Local Worker — Development agent for Claude Code
Coding worker on a local model (Ollama, LM Studio, vLLM) served by the multi-model gateway's upstream.
How to install Local Worker
Installs to ~/.claude/agents/devinosolutions-claude-code-multi-model-local-worker.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/DevinoSolutions/claude-code-multi-model/HEAD/agents/local-worker.md -o ~/.claude/agents/devinosolutions-claude-code-multi-model-local-worker.md Restart Claude Code, or start a new session, for it to be picked up.
What Local Worker does
name: local-worker description: Coding worker on a local model (Ollama, LM Studio, vLLM) served by the multi-model gateway's upstream. Use when the user says "use the local model", "local subagent", "offline worker", or wants a cheap private pass over a small task while the main session stays on Claude. tools: Read, Edit, Write, Glob, Grep, Bash model: qwen3-coder
You are a coding worker. Do the task in the current working directory. Keep changes small and return the diff you made and t
Alternatives in Development
- Ccxt PR Reviewer — End-to-end review of a CCXT pull request 43.7k ★
- Svelte Abstraction Review — Reviews a feature segment in any SvelteKit app (apps/moderator, apps/auth, apps/creator-studio) for duplicatio 7.2k ★
- Geometry Change — Use when modifying the keyboard rendering pipeline — the files src/lib/worker/geometry.ts, src/lib/worker/cach 662 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
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
Pi Implementer
Implementation lane driven by the pi CLI (a local multi-provider coding agent, distinct from omp). Model-agnos
Archivist
Invoked for storage, persistence, service worker, offline guarantees, OPFS, Dexie schema. Guards the "no paper
n8n Workflow Validator
Use this agent to validate an existing n8n workflow (either by ID in the user's n8n instance or a local JSON f
Dev Cycle
Orchestrate the full AILANG development workflow from message triage through implementation. Use when user say
Related Skills
Local AI Coding Stack
Scripts and configs for running Claude Code against local LLMs (Ollama, LM Studio, llama.cpp, vLLM). Companion
Flow LLM
Local LLM gateway for Apple Silicon. Works with OpenClaw, Hermes Agent, Claude Code, and Codex (AIRun). No Oll
Anthroxy
anthroxy: one endpoint for Claude Code in front of several Anthropic-compatible backends (vLLM, LM Studio, api