01 / capability
Model catalog and compatibility discovery
Available through the product surface and the machine interfaces, with permission attached.
Workspace & infrastructure · Concept
Own the workspace your agents work in.
A private model discovery, deployment, inference and routing platform for organizations running AI models on their own infrastructure.
01
What it is
LocalModels is built for AI engineers, developers, enterprise platform teams.
The problem
LocalModels replaces disconnected local model tools, manual inference setup and unmanaged model installations.
The approach
A private model discovery, deployment, inference and routing platform for organizations running AI models on their own infrastructure.
The boundary
Work stays inside an explicit scope: named sources, defined permissions, bounded execution, retained evidence.
02
Capabilities
Five contracts the product is specified around. Each one is a boundary as much as a feature.
02 / capability
Quantization and device-aware deployment
Exposed as a scoped capability with its own evidence trail, not a hidden setting.
03 / capability
Inference endpoint management
Defined as an explicit contract so operators can review it before it runs.
04 / capability
Evaluation and routing
Available through the product surface and the machine interfaces, with permission attached.
05 / capability
SDK, API, MCP and CLI access
Available through the product surface and the machine interfaces, with permission attached.
03
How it works
The same three steps apply whether a person or an agent is driving.
01
Define the scope
Start from the boundary LocalModels is allowed to act inside: the workspace, the sources, the budget, the authority.
02
Connect the surfaces
Expose the same capability through the interface a human uses and the interface an agent calls, with one permission model.
03
Act with evidence
Every action leaves a record that can be inspected, replayed and challenged before the next one runs.
Read the specification before you believe the category.
LocalModels is documented as a concept: requirements, interfaces and evidence expectations. It is not presented as a live service.