template_extractor_with_examples.py # Log template extractor with examples │ │ ├── log_utils.py # Log processing utilities │ │ ├── metric_utils.py # Metric processing utilities │ │ └── trace_utils.py # Trace processing utilities │ ├── models # Models (trace anomaly detection models) │ ├── scripts/ # Data preprocessing scripts including timestamp unification for log, trace, metric │ │ ├── merge_phaseone_phasetwo_input_json.py # Script to merge phaseone and phasetwo input.jsonl │ │ ├── raw_log_processor.py # Raw log processing │ │ ├── raw_metric_processor.py # Raw metric processing │ │ └── raw_trace_processor.py # Raw trace processing │ ├── models/ # Model files │ │ ├── trace_detectors.pkl # Trace anomaly detection model │ │ └── trace_detectors_normal_stats.pkl # Trace normal state statistics │ ├── input/ # Input data processing │ │ ├── extract_input_timestamp.py # Timestamp extraction │ │ └── input_timestamp.csv # Extracted input timestamp information │ ├── submission/ # Submission results │ │ ├── result.jsonl # Result file │ │ └── submit.py # Submission script │ ├── main_multiprocessing.py # Main program entry │ ├── preprocessing.sh # Data preprocessing script │ └── requirements.txt # Python dependenc
Excerpt of 20,288 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:8f78d9ca8ba1c366, llm:Repository description: 'Microservice Root Cause Localization Based on Large Model Agents' for 2025 CCF International AIOps Challenge — microservice root cause localization using large model agents (AIOps).
matched fp:8f78d9ca8ba1c366, llm:Repository description: 'Microservice Root Cause Localization Based on Large Model Agents' for 2025 CCF International AIOps Challenge — microservice root cause localization using large model agents (AIOps).
matched fp:8f78d9ca8ba1c366, llm:Repository description: 'Microservice Root Cause Localization Based on Large Model Agents' for 2025 CCF International AIOps Challenge — microservice root cause localization using large model agents (AIOps).