UpTrain is an open-source unified platform to evaluate and improve Generative AI applications. We provide grades for 20+ preconfigured checks (covering language, code, embedding use-cases), perform root cause analysis on failure cases and give insights on how to resolve them.

Timeseries Anomaly detection and Root Cause Analysis on data in SQL data warehouses and databases

[ICLR'25] OpenRCA: Can Large Language Models Locate the Root Cause of Software Failures?

Implementation of RiskLoc, a method for localizing multi-dimensional root causes.

Root Cause Analysis for Kubernetes

AERCA: Root Cause Analysis of Anomalies in Multivariate Time Series through Granger Causal Discovery (ICLR 2025 Oral)

Multi-Agent Debugger: An AI-powered debugging system using CrewAI to orchestrate specialized agents that analyze logs, trace code, and uncover root causes across your stack — powered by LLM providers.

Code for "LEMMA-RCA: A Large Multi-modal Multi-domain Dataset for Root Cause Analysis" paper

RootCLAM: On Root Cause Localization and Anomaly Mitigation through Causal Inference (CIKM 2023)

This repository provides all necessary code and data to reproduce the experiments from the ICSE - 2025 accepted paper: "Improved Detection and Diagnosis of Faults in Deep Neural Networks using Hierarchical and Explainable Classification."

Root Cause Analysis in the Industrial Domain using Knowledge Graphs: A Case Study on Power Transformers

Source code for the AITIA-PM algorithm. See paper entitled "Root Cause Analysis in Process Mining with Probabilistic Temporal Logic", published at the 2nd International Workshop on Event Data & Behavioral Analytics, co-located with ICPM2021

Implementation of the Heatmap-based Unsupervised Debugging of DNNs (HUDD) toolset

A Python 3 package for identifying distribution shifts (a.k.a feature-shifts) between datasets. Official implementation of the paper: "iSCAN: Identifying Causal Mechanism Shifts among Nonlinear Additive Noise Models".

Given a document, identifying the closest documents within the list of documents using tf-idf matrix and cosine similarity

Python tool that analyzes Slack conversations with AWS Bedrock AI to generate detailed RCA reports and actionable learnings for Dev and QA teams, with JIRA integration and intelligent summarization.

AIOps experiment system, next-generation AIOps platform powered by LLM, Multi-Agent architecture and RAG technology. Intelligent root cause analysis through agent collaboration - from problem detection to automated solution.

A curated list of resources, methodologies, frameworks, and case studies for performing RCA on UAV systems.

An AI-powered RAG pipeline for analyzing incidents, identifying root causes, detecting patterns, and generating solutions.

Python tool to predict failure rates and reliability in the smart meter industry using Weibull analysis.