Documentation
Architecture
OpsOrch consists of four main layers working together to provide a unified operational experience.
System Overview
Experience Layer
Orchestration & Tools
Adapter Layer
External Systems
1. API Substrate
OpsOrch Core
- • Stateless Go orchestration service
- • Unified REST APIs
- • Provider/plugin loading
- • Secret management
- • Zero data storage
- • Orchestration plans & runs
2. MCP Tools Layer
opsorch-mcp
- • TypeScript MCP server
- • Typed tools for LLMs
- • stdio & HTTP transports
- • 15+ operational tools
3. Ops Copilot
opsorch-copilot
- • LLM-driven planning runtime
- • Multi-step reasoning
- • Human-in-the-loop
- • Evidence-based answers
- • Runbook recommendations
4. Control Plane
opsorch-console (Open Source)
- • Unified incident, alert & ticket management
- • Advanced log & metric visualization
- • Service catalog & dependency mapping
- • Team management & organizational structure
- • AI-powered Copilot chat (Enterprise)
- • Runbook execution & step tracking
Design Principles
- Single API Surface
One unified API for incidents, alerts, timelines, logs, metrics, tickets, messaging, services, teams, deployments, and orchestration.
- Config-driven Routing
Providers are selected per capability via environment variables, allowing easy swapping of backend tools without code changes.
- Zero Operational Data Storage
OpsOrch Core does not store your operational data. It routes queries to your source-of-truth systems in real-time.
- Deep-linkable Evidence
Normalized resources carry provider URLs so UIs can jump directly to the original tool without copying data.
- Runbook-first Orchestration
Plans and runs stay in your workflow engine while OpsOrch surfaces execution state and manual steps.
- Security-first
Pluggable secret backends (Vault, KMS), environment-scoped queries, and comprehensive audit logs.