Skip to main content

🏠 Hestia

Operations & Infrastructure Agent | Domain: Operations

Guardian of the hearth monitoring system health, infrastructure, and operational metrics.

Overview​

KOSMOS V2.0 Hestia Agent - Operations & Infrastructure

Hestia handles all operational tasks including system monitoring, infrastructure management, and operational workflows.

Upgraded to LangGraph base with:

  • State persistence (checkpointing)
  • HITL for critical operations
  • Semantic router integration
  • SDUI operations dashboard components
  • Docker/Kubernetes MCP integration
Auto-Generated

This documentation is automatically extracted from source code. Source: implementation/backend/agents/hestia.py (665 lines)

Enumerations​

ServiceStatus​

Service health status.

MemberValue

AlertSeverity​

Alert severity levels.

MemberValue

OperationType​

Types of operations.

MemberValue

HestiaState​

State for Hestia operations workflow.

Extends base state with operations-specific fields.

Inherits from: AgentGraphState

HestiaAgent​

Hestia - Operations & Infrastructure Agent

Responsibilities:

  • Monitor system health and metrics
  • Manage deployments and rollbacks
  • Handle scaling operations
  • Process and route alerts
  • Manage backups and recovery
  • Coordinate with infrastructure

MCP Servers:

  • (would use kubernetes-mcp, docker-mcp in production)

SDUI Components:

  • GlassHealthDashboard: System status
  • GlassAlertPanel: Active alerts
  • GlassMeter: Resource utilization

Inherits from: <ast.Subscript object at 0x7fe8022f6980>

Methods​

__init__()​

create_state_class() → type​

Return HestiaState for workflow.

define_nodes() → Dict[str, Callable]​

Define Hestia-specific workflow nodes.

define_edges() → List[tuple]​

Define Hestia-specific workflow edges.

async get_system_status() → Dict[str, Any]​

Get overall system status.

async trigger_alert(severity: str, source: str, message: str) → None​

Trigger an operational alert.