Local models via LM Studio
Use LM Studio in your coding tools
Step-by-step setup for LM Studio in 11 coding tools: Aider, Claude Code, Cline, Codex CLI, Continue, GitHub Copilot, Goose, Kilo Code, OpenCode, Roo Code and Zed. Every step comes from official docs, read on .
LM Studio setup guides
- Documented by AiderUse LM Studio in AiderAider documents LM Studio through the lm_studio/ model prefix plus the LM_STUDIO_API_KEY and LM_STUDIO_API_BASE environment variables.localhost3 steps
- Documented by LM StudioUse LM Studio in Claude CodeLM Studio documents a Claude Code integration through its Anthropic-compatible POST /v1/messages endpoint. You set ANTHROPIC_BASE_URL to the local LM Studio server, then run claude with a local model id.localhost4 steps
- Documented by ClineUse LM Studio in ClineCline has a built-in LM Studio provider, documented on its Local models page. You start the LM Studio server, select LM Studio as the provider, keep the base URL http://localhost:1234 and pick a model.localhost5 steps
- From LM Studio and Codex CLI docsUse LM Studio in Codex CLICodex ships a built-in lmstudio provider for OSS mode and talks to LM Studio through its OpenAI-compatible POST /v1/responses endpoint. Run codex --oss, optionally with -m to choose a model, and set oss_provider = "lmstudio" to make it the default.localhost4 steps
- Documented by ContinueUse LM Studio in ContinueContinue has a top-level lmstudio provider in config.yaml. Its default apiBase is http://localhost:1234/v1.localhost3 steps
- From LM Studio and GitHub Copilot docsUse LM Studio in GitHub CopilotVS Code chat (GitHub Copilot) supports bring-your-own-key models through the Custom Endpoint provider, which speaks Chat Completions, Responses or Messages. LM Studio documents OpenAI-compatible /v1/chat/completions and /v1/responses plus Anthropic-compatible /v1/messages at http://localhost:1234, so you combine the two.localhost6 steps
- Documented by GooseUse LM Studio in GooseGoose 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.localhost4 steps
- Documented by Kilo CodeUse LM Studio in Kilo CodeKilo Code has a built-in lmstudio provider that needs no API key. You add it in Settings > Providers, and unlisted models can be registered in kilo.json.4 steps
- Documented by OpenCodeUse LM Studio in OpenCodeThe OpenCode providers docs include an LM Studio section. It registers LM Studio as an @ai-sdk/openai-compatible provider in opencode.json, pointed at http://127.0.0.1:1234/v1.127.0.0.13 steps
- Documented by Roo CodeUse LM Studio in Roo CodeRoo Code has a built-in LM Studio API provider that connects to LM Studio's OpenAI-compatible local server at http://localhost:1234 by default.localhost5 steps
- Documented by ZedUse LM Studio in ZedZed has a built-in LM Studio provider for the Zed Agent, Inline Assistant and similar features. You download a model, start the LM Studio API server, and pick an LM Studio model in the dropdown.5 steps
No verified LM Studio guide yet for Cursor. We only publish a pairing once official docs cover it.
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.