Open CLI

ollama

scriptableai
$ brew install ollama
Summary

Local models, ai prototyping, and private inference from the terminal.

  • ollama fits local ai well, especially for local models, ai prototyping, and private inference from the terminal.
  • 71,017 homebrew installs (30d).
  • Easy to automate.
  • Good fit for coding-agent workflows and repeatable scripts.
  • Output is mostly text-first, so verify results before scripting around it.
ai-ollama-SKILL.md

Ollama guide

Local models, ai prototyping, and private inference from the terminal. Built by Ollama. Start with `ollama pull llama3.2` and go from there. Runs entirely on your machine.

Open CLI packages the install path, verify step, and safe-start workflow so this tool can move from “interesting CLI” to something you can actually use. It also integrates with skills.sh so each CLI comes with the right companion skills, not just a binary and a docs link.

When to apply

  • local models, ai prototyping, and private inference from the terminal.
  • You want AI models and inference that runs entirely on your machine.
  • You need local models.
  • You need ai prototyping.
  • You need private inference.

Quick reference

Installbrew install ollama
Verifyollama --version
First real commandollama run llama3.2

Open CLI × skills.sh

Open CLI integrates ollama with the right skills.sh companions so you get the tool and the workflow together.

Prompt Engineering

Verified pairing

Open CLI integrates ollama with this skills.sh skill because it is the clearest fit for how ollama is usually used. Use sharper prompts so AI CLIs and agents produce more reliable results.

View on skills.sh
$ npx skills add https://github.com/inferen-sh/skills --skill prompt-engineering
Starter prompt

Use ollama together with the Prompt Engineering skills.sh skill. Start with a small prompt or read-only action, show the result, and propose the next loop before escalating scope.

Also useful from skills.sh
AI Automation Workflowsskills.shWorkflow Automationskills.sh

Why this tool

  • ollama fits local ai well, especially for local models, ai prototyping, and private inference from the terminal.
  • 71,017 homebrew installs (30d).
  • Easy to automate.

Watch-outs

  • Output is mostly plain text.
  • Better for local use than CI.

Example workflow

1. ollama pull llama3.2
2. ollama run llama3.2
3. ollama serve

Safe start

Step 1

Install ollama.

Step 2

Run `ollama --version` first.

Step 3

Start with `ollama run llama3.2`.

Step 4

Install the CLI and any required runtime, model, or Python environment.

Alternatives worth considering

claude

Coding agent, refactors, and codebase search from the terminal.

codex

Coding agent, terminal code tasks, and prompted edits from the terminal.

gemini

Coding agent, prompting, and terminal assistance from the terminal.