# 使用 Homebrew, apt, Nix 安装 llm

查看 llm 的安装路径、可执行文件、元数据以及面向 AI 代理工作流的安全说明。

## 安装

```sh
sudo av install brew:llm
```

其他安装命令:

### macOS

- Homebrew (100%):

```sh
brew install llm
```

  证据: local Homebrew formula metadata

### Linux

- Debian apt (92%):

```sh
sudo apt install llm
```

  证据: Debian stable package indexes: llm from https://deb.debian.org/debian/dists/stable/contrib/binary-amd64/Packages.xz

- Nix (92%):

```sh
nix profile install nixpkgs#llm
```

  证据: nixpkgs package indexes: pkgs/by-name/ll/llm/package.nix from https://api.github.com/repos/NixOS/nixpkgs/git/trees/master?recursive=1

## 软件包事实

- **软件包键:** brew:llm
- **软件包管理器:** Homebrew
- **版本:** 0.31.1
- **来源摘要:** Access large language models from the command-line
- **主页:** <https://llm.datasette.io/>
- **最后更新:** 2026-07-10T19:29:48Z
- **已生成:** 2026-08-03T19:37:03+00:00

## 可执行文件

- llm (别名)

## 安装行为

- Bottle: 不可用

## 版本和新鲜度

- 页面生成时间: 2026-08-03
- 管理器版本: 0.31.1
## 项目历史与用法

LLM is Simon Willison's command-line tool and Python library for working with large language models. It started as an OpenAI-focused CLI in 2023 and evolved into a plugin-based interface for remote APIs, local models, embeddings, prompt templates, logging, attachments, schemas, and tool use.

### 项目历史

The changelog records version 0.1 on April 1, 2023 as the initial prototype release. Version 0.5 on July 12, 2023 added a plugin mechanism for additional language models, a key change that moved LLM beyond a single-provider OpenAI wrapper.

During 2023 and 2024, LLM added chat, embeddings, templates, SQLite logging and search, model aliases, attachments, async models, and broader provider support. In May 2025, version 0.26 added tool support, letting models execute Python functions through the CLI and Python API.

### 采用历史

LLM became part of the Datasette-adjacent command-line culture around small composable tools, SQLite-backed logs, and plugin systems. Homebrew, Debian, and Nix packaging made it easy to install as a normal developer utility rather than only as a Python package.

Its adoption expanded with the growth of provider-specific plugins and local-model integrations, giving users one command-line interface across OpenAI, Anthropic, Gemini, Ollama-backed models, and many community plugins.

### 使用方式

Common uses include running one-off prompts from the shell, piping files into a model, starting interactive chats, storing API keys, saving prompt templates, logging responses to SQLite, generating embeddings, and calling models from Python code.

The documented configuration paths and keys.json locations matter to package users because Homebrew installs the executable, while user-specific model keys, templates, logs, and extra model definitions live outside the package prefix.

### 为什么软件包爱好者会关心

LLM is package-nerd significant because it turns rapidly changing AI APIs into a stable Unix-style command with plugins. The packaging story is unusually important: users want a single binary-ish command in PATH, but the real extension surface is Python plugins and user configuration.

It is also a useful example of modern CLI state management: credentials, templates, provider models, logs, and tool definitions are intentionally external to the package, so upgrades can move the application forward without overwriting user data.

### 时间线

- 2023-04-01: LLM 0.1 initial prototype release.
- 2023-07-12: LLM 0.5 added the plugin mechanism for additional language models.
- 2024-10-29: LLM 0.17 added attachment support for multimodal models.
- 2025-05-27: LLM 0.26 added tool support.
- 2026-06-09: LLM 0.32a3 appeared in the changelog with tool-call and human-in-the-loop improvements.

### Related projects

- Datasette is related through the broader Simon Willison/Datasette tooling ecosystem and the io.datasette.llm application data namespace.
- LLM plugins such as provider adapters and local-model integrations are central to the project's architecture.
- SQLite is related through LLM's prompt and response logging features.

### 来源

- <https://formulae.brew.sh/formula/llm>
- <https://github.com/simonw/llm>
- <https://github.com/simonw/llm/releases/tag/0.1>
- <https://llm.datasette.io/>
- <https://llm.datasette.io/en/stable/changelog.html>
- <https://llm.datasette.io/en/stable/setup.html>


## 安全说明

没有找到 llm 的匹配本地密钥处理 manifest。Nucleus 软件包元数据仍在此发布，以便未来覆盖拥有稳定的软件包 URL。



## Configuration and credential file locations

These source-backed paths show where this package keeps local settings or durable credentials. Automic Vault can use them as review targets for secret scanning, migration, and command approval.


## Configuration files

- Linux: ~/.config/io.datasette.llm/, ~/.config/io.datasette.llm/templates/*.yaml, ~/.config/io.datasette.llm/extra-openai-models.yaml
- macOS: ~/Library/Application Support/io.datasette.llm/, ~/Library/Application Support/io.datasette.llm/templates/*.yaml, ~/Library/Application Support/io.datasette.llm/extra-openai-models.yaml

## Credential files

- Linux: ~/.config/io.datasette.llm/keys.json
- macOS: ~/Library/Application Support/io.datasette.llm/keys.json
## 其他软件包管理器记录

- Debian apt - llm - 0.23-1: normalized package name match | Debian stable package indexes: llm from https://deb.debian.org/debian/dists/stable/contrib/binary-amd64/Packages.xz | CLI utility and Python library for interacting with Large Language Models | https://github.com/simonw/llm
- Nix - llm: normalized package name match | nixpkgs package indexes: pkgs/by-name/ll/llm/package.nix from https://api.github.com/repos/NixOS/nixpkgs/git/trees/master?recursive=1


## Combined YAML source

View the package source record on GitHub. [combined/llm.yml](https://github.com/mxcl/pkgdb/blob/main/combined/llm.yml)


## 来源

- pkg.so package database
- Geiger risk classifier
- curated configuration and credential file locations
- curated package history
- pkgdb category and tag curation
- external package-manager database matches
- cross-ecosystem install command graph