01
Who calls it?
Several applications, teams or an AI assistant point to the server. One application that owns the workflow points to the runtime.
Products
One engine, two delivery forms.
The same document processing, retrieval and inference stack, packaged for two different jobs. Deploy it as a private AI service, or compile it into your own application. Most teams end up using both, and they share a licence.
A service to run, or a library to ship.
The question is not which product is more capable. It is whether the intelligence belongs beside your applications or inside one of them.
Deploy
LM-Kit One
A private AI server. Install it, point it at your documents, and reach it over HTTP, over MCP from an AI assistant, or through its admin console. Chosen when several teams or tools need the same private capability, and when operators need something they can watch and govern. Currently in Business Preview.
See LM-Kit OneEmbed
LM-Kit.NET
The local AI runtime for .NET. One NuGet, in process, no sidecar and no second runtime to deploy. Chosen when the AI has to travel with your product, run on a customer machine, work offline, or sit inside a workflow where a network hop is not acceptable.
See LM-Kit.NETFour questions that usually settle it.
Answer these and the choice tends to make itself. If two answers point in different directions, that is a sign you want both, which is a supported and common shape.
02
Where does it run?
Hardware you administer favours the server. A machine belonging to your customer, or a desktop application you ship, favours the runtime.
03
Who operates it?
If somebody needs a console, access tokens and request history, that is the server. If operations means your existing application logs, that is the runtime.
04
Is a network hop acceptable?
Usually yes, and the server is simpler. When it is not, because of latency, offline operation or an air gap inside the product itself, the runtime is the answer.
Free for small teams. Commercial above the line.
One license, both products, no activation key. Nothing checks a license at runtime. Evaluation and development are free at any company size, with no time limit.
Free
$0no key, no expiry
The complete SDK and the complete server, including commercial use and redistribution, for small companies. Evaluation and development stay free at any size.
- Under $1M USD annual gross revenue
- 10 or fewer employees
- No more than $3M USD raised from outside investors
- Always free: personal, education, nonprofits, open source
Professional
Customannual, scaled to scope
Required above the thresholds. Scaled to deployment size, never metered by tokens, seats or end users. Carries the assurance a production deployment needs.
- Commercial use and redistribution at any scale
- Long-term support builds and security patches
- Support with response-time commitments
- Unlimited developers and end users
Get started