lmstudio-ai/lms

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

5232 stars · 446 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

lms is the official command-line tool for LM Studio, built on the lmstudio.js SDK. It lets users manage local LLMs (list, download, load, unload), start and stop LM Studio's local API server, stream logs, and scaffold SDK projects from the terminal.

Use cases

• start and stop the LM Studio local API server from the terminal
• list downloaded and loaded models in human or JSON format
• load or unload models with GPU acceleration for scripting
• download a model from the command line with lms get
• stream LM Studio logs for debugging
• scaffold a new project using the LM Studio SDK
• script local LLM workflows in shell scripts or CI

When to choose

• you use LM Studio and want to manage models or its server from the terminal
• you need machine-readable JSON output to script local LLM workflows
• you want to automate model loading/unloading around local inference jobs
• you're bootstrapping a TypeScript or Python project against LM Studio's SDKs

When to avoid

• you don't use LM Studio and want a standalone inference engine like llama.cpp or Ollama
• you need a GUI for model management rather than a CLI
• you want to chat with models directly - use the LM Studio app or SDKs instead

Facets

cli-tool · maturity active

cli llm-inference developer-tools http-server large-language-models developer-tools artificial-intelligence cli cross-platform windows lm-studio local-llm model-management local-server typescript command-line nodejs macos linux

Member repositories

For agents

markdown · JSON · MCP: product_card(name="lmstudio-ai/lms")