strands-agents

A model-driven approach to building AI agents in just a few lines of code

strands-agents Permissive license Apache-2.0 Active ★ 6,899 v1.52.0 released 2026-08-12

Install

strands-agents on PyPI

pip

pip install strands-agents

uv

uv add strands-agents

poetry

poetry add strands-agents

Package facts

License	Apache-2.0 (permissive)
Python support	supports the current Python release (>=3.10)
Install friction	low — pure-Python wheel
Runtime dependencies	13 — boto3, botocore, docstring-parser, httpx, jsonschema, mcp, opentelemetry-api, opentelemetry-instrumentation-threading, opentelemetry-sdk, pydantic, pyyaml, typing-extensions, watchdog
Maintenance	actively maintained — 1 days since the last release
Last repo commit	2026-08-13
First released	2025-05-14
Popularity	one of the top 1,000 most-downloaded packages on PyPI (30-day window, as of 2026-08-13)
Known vulnerabilities	none known (OSV.dev, checked 2026-08-13)

Evidence: strands_agents-1.52.0-py3-none-any.whl

Development Status :: 5 - Production/StableIntended Audience :: DevelopersLicense :: OSI Approved :: Apache Software LicenseOperating System :: OS IndependentProgramming Language :: Python :: 3Programming Language :: Python :: 3.10Programming Language :: Python :: 3.11Programming Language :: Python :: 3.12Programming Language :: Python :: 3.13Programming Language :: Python :: 3.14Topic :: Scientific/Engineering :: Artificial IntelligenceTopic :: Software Development :: Libraries :: Python Modules

About strands-agents

from the package's own PyPI description — quoted content, verbatim

<h1> Strands Agents - Python SDK </h1>

<h2> A model-driven approach to building AI agents in just a few lines of code. </h2>

<div align="center"> <a href="https://github.com/strands-agents/harness-sdk/graphs/commit-activity"><img alt="GitHub commit activity" src="https://img.shields.io/github/commit-activity/m/strands-agents/harness-sdk"/></a> <a href="https://github.com/strands-agents/harness-sdk/issues"><img alt="GitHub open issues" src="https://img.shields.io/github/issues/strands-agents/harness-sdk"/></a> <a href="https://github.com/strands-agents/harness-sdk/pulls"><img alt="GitHub open pull requests" src="https://img.shields.io/github/issues-pr/strands-agents/harness-sdk"/></a> <a href="https://github.com/strands-agents/harness-sdk/blob/main/LICENSE"><img alt="License" src="https://img.shields.io/github/license/strands-agents/harness-sdk"/></a> <a href="https://pypi.org/project/strands-agents/"><img alt="PyPI version"...

Read as markdown · JSON record · Source repository · Homepage · Docs

AI interpretation — verify before relying

AI-generated interpretation of the package facts above; every digit, version, license, or vulnerability id it cites is grounded in the facts already shown on this page

Strands Agents is a Python SDK for building AI agents with a model-driven approach, supporting multiple LLM providers and enabling tool integration via decorators or Model Context Protocol servers.

Low friction install with a pure-Python wheel and 13 well-established runtime dependencies. Actively maintained with a release one day old and strong community adoption, indicating ongoing development.

Apache-2.0 permissive license allows commercial and private use with minimal restrictions; you may use, modify, and distribute freely provided you include the license notice.

Usage

pip install strands-agents

from strands import Agent

agent = Agent()
agent("Your prompt here")

Requires Python 3.10+. Default Bedrock model provider requires AWS credentials configured and model access enabled; alternative model providers have their own credential requirements.

Verdict: Production-ready agent framework with strong maintenance signals (active status, recent release) and no known vulnerabilities. The multi-provider architecture and 13 runtime dependencies make it suitable for teams building LLM-powered agents, though credential setup varies by chosen model provider.

Needs verification

Whether external tool packages are required for basic agent functionality or optional for extended capabilities
Performance characteristics and latency profiles across different model providers
Specific AWS credential scoping and IAM policy requirements for Bedrock integration

python ai agent frameworkllm agent sdk multi-providermodel context protocol mcp toolsautonomous agent builderagentic ai pythontool-calling agent frameworkbedrock openai agent library