# LLM Command-Line Interface for Large Language Models

> LLM is a Python CLI tool and library by Simon Willison for accessing OpenAI, Anthropic Claude, Google Gemini, Meta Llama, and dozens of other language models from the terminal. It supports API-based and local models via plugins, conversation logging to SQLite, templates, embeddings, and tool use.

- Skill: `agentskillexchange/llm-command-line-interface-for-large-language-models` (Agent Skill)
- Install (CLI): `npx skillmds@latest add agentskillexchange/llm-command-line-interface-for-large-language-models`
- Raw SKILL.md: https://api.skillmd.com/api/skills/agentskillexchange/llm-command-line-interface-for-large-language-models/raw
- Safety review: pending (external: skill-scanner PASS, skillspector PASS)
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: agentskillexchange (https://skillmd.com/u/agentskillexchange)
- Updated: 2026-09-08
- Page: https://skillmd.com/skills/agentskillexchange/llm-command-line-interface-for-large-language-models

---


# LLM Command-Line Interface for Large Language Models

LLM is a Python CLI tool and library by Simon Willison for accessing OpenAI, Anthropic Claude, Google Gemini, Meta Llama, and dozens of other language models from the terminal. It supports API-based and local models via plugins, conversation logging to SQLite, templates, embeddings, and tool use.

## Installation

Use the upstream install or setup path that matches your environment:
- pip install llm
- brew install llm
- pipx install llm
- uv tool install llm

Requirements and caveats from upstream:
- A CLI tool and Python library for interacting with **OpenAI**, **Anthropic’s Claude**, **Google’s Gemini**, **Meta’s Llama** and dozens of other Large Language Models, both via remote APIs and with models that can be...
- [Using embeddings from Python](https://llm.datasette.io/en/stable/embeddings/python-api.html)
- [Working with collections](https://llm.datasette.io/en/stable/embeddings/python-api.html#working-with-collections)

Basic usage or getting-started notes:
- # Run: sphinx-build -M markdown ./docs ./tmpdir
- subprocess.run([
- [Run prompts from the command-line](https://llm.datasette.io/en/stable/usage.html#usage-executing-prompts)

- Source: https://github.com/simonw/llm
- Extracted from upstream docs: https://raw.githubusercontent.com/simonw/llm/HEAD/README.md

## Source

- [Agent Skill Exchange](https://agentskillexchange.com/skills/llm-command-line-interface-large-language-models/)