LM-Kit Launches Private AI Application Server LM-Kit One for Local Deployment

On September 15, 2026, LM-Kit, part of the Calico IIM group, announced the general availability of LM-Kit One, a private AI application server for Windows, Linux and macOS. The product is designed for organizations that want to build AI capabilities inside their own environment and for software vendors deploying AI alongside their applications.

LM-Kit One combines model execution, document processing, retrieval, agents and operational controls in a single product. Teams can extract structured data from documents, build assistants that answer from internal knowledge with source references, and automate work through agents with explicit tool permissions. All components are maintained and released together.

For data control, fully local deployments run without an external AI service once models are provisioned and external tools and optional telemetry are disabled. The server does not send customer documents, prompts, results or usage telemetry to LM-Kit. Administrators control models, access policies and agent permissions, with logs and metrics retained locally. Connections to external tools or assistants are optional.

Deployments can start on a single machine and scale to multiple nodes behind a load balancer, with shared databases and storage. Kubernetes is optional; virtual machines and Windows services are also supported. Applications integrate through native REST endpoints, OpenAI-, Anthropic- and Ollama-compatible interfaces, or the Model Context Protocol (MCP). LM-Kit One has run within Calico IIM for more than a year, and the group serves over 600 customers. Evaluation and development are free with no time limit; production use is free for eligible small businesses.