Local Llm Ops

This is a batteries-included toolkit for running Ollama on macOS with Apple Silicon. It bundles setup scripts, a CLI chat launcher with task modes (coding, creative, analytical), benchmarking harness, and diagnostics into one repo. The workflow is straightforward: run setup_chatbot.sh, pull a model like mistral, then launch with ./chatllm or use aliases for quick access. Benchmarks are scripted and repeatable, which is handy if you're comparing models or tracking performance across updates. The diagnostic script is a nice touch when things break. If you're running local LLMs regularly and want the operational scaffolding already built, this saves you from stitching together your own scripts.

skills.sh installs: 464
GitHub stars: 79
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add bobmatnyc/claude-mpm-skills --skill local-llm-ops --agent claude-code

Installs into .claude/skills of the current project.

Files

Local LLM Ops (Ollama)

Overview

Your localLLM repo provides a full local LLM toolchain on Apple Silicon: setup scripts, a rich CLI chat launcher, benchmarks, and diagnostics. The operational path is: install Ollama, ensure the service is running, initialize the venv, pull models, then launch chat or benchmarks.

Quick Start

./setup_chatbot.sh
./chatllm

If no models are present:

ollama pull mistral

Setup Checklist

Install Ollama: brew install ollama
Start the service: brew services start ollama
Run setup: ./setup_chatbot.sh
Verify service: curl http://localhost:11434/api/version

Chat Launchers

./chatllm (primary launcher)
./chat or ./chat.py (alternate launchers)
Aliases: ./install_aliases.sh then llm, llm-code, llm-fast

Task modes:

./chat -t coding -m codellama:70b
./chat -t creative -m llama3.1:70b
./chat -t analytical

Benchmark Workflow

Benchmarks are scripted in scripts/run_benchmarks.sh:

./scripts/run_benchmarks.sh

This runs bench_ollama.py with:

benchmarks/prompts.yaml
benchmarks/models.yaml
Multiple runs and max token limits

SKILL.md on GitHub

Details

Repository: github.com/bobmatnyc/claude-mpm-skills
Category: AI & Agent Building
First seen: Jun 3, 2026