CompassAI Overview
Federal Frontier CompassAI — the digital twin UI for infrastructure visibility, AI-powered queries, and graph visualization across the Federal Frontier Platform.
CompassAI is the Federal Frontier Platform’s digital twin user interface. It provides platform operators with a unified view of infrastructure state by querying the Federal Frontier Ontology (FFO) — a TypeDB knowledge graph that models clusters, nodes, deployments, services, findings, images, and their relationships.
URL: https://compass.vitro.lan
| Current versions: API v5.13.79 | Frontend v5.1.17 |
Capabilities
CompassAI provides five primary capabilities for platform operators:
| Capability | Description |
|---|---|
| AI Chat | Natural language queries against infrastructure state, served through the Frontier llm-router service (self-hosted and commercial frontier models) and 283 MCP tools |
| Instance Graph | Interactive ReactFlow visualization of FFO entities and relationships |
| Storage Dashboard | Ceph cluster health, pool usage, OSD status, and monitor visibility |
| Workitem Tracking | View and manage workitems associated with deployments and findings |
| MCP Integration | Access to 16 MCP servers exposing 283 tools across the platform |
Architecture
CompassAI is composed of two independently deployed components:
Next.js + BPJS
Port 3000/nginx] --> API[CompassAI API
FastAPI
Port 8000] API --> DB[TypeDB
FFO] API --> MCP[16 MCP Servers
283 tools] style FE fill:#2d3748,stroke:#4299e1,color:#e2e8f0 style API fill:#2d3748,stroke:#4299e1,color:#e2e8f0 style DB fill:#2c7a7b,stroke:#38b2ac,color:#e2e8f0 style MCP fill:#1a365d,stroke:#4299e1,color:#e2e8f0
Frontend
The frontend is a Next.js application using BlueprintJS as the component library. It renders the chat interface, instance graph, storage dashboard, and workitem views. The frontend communicates exclusively with the CompassAI API — it never queries TypeDB or MCP servers directly. For component conventions and design system documentation shared across all FFP applications, see FFP UI Design System.
API
The CompassAI API is a Python FastAPI application that serves as the backend for all CompassAI functionality. It handles:
- Chat processing — Pattern-matching queries for instant results, LLM-based queries for everything else
- TypeDB queries — All FFO reads and writes go through the API’s TypeDB driver connection
- MCP tool invocation — The API maintains connections to 16 MCP servers and orchestrates tool calls on behalf of the LLM
- Remuda — Operators register MCP servers as forwards; agents discover and invoke tools through the Remuda endpoint
MCP Server Integration
CompassAI integrates with 16 MCP servers that collectively expose 283 tools. Those servers are registered as forwards in Remuda. Agents discover and invoke tools through the Remuda endpoint. When the LLM determines it needs external data to answer a query, it selects appropriate tools from the available set and the API executes the calls.
The MCP servers span infrastructure domains including:
- FFO (ontology queries)
- Keycloak (identity and access)
- OpenStack / Kolla (compute and networking)
- Ceph (storage)
- Kubernetes (workload orchestration)
- ArgoCD (GitOps)
- And others
Related Documentation
- AI Chat Interface — Query templates and LLM-powered chat
- Instance Graph — Entity and relationship visualization
- Storage Dashboard — Ceph monitoring
- Deploying CompassAI — Build, push, and deploy
- Configuration Reference — Environment variables and tuning