How mayurzope06/intelligent-aiops works
Intelligent AIOps is an SRE command center for observing a commerce microservice cluster, correlating telemetry into incidents, diagnosing causes, and coordinating operator-approved remediation verified against live metrics. The main workflow runs from the React console through the backend’s telemetry and correlation logic to diagnosis or service actions, then returns incident and audit state to the console. The README documents broader capabilities than the sampled excerpts; edges for those capabilities are included only where the README or source supports them.
Main entry points: index.js AIOps API · App.jsx Operations Console · src/server.js Order Service · src/server.js API Gateway
Components 25
SRE Console
- Operations Console
frontend/src/App.jsx - Topology Canvas
frontend/src/components/TopologyView.jsx - Incident View
frontend/src/components/IncidentsView.jsx - RCA Modal
frontend/src/components/RCAModal.jsx - Progress HUD
frontend/src/components/AsyncProgressHUD.jsx
AIOps Core
- AIOps API
backend/index.js - Dependency Topology
backend/config/topology.js - Prometheus Adapter
backend/adapters/prometheusAdapter.js - Loki Adapter
backend/adapters/lokiAdapter.js - Signal Correlation
backend/engine/correlationEngine.js - AI Reasoning
backend/engine/aiReasoning.js - Runbook Retrieval
backend/rag/ragEngine.js - Incident Manager
backend/services/incidentManager.js - Local State
backend/services/storage.js - Runbook Files
backend/rag
Commerce Cluster
- API Gateway
services/gateway-service/src/server.js - Auth Service
services/auth-service/src/server.js - Order Service
services/order-service/src/server.js - Inventory Service
services/inventory-service/src/server.js - Payment Service
services/payment-service/src/server.js
Observability Services
- Prometheus
- Loki
Other components
- SRE Operator
- MongoDB Cluster
- Google Gemini
Connections 34
- SRE Operator → Operations Console: operates
- Operations Console → AIOps API: queries and commands
- Operations Console → Topology Canvas: renders
- Operations Console → Incident View: renders
- Operations Console → RCA Modal: shows diagnosis
- Operations Console → Progress HUD: shows progress
- AIOps API → Dependency Topology: reads graph
- AIOps API → Prometheus Adapter: queries telemetry
- AIOps API → Signal Correlation: correlates signals
- Signal Correlation → Prometheus Adapter: queries metrics
- Signal Correlation → Loki Adapter: fetches errors
- AIOps API → AI Reasoning: requests diagnosis
- AI Reasoning → Runbook Retrieval: retrieves context
- Runbook Retrieval → Runbook Files: reads and indexes
- AI Reasoning → Google Gemini: generates RCA
- AIOps API → Incident Manager: manages incidents
- Incident Manager → Local State: reads and writes
- AIOps API → API Gateway: injects and remediates
- AIOps API → Auth Service: injects and remediates
- AIOps API → Order Service: injects and remediates
- AIOps API → Inventory Service: injects and remediates
- AIOps API → Payment Service: injects and remediates
- API Gateway → Auth Service: verifies identity
- API Gateway → Order Service: forwards checkout
- Order Service → Inventory Service: reserves stock
- Order Service → Payment Service: charges payment
- Payment Service → MongoDB Cluster: uses database
- Prometheus → API Gateway: scrapes metrics
- Prometheus → Auth Service: scrapes metrics
- Prometheus → Order Service: scrapes metrics
- Prometheus → Inventory Service: scrapes metrics
- Prometheus → Payment Service: scrapes metrics
- Prometheus Adapter → Prometheus: queries API
- Loki Adapter → Loki: queries logs