kubeshark/kubeshark
Kubeshark provides eBPF-powered network observability for Kubernetes, indexing L4/L7 traffic with full K8s context and decrypting TLS, queryable by AI agents and humans.
Awesome AI for Infra › Root Cause Analysis
scitix/siclaw
Siclaw is an AI-powered SRE platform focused on read-only infrastructure diagnostics. Its core purpose is to assist DevOps and SRE teams in gathering evidence, forming and validating hypotheses, and conducting root-cause analysis without directly modifying the environment. Users can describe problems in plain language, and Siclaw, acting as an AI agent, will investigate from the terminal, web UI, or chat channels. Key features include a 4-phase Deep Investigation workflow, Investigation Memory to learn from past incidents, and the ability to turn diagnostic playbooks into reusable runbooks. The platform is extensible via the Model Context Protocol (MCP) to connect external tools and data sources. Siclaw supports multi-channel access and offers various deployment profiles, including a personal TUI mode, a local server with a web UI backed by SQLite, and a planned production Kubernetes deployment. The architecture includes a control plane (Portal + Gateway + shared DB) for managing agents, skills, and knowledge, and isolated AgentBoxes for running investigations. The project emphasizes safe, read-only operations for complex IT environments.
https://github.com/scitix/siclaw
Also in Root Cause Analysis
Tracer-Cloud/opensre
OpenSRE is an open-source framework for building, training, and evaluating AI SRE agents specifically designed for incident investigation and response, running on your own infrastructure.
HolmesGPT/holmesgpt
HolmesGPT is an open-source AI agent for SRE that investigates production incidents, finds root causes, and can automatically identify and fix problems 24/7.
derisk-ai/OpenDerisk
OpenDeRisk is an AI-native risk intelligence system providing 24/7 comprehensive protection for application systems through multi-agent collaboration for deep root cause analysis.
tangpan360/MicroRCA-Agent
MicroRCA-Agent is an LLM-agent-based solution for microservice root cause localization and fault analysis, processing multi-modal Log, Trace, and Metric data.
cuebook/CueObserve
CueObserve is an open-source platform for time-series anomaly detection and root cause analysis directly on data warehouses, designed to monitor key metrics and identify causative factors.
shaido987/riskloc
RiskLoc is an AI-powered method for localizing multi-dimensional root causes in time-series data, identifying the specific dimensions and values contributing to anomalies.
openrca/orca
OpenRCA provides automated root cause analysis for Kubernetes clusters by constructing a real-time topology graph enriched with telemetry data from various sources.