Project Links

Meta

Author: AWS

Requires Python: >=3.10

Classifiers

Development Status

5 - Production/Stable

Intended Audience

Developers

License

OSI Approved :: Apache Software License

Operating System

OS Independent

Programming Language

Python :: 3
Python :: 3.10
Python :: 3.11
Python :: 3.12
Python :: 3.13
Python :: 3.14

Topic

Scientific/Engineering :: Artificial Intelligence
Software Development :: Libraries :: Python Modules

Strands Agents - Python SDK

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

Documentation ◆ Samples ◆ Tools ◆ MCP Server

Strands Agents is a simple yet powerful SDK that takes a model-driven approach to building and running AI agents. From simple conversational assistants to complex autonomous workflows, from local development to production deployment, Strands Agents scales with your needs.

Feature Overview

Lightweight & Flexible: Simple agent loop that just works and is fully customizable
Model Agnostic: Support for Amazon Bedrock, Anthropic, Gemini, LiteLLM, Llama, Ollama, OpenAI, Writer, and custom providers
Advanced Capabilities: Multi-agent systems, autonomous agents, and streaming support
Built-in MCP: Native support for Model Context Protocol (MCP) servers, enabling access to thousands of pre-built tools

Quick Start

# Install Strands Agents
pip install strands-agents strands-agents-tools

from strands import Agent
from strands_tools import calculator
agent = Agent(tools=[calculator])
agent("What is the square root of 1764")

Note: For the default Amazon Bedrock model provider, you'll need AWS credentials configured and model access enabled for Claude 4 Sonnet in the us-west-2 region. See the Quickstart Guide for details on configuring other model providers.

Installation

Ensure you have Python 3.10+ installed, then:

# Create and activate virtual environment
python -m venv .venv
source .venv/bin/activate  # On Windows use: .venv\Scripts\activate

# Install Strands and tools
pip install strands-agents strands-agents-tools

Features at a Glance

Python-Based Tools

Easily build tools using Python decorators:

from strands import Agent, tool

@tool
def word_count(text: str) -> int:
    """Count words in text.

    This docstring is used by the LLM to understand the tool's purpose.
    """
    return len(text.split())

agent = Agent(tools=[word_count])
response = agent("How many words are in this sentence?")

Hot Reloading from Directory: Enable automatic tool loading and reloading from the ./tools/ directory:

from strands import Agent

# Agent will watch ./tools/ directory for changes
agent = Agent(load_tools_from_directory=True)
response = agent("Use any tools you find in the tools directory")

MCP Support

Connect to Model Context Protocol (MCP) servers:

from strands import Agent
from strands.tools.mcp import MCPClient
from mcp import stdio_client, StdioServerParameters

aws_docs_client = MCPClient(
    lambda: stdio_client(StdioServerParameters(command="uvx", args=["awslabs.aws-documentation-mcp-server@latest"]))
)

with aws_docs_client:
   agent = Agent(tools=aws_docs_client.list_tools_sync())
   response = agent("Tell me about Amazon Bedrock and how to use it with Python")

The SDK works with both major versions of the mcp package through a built-in compatibility layer, so most code that uses MCPClient runs unchanged on either version. A fresh install resolves to mcp 2.x, and pinning mcp<2 keeps you on 1.x. See docs/MCP_VERSIONS.md for support status, the behavior differences on 2.x, and migration notes.

Multiple Model Providers

Support for various model providers:

from strands import Agent
from strands.models import BedrockModel
from strands.models.ollama import OllamaModel
from strands.models.llamaapi import LlamaAPIModel
from strands.models.gemini import GeminiModel
from strands.models.llamacpp import LlamaCppModel

# Bedrock
bedrock_model = BedrockModel(
  model_id="us.amazon.nova-pro-v1:0",
  temperature=0.3,
  streaming=True, # Enable/disable streaming
)
agent = Agent(model=bedrock_model)
agent("Tell me about Agentic AI")

# Google Gemini
gemini_model = GeminiModel(
  client_args={
    "api_key": "your_gemini_api_key",
  },
  model_id="gemini-2.5-flash",
  params={"temperature": 0.7}
)
agent = Agent(model=gemini_model)
agent("Tell me about Agentic AI")

# Ollama
ollama_model = OllamaModel(
  host="http://localhost:11434",
  model_id="llama3"
)
agent = Agent(model=ollama_model)
agent("Tell me about Agentic AI")

# Llama API
llama_model = LlamaAPIModel(
    model_id="Llama-4-Maverick-17B-128E-Instruct-FP8",
)
agent = Agent(model=llama_model)
response = agent("Tell me about Agentic AI")

Built-in providers:

Custom providers can be implemented using Custom Providers

Example tools

Strands offers an optional strands-agents-tools package with pre-built tools for quick experimentation:

from strands import Agent
from strands_tools import calculator
agent = Agent(tools=[calculator])
agent("What is the square root of 1764")

It's also available on GitHub via strands-agents/tools.

