install

Additional install commands

macOS

Homebrewverified · 100%

brew install strands-agents-sops

local Homebrew formula metadata

overview

Package summary

Standard Operating Procedures for AI agents using natural language

Project links

Commands and aliases

strands-agents-sops

history

Project history and usage

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.

Project history

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.

Adoption history

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.

How it is used

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.

Why package nerds care

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.

Timeline

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.

Sources

security posture

Risk level: green

narrow executable package without higher-risk signals.

Risk classifier

green risk · low confidence · appliance

Why

narrow executable package without higher-risk signals

Signals

metadata:no-higher-risk-signals

Install behavior

No Homebrew post-install hook is recorded in formula metadata.
Homebrew bottle metadata is available for 1 platform targets.
Installs with 5 runtime dependencies.

Recommended review

Before unattended agent use, check whether the tool reads plaintext credentials, writes remote state, publishes artifacts, or shells out to plugins.

executables

Installed executables

Command	Kind	Exposure	Note
`strands-agents-sops`	cli	global executable

freshness

Version and freshness

These signals separate page generation age, package-manager activity, and upstream release comparison. Version lag is warned only when an evidence URL and comparable versions are present.

page generated2026-07-08

manager version1.1.2

manager updated2026-06-21

local dataok

upstreamnot checked

latest detectednot detected

https://aws.amazon.com/blogs/opensource/introducing-strands-agent-sops-natural-language-workflows-for-ai-agents/

infoRelease/tag comparison is only available for GitHub repositories.https://aws.amazon.com/blogs/opensource/introducing-strands-agent-sops-natural-language-workflows-for-ai-agents/none confidence

install metadata

Package metadata

Package key	brew:strands-agents-sops
Version	1.1.2
Package manager	Homebrew
Package manager page	https://formulae.brew.sh/formula/strands-agents-sops
Homepage	https://aws.amazon.com/blogs/opensource/introducing-strands-agent-sops-natural-language-workflows-for-ai-agents/
Repository	https://github.com/strands-agents/agent-sop
Upstream docs	https://aws.amazon.com/blogs/opensource/introducing-strands-agent-sops-natural-language-workflows-for-ai-agents
License	Apache-2.0
Source archive	https://files.pythonhosted.org/packages/6c/e7/59ac10769f9e691587d77305d57fc7907ccdd2d84b3108963de7b1c71d70/strands_agents_sops-1.1.2.tar.gz
Last updated	2026-06-21T11:00:38Z
Pulse	updated
Dependencies	certifi, cryptography, pydantic, python@3.14, rpds-py
Bottle	available (on all)
Homebrew post-install	not defined
Service	none declared

registry facts

Source database details

Source Database	Homebrew formula API
Tap	homebrew/core
Full Name	strands-agents-sops
Version Scheme	0
Revision	5
Bottle Stable Root URL	https://ghcr.io/v2/homebrew/core
Deprecated	no
Disabled	no
Keg Only	no
URL Keys	stable

package graph

Links come from deterministic package relationships, av.db category and tag curation, ecosystem matches, and package hub membership.

source trail

Generated from repository data

This page is generated by av-web from the private package SQLite artifact built by scripts/generate-pkg-sqlite.py.

Combined YAML source

View the package source record on GitHub.

combined/strands-agents-sops.yml

Used sources

Geiger risk classifier
Nucleus package database
av.db category and tag curation
cross-ecosystem install command graph
curated package history
package relationship graph
package version freshness
package-page enrichment

Install strands-agents-sops with Homebrew