Kubling
kubling.com
What it is
Kubling gives AI agents and automation a bounded model of live IT and OT state, federated directly from source systems. It defines shared entities, relationships, source ownership, and valid actions 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 exposes API operations as relational entities and maps mutations to HTTP operations. Instances can use local providers, federate other Kubling instances, or do both, with no central instance required. Providers are independent services behind a public gRPC contract and can be written in any gRPC-supported 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. Quickstart requires Git, Docker Engine, and Docker Compose v2. Provider APIs are pre-1.0; exact versions are recommended.
Spec sheet
- Purpose
- Kubling provides AI agents and automation with a bounded model of live IT and OT state, federated directly from source systems.Read 3 Oct 2026 · kubling.com
- Intended users
- The site describes use for data center, IT and platform, and industrial operations teams.Read 3 Oct 2026 · kubling.com
- Deployment
- Instances can use local providers, federate other Kubling instances, or both; the site says no central instance is required.Read 3 Oct 2026 · kubling.com
- Integrations
- The provider catalog lists Cassandra, Kubernetes, OpenAPI, and Redis integrations, plus an in-memory reference provider.Read 3 Oct 2026 · docs.kubling.com
- Authentication
- Kubling does not have an internal IAM mechanism and relies on external systems for authentication, authorization, and role reading.Read 3 Oct 2026 · docs.kubling.com
- Cross-source operations
- Queries and mutations can cross databases, APIs and infrastructure, with providers translating operations into each source’s native protocol.Read 2 Oct 2026 · kubling.com
- Federated queries
- Queries and mutations can cross databases, APIs, and infrastructure, with providers translating operations to each source's native protocol.Read 3 Oct 2026 · kubling.com
- 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.Read 3 Oct 2026 · docs.kubling.com
- Open source boundary
- The provider protocol, Go SDK, and official providers are open source, while the engine is not.Read 3 Oct 2026 · kubling.com
- OpenAPI integration
- The OpenAPI provider exposes API operations as relational entities and maps mutations back to the API’s HTTP operations.Read 2 Oct 2026 · kubling.com
- Operational model
- The model makes entities, relationships, source ownership, policies, capabilities, and valid actions explicit.Read 3 Oct 2026 · kubling.com
- Production versioning
- The quickstart recommends pinning exact Kubling and provider versions in production deployments.Read 3 Oct 2026 · docs.kubling.com
- Provider architecture
- Providers are independent services behind a public gRPC contract and can use any language that supports gRPC.Read 3 Oct 2026 · kubling.com
- Provider development
- Providers are independent services behind a public gRPC contract, and teams can implement them in any language that supports gRPC.Read 2 Oct 2026 · kubling.com
- 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.Read 3 Oct 2026 · docs.kubling.com
- Quickstart requirements
- The documented quickstart requires Git, Docker Engine and Docker Compose v2.Read 2 Oct 2026 · docs.kubling.com
- Quickstart scope
- The quickstart runs Kubling, Kubling Studio and the official In-memory provider as a disposable Docker Compose project.Read 2 Oct 2026 · docs.kubling.com
- 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.Read 2 Oct 2026 · docs.kubling.com
- Source ownership
- Providers retain their credentials, source logic and release cycle while Kubling handles federation, planning and policy.Read 2 Oct 2026 · kubling.com
- Transport security
- Kubling's HTTP endpoints can be secured with TLS by configuring a certificate at the application level.Read 3 Oct 2026 · docs.kubling.com
Strong points and limits
Strong points
- Federates queries across databases, APIs, and infrastructure
- Providers retain source credentials and logic
- No central instance is required
- Public gRPC contract supports multiple languages
- Includes Cassandra, Kubernetes, OpenAPI, and Redis providers
Limits
- The Kubling engine is not open source
- Quickstart requires Git and Docker Compose v2
- Provider APIs and releases are pre-1.0
- No internal IAM mechanism
Who it suits
It suits data center, IT and platform, and industrial operations that need federated state for agents or automation. Teams should be comfortable with Docker Compose, external authentication, and pre-1.0 provider releases.
Verdict
Kubling presents a federated semantic layer for agent operations across varied systems. Its split between open-source providers and a non-open engine, plus external authentication and pre-1.0 integrations, is central to evaluation.
Where Specifiction places it
- Data Virtualization Software#16 of 257.5