LLM (CLI) review

Q: How do I install LLM (CLI)?

Run pip install llm. The llm package needs Python 3.10 or newer. The install section above has the other options from the project's README.

LLM is a CLI tool and Python library for running prompts against remote API models and local models from the command line.

Updated Nov 1, 2026. Review written Oct 22, 2026 from the project's own sources; usage data refreshed every Monday.

TL;DR

LLM is a command-line tool and Python library for working with OpenAI, Anthropic, Gemini and many other language models, remote or local. It suits developers who want to prompt models from the terminal and script them. It logs prompts and responses to SQLite and adds models through plugins.

12.7kGitHub stars
+23new stars, week of Oct 25
–not ranked this week

LLM (CLI) at a glance

Category: Model SDKs and gateways
Maintained by: Simon Willison (individual, @simonw on GitHub)
License: Apache 2.0
Language: Python, Just, Shell
Repository: github.com/simonw/llm
Website: llm.datasette.io
PyPI package: llm 0.36
Latest release: 0.36 on GitHub, Sep 22, 2026
First published: Apr 1, 2023

What LLM (CLI) does

LLM runs prompts from the command line, including piped file input with a system prompt.
LLM stores prompts and responses in a SQLite database.
LLM generates and stores embeddings with the llm embed and llm embed-multi commands.
LLM extracts structured content from text and images using schemas.
LLM can grant models the ability to execute tools.
LLM starts interactive chat sessions with a model using llm chat.
LLM accepts attachments such as images, for example to extract text from a scanned document.

How it works

LLM runs as the llm command or as a Python library. You store API keys with llm keys set, then prompt a model by name with -m. Plugins installed with llm install add providers such as Gemini, Anthropic and Ollama. LLM can also target any OpenAI-compatible Chat Completions endpoint, such as LM Studio.

How to install and start using LLM (CLI)

With pip

pip install llm

With Homebrew

brew install llm

With uv

uv tool install llm

Requirements

Python 3.10 or later.
An API key for remote providers such as OpenAI, Gemini or Anthropic.

First steps

Store your OpenAI API key with llm keys set openai.
Run a prompt such as llm "Ten fun names for a pet pelican".
Install a provider plugin, for example llm install llm-anthropic, then set its key.
Start an interactive session with llm chat -m gpt-4.1.

Who LLM (CLI) is for

Developers who want to prompt language models from the terminal and in shell pipelines.
Python developers who need one library for many model providers.
Developers running local models through Ollama or LM Studio.

Limitations to know

LLM supports Gemini, Anthropic and Ollama models only after installing separate plugins.
LLM's Homebrew installation carries a warning note in the documentation.
LLM refuses chat sessions for plugin models that only accept single-turn prompts.

Is LLM (CLI) growing? Usage data

LLM (CLI) was not ranked on the Devtoolwatch Board in the week of Oct 25–31, 2026: it needs 25 or more new stars or 1,000 or more added downloads in a week to rank.

New GitHub stars per week for the last 12 weeks, from GitHub's stargazer history (today's stargazers by the week they starred).

Show the weekly numbers

New GitHub stars per week for LLM (CLI)
Week of	New stars
Aug 9, 2026	41
Aug 16, 2026	32
Aug 23, 2026	40
Aug 30, 2026	47
Sep 6, 2026	32
Sep 13, 2026	42
Sep 20, 2026	37
Sep 27, 2026	26
Oct 4, 2026	29
Oct 11, 2026	36
Oct 18, 2026	33
Oct 25, 2026	23

On Hacker News

LLM-hacker-news: LLM plugin for pulling content from Hacker News, 92 points and 55 comments (Apr 8, 2025)
LLM Command Line Tool, 9 points and 1 comments (Aug 28, 2024)

The Board ranks tools by four signals each week: new stars, new stars for the repo's size, added downloads and download growth beyond the market. How the ranking works.

LLM (CLI) alternatives

Other LLM SDKs and gateways on the Board in the week of Oct 25–31, 2026, by momentum:

Model SDKs and gateways ranked by momentum, the week of Oct 25–31, 2026
Rank	Tool	Stars	Downloads/wk
#1	thinking-orbsthinking-orbs is a React library of dotted, animated thought-orb loading indicators for AI and agent user interfaces.	3.9k	1.4M
#2	HeadroomHeadroom compresses tool outputs, logs, files, and RAG chunks locally before they reach the LLM, as a library, proxy, or MCP server.	78.5k	125.8k
#3	LiteLLMLiteLLM is an open source AI gateway and Python SDK that calls 100+ LLM providers through one OpenAI-format interface.	62.5k	23.1M
#4	Honcho Memory library for building stateful agents	7.9k	–
#5	Anthropic SDKAnthropic SDK is the official Python library for calling the Claude API from Python applications.	4k	111M
#6	Hugging Face HubHugging Face Hub is the official CLI and Python client for downloading, uploading and managing models, datasets and Spaces on the…	4k	68.3M

All LLM SDKs and gateways, ranked

Recent LLM (CLI) releases

0.36, Sep 22, 2026
0.35, Sep 7, 2026
0.34, Sep 2, 2026
0.33, Aug 22, 2026
0.32.1, Aug 21, 2026

LLM (CLI) FAQ

Is LLM (CLI) free and open source?

Yes. LLM (CLI)'s source code is on GitHub (simonw/llm) under the Apache 2.0 license, so you can use it for free.

How do I install LLM (CLI)?

Run pip install llm. The llm package needs Python 3.10 or newer. The install section above has the other options from the project's README.

Is LLM (CLI) still maintained?

Yes. The simonw/llm repository was last updated on Oct 21, 2026, and the latest release, 0.36 on GitHub, came out on Sep 22, 2026.

How popular is LLM (CLI)?

LLM (CLI) has 12.7k GitHub stars as of Nov 1, 2026. It gained 23 new stars in the week of Oct 25–31, 2026, against a 12-week average of 35 a week.

What are the best alternatives to LLM (CLI)?

Other LLM SDKs and gateways on the Devtoolwatch Board in the week of Oct 25–31, 2026, by momentum: thinking-orbs (#1), Headroom (#2), LiteLLM (#3), Honcho (#4), Anthropic SDK (#5). The alternatives table above has their numbers.

Can LLM use local models?

Yes. LLM can use local models through plugins such as llm-ollama, and it can target any OpenAI-compatible Chat Completions endpoint, such as LM Studio running on localhost.

Where does LLM store my prompts and responses?

LLM logs prompts and responses to SQLite. Version 0.32 introduced a content-addressed SQLite logging schema, and you can inspect the logs with llm logs.

Can I try LLM without installing it?

Yes. With uvx you can run LLM against an OpenAI-compatible endpoint without installing it first, for example uvx llm openai endpoint http://localhost:1234/v1.

Does LLM show reasoning traces?

Yes. Since version 0.32, the llm command displays reasoning traces on standard error for models that support them.

Sources

LLM (CLI) README badge

Maintainers can show the tool's weekly Board rank in their README:

[![Devtoolwatch](https://index.devtoolwatch.com/badge/llm-cli.svg)](https://index.devtoolwatch.com/tools/llm-cli/)

How this page is made: Devtoolwatch writes each review from the project's README, releases, package metadata and website, with an AI model, then checks every claim against the source it cites and drops what the sources don't support. The numbers come from Devtoolwatch's daily GitHub snapshots, GitHub's stargazer history, and the npm and PyPI download APIs. Spotted an error? Email [email protected].