Lmstudio Local — Development agent for Claude Code
A locally-hosted model served through LM Studio's OpenAI-compatible API.
How to install Lmstudio Local
Installs to ~/.claude/agents/plainjane20-muster-lmstudio-local.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/PlainJane20/muster/HEAD/agents/lmstudio-local.md -o ~/.claude/agents/plainjane20-muster-lmstudio-local.md Restart Claude Code, or start a new session, for it to be picked up.
What Lmstudio Local does
id: lmstudio-local name: LM Studio Local Model runtime: lm_studio tool_access: read_only tags:
- local
- offline
- private risk_tier: low
A locally-hosted model served through LM Studio's OpenAI-compatible API, for offline/private text generation with no tool access -- same shape as local-llama (Ollama). Documented-only adapter -- no LM Studio server was running in the environment this was built in.
Alternatives in Development
- Svelte Abstraction Review — Reviews a feature segment in any SvelteKit app (apps/moderator, apps/auth, apps/creator-studio) for duplicatio 7.2k ★
- Gemini Skills — Skills for the Gemini API, SDK and model/agent interactions 2.3k ★
- Codex Orchestrator — CLI tool for delegating tasks to GPT Codex agents via tmux sessions 263 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Local Worker
Coding worker on a local model (Ollama, LM Studio, vLLM) served by the multi-model gateway's upstream. Use whe
Openrouter Agent
Runs a model from any of ~60 vendors through OpenRouter's OpenAI-compatible endpoint, billed per token against
Ollama Agent
Runs a local model served by Ollama on this machine. One mode - consult (no machine access; the endpoint is a
Bench Runner
Executes a11y skill benchmarks across hosted and local model families. Runs cloud/Codex/Ollama benchmark scrip
Opencode
Coding subagent that runs inside opencode, on any provider and model opencode supports (OpenAI, Google, Moonsh
Claude Context Local
Code search MCP for Claude Code. Make entire codebase the context for any coding agent. Embeddings are created
Related Skills
Fallback
Show or change hmd's OmniRoute fallback-routing gate — whether Heimdall may route work to a third-party model,
Afm Studio
Apple's on-device foundation model as a Mac app, a CLI, an MCP server for Claude, and a local OpenAI-compatibl
Setup Lmstudio VSCode
Set up a fully local coding model in VS Code on an Apple Silicon Mac (LM Studio MLX engine, no admin), with au