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.
181 stars.
Use this if you need to automatically monitor large volumes of system logs to proactively identify abnormal system behavior and potential failures.
Not ideal if you are looking for a solution to analyze application-level logs for business insights, or if you need to debug specific code errors rather than detect system-wide operational anomalies.
Stars
181
Forks
36
Language
Python
License
MIT
Category
Last pushed
Dec 09, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/guanwei49/LogLLM"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Compare
Related models
sintel-dev/sigllm
Using Large Language Models for Time Series Anomaly Detection
poloclub/llm-landscape
NeurIPS'24 - LLM Safety Landscape
yangzhch6/AlignedCoT
Implementation of our paper "Speak Like a Native: Prompting Large Language Models in a Native Style"
CloudnetUCSC/VMFT-LAD
The source repository of "Virtual Machine Proactive Fault Tolerance using Log-based Anomaly...