How joshkumar50/hindsight-incident-agent works
Hindsight Incident Agent is an autonomous Kubernetes SRE platform: it observes incidents, analyzes causes, consults persistent incident memory, plans remediation, and executes or rolls back recovery. Its React dashboard exposes incident, analysis, observability, chaos, audit, and memory capabilities through a BFF. The README describes Redis Streams as the service decoupling layer; sampled code confirms the orchestrator’s RCA-to-planning calls and recovery execution’s policy and Kubernetes calls. Many specialized services are represented from the tree and README, but their internal wiring was not sampled, so those links are omitted or marked unverified.
Main entry points: client.py Redis Streams event bus · ai-orchestrator/main.py AI workflow orchestrator · execution-engine/main.py Recovery execution · App.tsx React dashboard
Components 31
Dashboard Experience
- React dashboard
ui/src/App.tsx - Incident and analysis views
ui/src/pages/IncidentCenter.tsx - Chaos console
ui/src/pages/ChaosEngineering.tsx - UI API client
ui/src/api/client.ts - Dashboard BFF
platform/dashboard-bff/main.py
Incident Intelligence
- Incident management
platform/incident-engine/main.py - AI workflow orchestrator
platform/ai-orchestrator/main.py - Root-cause analysis
platform/root-cause-analysis-engine/main.py - Incident memory
platform/knowledge-engine/main.py - Decision engine
platform/decision-engine/main.py - AI copilot
platform/ai-copilot/main.py
Recovery Control
- Recovery planner
platform/recovery-planning-engine/main.py - Recovery execution
platform/execution-engine/main.py - Policy authorization
platform/policy-engine/main.py - Kubernetes controller
platform/kubernetes-controller/main.py - Recovery verification
platform/recovery-verification-engine/main.py - Rollback engine
platform/rollback-engine/main.py
Operations and Chaos
- Chaos controller
platform/chaos-controller/main.py - Chaos scenarios
platform/chaos-scenario-manager/main.py - Chaos engine
platform/chaos-engine/main.py - Fault injection
platform/fault-injection-engine/main.py - Monitoring engine
platform/monitoring-engine/main.py - Telemetry collector
platform/telemetry-collector/main.py - Audit engine
platform/audit-engine/main.py
Shared Runtime
- Redis Streams event bus
pkg/eventbus/client.py - Shared service foundations
pkg/core - Anomaly math
pkg/math_engine/anomaly.py
Other components
- SRE operator
- Hindsight memory service
- Prometheus
- Target microservices
apps
Connections 34
- SRE operator → React dashboard: uses
README.md - React dashboard → Incident and analysis views: renders
- React dashboard → Chaos console: renders
- Incident and analysis views → UI API client: requests data
- Chaos console → UI API client: requests data
ui/src/pages/ChaosEngineering.tsx - UI API client → Dashboard BFF: calls API
README.md - Dashboard BFF → AI copilot: requests explanations
README.md - Dashboard BFF → Incident management: reads incidents
README.md - Redis Streams event bus → AI workflow orchestrator: delivers events
README.md - AI workflow orchestrator → Root-cause analysis: requests analysis
platform/ai-orchestrator/main.py - AI workflow orchestrator → Incident memory: searches history
platform/ai-orchestrator/main.py - AI workflow orchestrator → Decision engine: evaluates decision
platform/ai-orchestrator/main.py - AI workflow orchestrator → Recovery planner: requests plan
platform/ai-orchestrator/main.py - AI workflow orchestrator → Hindsight memory service: recalls and retains
platform/ai-orchestrator/main.py - Incident memory → Hindsight memory service: searches and stores
platform/knowledge-engine/main.py - AI workflow orchestrator → Redis Streams event bus: publishes decisions
platform/ai-orchestrator/main.py - Redis Streams event bus → Recovery execution: delivers recovery plans
platform/execution-engine/main.py - Recovery execution → Policy authorization: checks authorization
platform/execution-engine/main.py - Recovery execution → Kubernetes controller: requests changes
platform/execution-engine/main.py - Recovery execution → Redis Streams event bus: publishes recovery status
platform/execution-engine/main.py - Redis Streams event bus → Rollback engine: delivers failures
platform/rollback-engine/main.py - Rollback engine → Kubernetes controller: requests undo
platform/rollback-engine/main.py - Rollback engine → Redis Streams event bus: publishes rollback status
platform/rollback-engine/main.py - Redis Streams event bus → Chaos controller: delivers recovery events
platform/chaos-controller/main.py - Chaos controller → Redis Streams event bus: publishes chaos events
platform/chaos-controller/main.py - Redis Streams event bus → Monitoring engine: delivers telemetry events
platform/monitoring-engine/main.py - Monitoring engine → Prometheus: queries metrics
platform/monitoring-engine/main.py - Telemetry collector → Redis Streams event bus: publishes telemetry
platform/telemetry-collector/main.py - Chaos scenarios → Chaos controller: configures experiments
- Chaos engine → Target microservices: injects chaos
- Fault injection → Target microservices: injects faults
- Audit engine → Redis Streams event bus: records events
platform/audit-engine/main.py - Shared service foundations → Redis Streams event bus: supports services
pkg/eventbus/client.py - Monitoring engine → Anomaly math: uses calculations