Kubling
kubling.com
- Linux
- Web
- API
- Self-hosted
What Kubling is
Kubling gives AI agents and automation a bounded model of live IT and OT state, federated directly from source systems. It makes entities, relationships, source ownership, and valid actions explicit so queries and mutations can cross databases, APIs, and infrastructure. Providers translate operations into each source’s native protocol while retaining credentials, source logic, and release cycles; Kubling handles federation, planning, and policy. The OpenAPI provider represents API operations as relational entities and maps mutations to HTTP operations. Instances can use local providers, connect to other Kubling instances, or combine both without a required central instance. Providers are independent services behind a public gRPC contract and can be written in any gRPC-capable language. The catalog lists Cassandra, Kubernetes, OpenAPI, Redis, and an in-memory provider. The provider protocol, Go SDK, and official providers are open source, but the engine is not. Kubling targets data-center, IT and platform, and industrial operations.
Who it suits
Kubling is presented for data-center operators, IT and platform teams, and industrial operations. It suits teams building federated agent workflows across multiple systems.
Good to know, and what to watch
- Federates queries across databases and APIs
- Providers retain credentials and source logic
- Public gRPC contract supports any compatible language
- No central instance is required
- OpenAPI operations map to HTTP mutations
- The engine itself is not open source
- Provider APIs and releases are pre-1.0
- Quickstart requires Git and Docker Compose v2
- Authentication relies on external systems
The verdict
Kubling provides a federated semantic layer for agents working across operational sources, with provider-based extensibility and multiple access protocols. Teams should account for its pre-1.0 provider maturity, external authentication, and required deployment tooling.
What the maker publishes
- Authentication
- The RBAC documentation says Kubling relies on external systems for authentication and authorization and has no internal IAM mechanism. source
- Authentication
- Kubling does not have an internal IAM mechanism and relies on external systems for authentication, authorization, and role reading. source
- Cross-source operations
- Queries and mutations can cross databases, APIs and infrastructure, with providers translating operations into each source’s native protocol. source
- Deployment
- Instances can use local providers, federate other Kubling instances, or do both; the site says no central instance is required. source
- Deployment
- Instances can use local providers, federate other Kubling instances, or both; the site says no central instance is required. source
- Federated queries
- Queries and mutations can cross databases, APIs, and infrastructure, with providers translating operations to each source's native protocol. source
- Integration maturity
- The provider catalog says provider APIs and releases are pre-1.0 and recommends pinning exact image versions and reviewing compatibility notes before upgrades. source
- Integrations
- The provider catalog lists Cassandra, Kubernetes, OpenAPI, and Redis integrations, plus an in-memory reference provider. source
- Intended users
- The site presents use cases for data center operations, IT and platform operations, and industrial operations. source
- Intended users
- The site describes use for data center, IT and platform, and industrial operations teams. source
- OpenAPI integration
- The OpenAPI provider exposes API operations as relational entities and maps mutations back to the API’s HTTP operations. source
- Open source boundary
- The provider protocol, Go SDK and official providers are open source; the engine is not. source
- Open source boundary
- The provider protocol, Go SDK, and official providers are open source, while the engine is not. source
- Operational model
- It makes shared entities, relationships, source ownership and valid actions explicit for agents. source
- Operational model
- The model makes entities, relationships, source ownership, policies, capabilities, and valid actions explicit. source
- Production versioning
- The quickstart recommends pinning exact Kubling and provider versions in production deployments. source
- Provider architecture
- Providers are independent services behind a public gRPC contract and can use any language that supports gRPC. source
- Provider development
- Providers are independent services behind a public gRPC contract, and teams can implement them in any language that supports gRPC. source
- Purpose
- Kubling gives AI agents and automation a bounded model of live IT and OT state, federated directly from its sources. source
- Purpose
- Kubling provides AI agents and automation with a bounded model of live IT and OT state, federated directly from source systems. source
- Quickstart
- The documented quickstart runs Kubling, Kubling Studio, and an in-memory provider in Docker Compose and requires Git, Docker Engine, and Docker Compose v2. source
- Quickstart requirements
- The documented quickstart requires Git, Docker Engine and Docker Compose v2. source
- Quickstart scope
- The quickstart runs Kubling, Kubling Studio and the official In-memory provider as a disposable Docker Compose project. source
- Security boundary
- Kubling’s agent security documentation says runtime connection credentials authenticate the Kubling-to-runtime channel and do not grant VDB or source access. source
Checked against the maker's pages on 3 Oct 2026.