An open-source ML-powered analytics engine for automated outlier detection and root cause analysis on high-dimensional metrics.
Chaos Genius is an open-source machine learning-powered analytics engine designed for automated outlier detection and root cause analysis. It helps organizations monitor and analyze high-dimensional business, data, and system metrics by segmenting datasets across key performance indicators and dimensions. The platform provides insights into what drives changes in metrics and identifies anomalies in time-series data.
Data teams, analysts, and engineers in organizations that need to monitor business metrics, system performance, or data quality at scale. It's particularly useful for those dealing with high-dimensional datasets and seeking automated root cause analysis.
Developers choose Chaos Genius for its open-source, self-hostable nature and its specialized focus on automated multidimensional drilldowns and anomaly detection. It offers a modular toolkit with multiple ML models and smart alerting, reducing the need for manual investigation of metric changes.
ML powered analytics engine for outlier detection and root cause analysis.
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.
Uses statistical filtering and A* path-based search to automatically identify key drivers of change across high-cardinality dimensions, reducing manual investigation.
Offers a toolkit with multiple ML models like Prophet, EWMA, and Greykite to handle seasonality and trends in time-series data, providing flexibility for different use cases.
Features self-learning thresholds and configurable alerts via email and Slack integration, helping combat alert fatigue with actionable insights.
Deployable via Docker with no vendor lock-in, allowing customization for specific data infrastructures and scales, as highlighted in the quick start guides.
The repository is explicitly marked as archived, meaning no bug fixes, security updates, or new features will be added, posing risks for production use.
Core functionalities like seasonality detection, automated root cause analysis, and forecasting are noted as in the roadmap, indicating they may be unfinished or unreliable.
Alerting is restricted to email and Slack only, lacking support for modern notification methods like webhooks, SMS, or other integrations, which could limit flexibility.
Requires Docker and may have significant resource demands for processing high-dimensional datasets, as suggested by its focus on scale, potentially increasing setup complexity.