📄️ Kafka
Kafka is the stream backbone for telemetry enrichment.
📄️ MQTT
MQTT is the device-facing transport (Mosquitto) and part of the ThingsBoard bridge.
📄️ PostgreSQL
This repo uses a Central PostgreSQL instance as the canonical relational datastore for multiple services.
📄️ Redis
Redis is used for sessions, cache, and cross-service ephemeral state.
📄️ Qdrant
Qdrant is the vector store used by AI/RAG components.
📄️ Zitadel
Zitadel is the identity provider (OIDC) and the foundation for SSO and role-based access.
📄️ ThingsBoard
ThingsBoard is the central IoT management platform (devices, dashboards, rule engine, RPC).
📄️ RAG (Retrieval-Augmented Generation)
RAGs provide a configurable "document memory" for the AI. In this ecosystem they are managed from the Portal Admin UI.
📄️ MCP (Model Context Protocol)
MCP services allow the AI layer to call external tools and systems. In this repo, MCPs can be executed in different modes depending on isolation and operational needs.
📄️ LLM Models
The ecosystem can connect to multiple LLM providers (cloud or local). Model configuration is managed from the Portal Admin UI.