Automic VaultAutomic Vault

brew

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

其他安装命令

macOS

Homebrew已验证 · 100%
brew install llm

local Homebrew formula metadata

Linux

Debian apt已验证 · 92%
sudo apt install llm

Debian stable package indexes · llm · 来源: deb.debian.org

Nix已验证 · 92%
nix profile install nixpkgs#llm

nixpkgs package indexes · pkgs/by-name/ll/llm/package.nix · 来源: api.github.com

概览

软件包摘要

Access large language models from the command-line

历史

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.

安全态势

尚未找到受保护工具覆盖

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。

安装行为

  • formula 元数据中未记录 Homebrew post-install 钩子。
  • Homebrew bottle 元数据适用于 6 个平台目标。
  • 安装时包含 4 个运行时依赖。
  • 构建元数据列出 1 个构建依赖。

建议审查

在无人值守的代理使用前,请检查该工具是否读取明文凭据、写入远程状态、发布制品或调用插件。

local files

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

Config paths the tool may read or write during local use.

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

Credential-bearing paths to review before unattended agent runs.

Linux
~/.config/io.datasette.llm/keys.json
macOS
~/Library/Application Support/io.datasette.llm/keys.json

可执行文件

已安装的可执行文件

命令类型暴露范围备注
llmcli全局可执行文件

新鲜度

版本和新鲜度

这些信号区分页生成时间、软件包管理器活动和上游发布比较。只有存在证据 URL 和可比较版本时,才会提示版本落后。

页面生成时间2026-07-25
管理器版本0.31.1
管理器更新时间2026-07-10
本地数据OK
上游not checked
检测到的最新版本未检测到

https://llm.datasette.io/

安装元数据

软件包元数据

软件包键brew:llm
版本0.31.1
软件包管理器Homebrew
软件包管理器页面https://formulae.brew.sh/formula/llm
主页https://llm.datasette.io/
仓库https://github.com/simonw/llm
上游文档https://llm.datasette.io/en/stable
许可证Apache-2.0
源码归档https://files.pythonhosted.org/packages/02/2a/ac37d94f6ac91d501475d80a0a1d8fb6bce392f9d7b483bf87257342e0b7/llm-0.31.1.tar.gz
最后更新2026-07-10T19:29:48Z
Pulseupdated
依赖certifi, libyaml, pydantic, python@3.14
构建依赖rust
Bottle可用 (于 arm64_linux, arm64_sequoia, arm64_sonoma, arm64_tahoe, sonoma, x86_64_linux)
Homebrew post-install未定义
服务未声明

注册表事实

源数据库详情

Source DatabaseHomebrew formula API
Taphomebrew/core
Full Namellm
Version Scheme0
Revision0
Bottle Stable Root URLhttps://ghcr.io/v2/homebrew/core
Deprecatedno
Disabledno
Keg Onlyno
URL Keys
  • stable

源数据库匹配

其他软件包管理器记录

匹配项来自外部软件包管理器索引,并与本地 Automic Vault 软件包链接分开显示。

Debian apt95%

llm 0.23-1

CLI utility and Python library for interacting with Large Language Models

https://github.com/simonw/llm

sudo apt install llm
  • Section: contrib/science
  • Architecture: all
  • 14 依赖
  • normalized package name match
  • 匹配方式:Llm
Debian stable package indexes · deb.debian.org · Debian stable package indexes: llm from https://deb.debian.org/debian/dists/stable/contrib/binary-amd64/Packages.xz
Nix95%

llm

nix profile install nixpkgs#llm
  • normalized package name match
  • 匹配方式:Llm
nixpkgs package indexes · api.github.com · nixpkgs package indexes: pkgs/by-name/ll/llm/package.nix from https://api.github.com/repos/NixOS/nixpkgs/git/trees/master?recursive=1

来源线索

由仓库数据生成

此页面由 av-webscripts/generate-pkg-sqlite.py 生成的私有软件包 SQLite 工件提供。

使用的来源

  • Geiger risk classifier
  • Nucleus package database
  • av.db category and tag curation
  • cross-ecosystem install command graph
  • curated configuration and credential file locations
  • curated package history
  • external package-manager database matches
  • package relationship graph
  • package version freshness
  • package-page enrichment