The execution layer between an agent's intent and the physical world — 36 multi-protocol drivers sense the field, Spring AI brings LLMs in, so agents can see, understand, decide, act, and trace every execution. Multi-tenant, edge-to-cloud, fully open source.
AI should not only understand the world — it should act in it, safely. IoT DC3 is an open-source Physical AI Runtime for industrial IoT (AGPL-3.0): the execution layer between an agent's intent and the physical world. Models reason; IoT DC3 handles sensing, connectivity, governance, and execution.
36 driver modules pull data up from heterogeneous devices and normalize it into semantically labeled point values; Spring AI plugs large language models into operations. The result is a complete loop for agents: see (devices, telemetry, alarms) → understand (physical signals structured into model-ready context) → decide (models reasoning with industrial rules and history) → act (commands issued through permission, whitelist, and risk-tier policy gates) → trace (a full audit trail from intent to execution and feedback).
For the full product vision see dc3.site. It's a good fit for teams that need to connect many industrial protocols, manage devices and points, query real-time and historical data, and build on the platform within the Spring ecosystem — including letting AI take part in operations, safely. To understand the problem it solves and how it compares to alternatives, start with the pitch.
The platform is one gateway, four center services, and a set of protocol drivers. Only the gateway's HTTP port faces outward; the centers talk to each other over gRPC, and drivers and the data center are decoupled through RabbitMQ.
For how each hop works and why it's designed that way, see Architecture.
dc3-web/ directory of this repo; the standalone iot-dc3-web repo is archived)See Technology Stack for the full breakdown.
IoT DC3 is open source under the AGPL-3.0 License. For licensing details and commercial licensing, see LICENSE.txt.