# strands-agents-sops を Homebrew でインストール

strands-agents-sops のインストール経路、実行ファイル、メタデータ、AI エージェント向けセキュリティノートを確認します。

## インストール

```sh
sudo av install brew:strands-agents-sops
```

追加のインストールコマンド:

### macOS

- Homebrew (100%):

```sh
brew install strands-agents-sops
```

  証拠: local Homebrew formula metadata

## パッケージ情報

- **パッケージキー:** brew:strands-agents-sops
- **パッケージマネージャ:** Homebrew
- **バージョン:** 1.1.2
- **ソース概要:** Standard Operating Procedures for AI agents using natural language
- **ホームページ:** <https://aws.amazon.com/blogs/opensource/introducing-strands-agent-sops-natural-language-workflows-for-ai-agents/>
- **リポジトリ:** <https://github.com/strands-agents/agent-sop>
- **最終更新:** 2026-07-17T10:19:51Z
- **生成日時:** 2026-08-03T19:37:03+00:00

## 実行可能ファイル

- strands-agents-sops (エイリアス)

## インストール挙動

- Bottle: 利用不可

## バージョンと鮮度

- ページ生成日: 2026-08-03
- マネージャ版: 1.1.2
## プロジェクトの歴史と使われ方

strands-agents-sops packages Agent SOPs, a Strands Agents project for distributing natural-language standard operating procedures to AI agents through Python modules, skills, and an MCP server.

### プロジェクトの歴史

AWS introduced Agent SOPs publicly on November 20, 2025. The AWS Open Source Blog describes the format as emerging from Amazon's internal builder community as a middle ground between rigid code-defined workflows and unconstrained model-driven agents.

The official GitHub README describes SOPs as markdown-based instruction sets with natural language, parameterized inputs, RFC 2119-style constraints, examples, troubleshooting, and multiple distribution modes.

### 採用の歴史

The AWS launch post says the idea spread across Amazon teams and that thousands of SOPs were in use internally before open sourcing. The package then exposed the workflows to external users through pip, Homebrew, Python imports, MCP prompts, and converted skill directories.

As a Homebrew formula, strands-agents-sops represents the recent package-manager pattern of shipping AI-agent workflow content as an executable CLI/MCP server rather than only as documentation.

### 使われ方

The README's quick start shows brew install strands-agents-sops and pip install strands-agents-sops. It also shows using the package with Strands Agents as a system prompt source and running it as an MCP server so assistants can discover SOP prompts.

The bundled SOPs cover codebase summaries, prompt-driven development, task generation, code assistance, and evaluation workflows.

### パッケージ好きにとっての重要性

The package is significant to CLI/package-manager culture because it treats agent instructions as versioned, installable tooling. That makes prompts and workflows discoverable through the same channels developers already use for linters, language servers, and build tools.

It also shows why MCP-era tools are landing in package managers: an executable can be registered with an assistant, expose prompts, and let teams share workflows without each user copying prompt text by hand.

### タイムライン

- 2025-11-20: AWS announces Agent SOPs as open source.
- 2025-11-20: AWS launch post documents pip installation and the strands-agents-sops MCP server command.
- 2026: Homebrew formula is present in source_facts.package-manager for strands-agents-sops.

### Related projects

- The README links Agent SOPs to the Strands Agents Python SDK, Strands tools, samples, the Strands MCP server, and Agent Builder.
- The AWS post describes usage in Strands, Kiro, Cursor, Claude, GPT-4, and MCP-compatible assistants.

### ソース

- <https://aws.amazon.com/blogs/opensource/introducing-strands-agent-sops-natural-language-workflows-for-ai-agents/>
- <https://github.com/strands-agents/agent-sop#readme>
- <https://strandsagents.com/docs/user-guide/evals-sdk/eval-sop>
- source_facts.package-manager


## セキュリティノート

narrow executable package without higher-risk signals.

- **Geiger リスク:** グリーン / 低
- narrow executable package without higher-risk signals


## Combined YAML source

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


## ソース

- pkg.so package database
- Geiger risk classifier
- curated package history
- pkgdb category and tag curation
- cross-ecosystem install command graph