sigllm and LogLLM
These are **complements** that address adjacent but distinct anomaly detection domains—one applies LLMs to time series data while the other applies LLMs to unstructured system logs, allowing them to be used together in a comprehensive monitoring pipeline.
About sigllm
sintel-dev/sigllm
Using Large Language Models for Time Series Anomaly Detection
This project helps operations engineers, data analysts, or researchers quickly identify unusual patterns in their time-series data. You feed it a timestamped sequence of measurements, and it tells you where anomalies occur. This tool is designed for anyone needing to spot unexpected shifts or events in streams of data, like system metrics, sensor readings, or financial data.
About LogLLM
guanwei49/LogLLM
LogLLM: Log-based Anomaly Detection Using Large Language Models (system log anomaly detection)
This project helps operations engineers and system administrators automatically detect unusual behavior in system logs. It takes raw system log files (like HDFS, BGL, Liberty, or Thunderbird logs) as input and identifies log sequences that indicate anomalies. The output is a clear classification of whether specific log events or sequences are normal or anomalous, helping users quickly pinpoint system issues.
Scores updated daily from GitHub, PyPI, and npm data. How scores work