Setup guide - Documented by Goose
Use LM Studio in Goose
Goose has a built-in LM Studio provider that connects to localhost:1234 and needs no API key. You configure it from goose Desktop or with goose configure.
Last verified 4 steps1 official source
Steps
- Step 1.
Download and install LM Studio, download a model that supports tool calling (e.g., Qwen, Llama, or Mistral variants), and start the local server. It runs on
http://localhost:1234by default. - Step 2.
goose Desktop: open the sidebar, click Settings, open the Models tab, click Configure providers, choose LM Studio and click Configure, click Submit (no API key is needed), then select the model you have loaded in LM Studio.
- Step 3.
goose CLI: run goose configure, select Configure Providers, choose LM Studio as the provider, and enter the model name that matches the model loaded in LM Studio.
Terminalgoose configure - Step 4.
Example CLI session from the docs.
Snippet┌ goose-configure │ ◇ What would you like to configure? │ Configure Providers │ ◇ Which model provider should we use? │ LM Studio │ ◇ Enter a model from that provider: │ qwen2.5-7b-instruct │ └ Configuration saved successfully
Caveats
- Goose tip: make sure the model name you enter in goose matches the model identifier shown in LM Studio's server panel.
- Source is the official goose docs markdown in the aaif-goose/goose GitHub repo. It is published at goose-docs.ai/docs/getting-started/providers/, but that host was not directly fetched.
More setup guides
Same tool, other providers
Related reading
- LM Studio Bionic: A Local-First AI Agent for Open ModelsLM Studio launches Bionic, a standalone agent harness for open models with local inference, voice input, and zero data retention cloud options.
- Ollama vs LM Studio vs vLLM vs llama.cpp: Picking a Local Runtime for Coding AgentsOllama vs LM Studio vs vLLM vs llama.cpp for coding agents: what each local runtime is for, where they overlap, and which to pick for your setup.
- Goose: The Open Source AI Agent With 70+ MCP ExtensionsGoose is an open-source Rust AI agent with a desktop app, CLI, and API that works across 15+ LLM providers and 70+ MCP extensions. Here is where it fits.
FAQ
How do I use LM Studio in Goose?
Goose has a built-in LM Studio provider that connects to localhost:1234 and needs no API key. You configure it from goose Desktop or with goose configure.
Which LM Studio model ids work in Goose?
The official docs read for this guide list qwen2.5-7b-instruct. Requests go to http://localhost:1234.
Is this an official LM Studio and Goose setup?
Goose documents this setup in its own docs. It was last checked against 1 official page on October 17, 2026.
Sources
Last verified against 1 official page.
Newsletter
New models, set up the day they ship
One email per week. New model releases, the coding tools that support them and how to wire them up.