Bidirectional Streaming

⚠️ Experimental Feature: Bidirectional streaming is currently in experimental status. APIs may change in future releases as we refine the feature based on user feedback and evolving model capabilities.

Build real-time voice and audio conversations with persistent streaming connections. Unlike traditional request-response patterns, bidirectional streaming maintains long-running conversations where users can interrupt, provide continuous input, and receive real-time audio responses. Get started with your first BidiAgent by following the Quickstart guide.

Supported Model Providers:

Amazon Bedrock Nova Sonic
Google Gemini Live
OpenAI Realtime API

Installation:

# Server-side only (no audio I/O dependencies)
pip install strands-agents[bidi]

# With all portable Bidi providers, terminal I/O, and audio processing (no local audio devices)
pip install strands-agents[bidi-all]

# For local microphone/speaker access, install PortAudio for your OS first, then:
pip install strands-agents[bidi,bidi-io,bidi-pyaudio]

Note: Bedrock Nova Sonic requires Python 3.12+ due to its experimental AWS SDK dependency.

Quick Example:

import asyncio
from strands.experimental.bidi.agent import BidiAgent
from strands.experimental.bidi.models import BedrockNovaSonicModel
from strands.experimental.bidi.io import AudioIO
from strands_tools import calculator, stop

async def main():
    # Create bidirectional agent with Nova Sonic v2
    model = BedrockNovaSonicModel(model_id="amazon.nova-2-sonic-v1:0")
    agent = BidiAgent(model=model, tools=[calculator, stop])

    # Setup audio I/O (local audio requires the bidi-pyaudio extra)
    audio_io = AudioIO()

    # Run with real-time audio streaming and terminal transcripts
    # stop tool allows user to verbally stop agent execution
    await agent.run(
        inputs=[audio_io.input()],
        outputs=[audio_io.output()]
    )

if __name__ == "__main__":
    asyncio.run(main())

Note: ConsoleIO is included with the bidi-io extra. AudioIO requires the bidi-io and bidi-pyaudio extras plus the PortAudio system library. For server-side deployments where audio I/O is handled by clients (browsers, mobile apps), install only strands-agents[bidi] and implement custom input/output streams using the InputStream and OutputStream protocols.

Configuration Options:

from strands.experimental.bidi.models import BedrockNovaSonicModel

# Configure audio streams and Nova Sonic session parameters.
model = BedrockNovaSonicModel(
    model_id="amazon.nova-2-sonic-v1:0",
    audio={
        "input": {"sample_rate": 16000},
        "output": {"sample_rate": 16000},
    },
    voice="matthew",
    params={
        "turnDetectionConfiguration": {
            "endpointingSensitivity": "MEDIUM"
        },
        "inferenceConfiguration": {
            "maxTokens": 2048,
            "temperature": 0.7
        },
    },
)

# Configure I/O devices
audio_io = AudioIO(
    input_device_index=0,  # Specific microphone
    output_device_index=1,  # Specific speaker
    input_buffer_size=10,
    output_buffer_size=10
)

Documentation

For detailed guidance & examples, explore our documentation:

Development

pip install hatch
hatch test        # run unit tests
hatch fmt         # format & lint

Contributing ❤️

We welcome contributions! See our Contributing Guide for details on:

Reporting bugs & features
Development setup
Contributing via Pull Requests
Code of Conduct
Reporting of security issues

Stay in touch with the team

Come meet the Strands team and other users on Discord

License

This project is licensed under the Apache License 2.0 - see the LICENSE file for details.

Security

See CONTRIBUTING for more information.

Wheel compatibility matrix

Platform	Python 3
any

Files in release

strands_agents-1.57.1-py3-none-any.whl (838.1KiB)

strands_agents-1.57.1.tar.gz (1.6MiB)

Extras:

Dependencies:

boto3 (<2.0.0,>=1.26.0)

botocore (<2.0.0,>=1.29.0)

docstring-parser (<1.0,>=0.15)

httpx (<1.0.0,>=0.28.1)

jsonschema (<5.0.0,>=4.0.0)

mcp (<2.2,>=1.23.0)

opentelemetry-api (<2.0.0,>=1.30.0)

opentelemetry-instrumentation-threading (<1.00b0,>=0.51b0)

opentelemetry-sdk (<2.0.0,>=1.30.0)

pydantic (<3.0.0,>=2.4.0)

pyyaml (<7.0.0,>=6.0.0)

typing-extensions (<5.0.0,>=4.13.2)

watchdog (<7.0.0,>=6.0.0)

strands-agents 1.57.1

Development Status

Intended Audience

License

Operating System

Programming Language

Topic

Strands Agents - Python SDK

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

Feature Overview

Quick Start

Installation

Features at a Glance

Python-Based Tools

MCP Support

Multiple Model Providers

Example tools

Bidirectional Streaming

Documentation

Development

Contributing ❤️

Stay in touch with the team

License

Security

Wheel compatibility matrix

Files in release