Model Runtimes
lnk model runtime manages the local inference servers Local Link discovers. Add the server you are building at its own address so your agent can use it while you restart and develop it.
Use a model at its own address
A model served on a port of its own is then a model like Ollama's.
lnk agent start --model.default <model> uses it.
lnk model runtime add http://localhost:5000 --name mymodellnk model runtime remove mymodelCheck What Your Server Answers
Your server needs to answer OpenAI's /v1/models and
/v1/chat/completions, as vLLM and llama.cpp do. Local Link adds only an
address on this machine, which is localhost, 127.0.0.1 or [::1].
While nothing answers there, list shows it as not answering.
List Runtime Servers
lnk model runtime list shows discovered and added servers, including added addresses that are not answering. lnk model list lists their model names. Use lnk model runtime list when you need a server's address.