Inspect and configure the Local LLM provider.

Synopsis

local-llm [status|discover]

Description

Connects SLICC to any OpenAI-compatible local server (Ollama, LM Studio, llama.cpp, vLLM, mlx_lm.server, Jan, LocalAI). Configure the base URL in Settings -> Providers -> Local LLM, then run 'local-llm discover' to populate the model list automatically.

Options

status Show current config and verify connection (same as no args).

discover Probe the server and save discovered model IDs.

Examples

$ local-llm

Show current config and connection status.

$ local-llm discover

Probe the configured server for available models.

Notes

Common base URLs: Ollama http://localhost:11434/v1, LM Studio http://localhost:1234/v1, llama.cpp http://localhost:8080/v1, vLLM http://localhost:8000/v1, Jan http://localhost:1337/v1.

See Also

models, hf