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:
- Amazon Bedrock
- Anthropic
- Gemini
- Cohere
- LiteLLM
- llama.cpp
- LlamaAPI
- MistralAI
- Ollama
- OpenAI
- OpenAI Responses API
- SageMaker
- Writer
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 (v1, v2)
- 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, text I/O, and audio processing
pip install strands-agents[bidi-all]
# For local microphone/speaker access, install PortAudio for your OS first, then:
pip install strands-agents[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 import BidiAgent
from strands.experimental.bidi.models import BedrockNovaSonicModel
from strands.experimental.bidi.io import BidiAudioIO, BidiTextIO
from strands_tools import calculator, stop
async def main():
# Create bidirectional agent with Nova Sonic v2
model = BedrockNovaSonicModel()
agent = BidiAgent(model=model, tools=[calculator, stop])
# Setup audio and text I/O (local audio requires the bidi-pyaudio extra)
audio_io = BidiAudioIO()
text_io = BidiTextIO()
# Run with real-time audio streaming
# stop tool allows user to verbally stop agent execution
await agent.run(
inputs=[audio_io.input()],
outputs=[audio_io.output(), text_io.output()]
)
if __name__ == "__main__":
asyncio.run(main())
Note:
BidiTextIOis included with thebidiextra.BidiAudioIOrequires thebidi-pyaudioextra and the PortAudio system library. For server-side deployments where audio I/O is handled by clients (browsers, mobile apps), install onlystrands-agents[bidi]and implement custom input/output handlers using theBidiInputandBidiOutputprotocols.
Configuration Options:
from strands.experimental.bidi.models import BedrockNovaSonicModel
# Configure audio streams and Nova Sonic session parameters.
model = BedrockNovaSonicModel(
audio={
"input_rate": 16000,
"output_rate": 16000,
"voice": "matthew",
},
params={
"turnDetectionConfiguration": {
"endpointingSensitivity": "MEDIUM"
},
"inferenceConfiguration": {
"maxTokens": 2048,
"temperature": 0.7
},
},
)
# Configure I/O devices
audio_io = BidiAudioIO(
input_device_index=0, # Specific microphone
output_device_index=1, # Specific speaker
input_buffer_size=10,
output_buffer_size=10
)
# Text input mode (type messages instead of speaking)
text_io = BidiTextIO()
await agent.run(
inputs=[text_io.input()], # Use text input
outputs=[audio_io.output(), text_io.output()]
)
# Multi-modal: Both audio and text input
await agent.run(
inputs=[audio_io.input(), text_io.input()], # Speak OR type
outputs=[audio_io.output(), text_io.output()]
)
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.
1 maintainer
Release files for strands-agents 1.55.1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| strands_agents-1.55.1.tar.gz | 1.6 MB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| strands_agents-1.55.1-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 2.4 MB
Release files / strands_agents-1.55.1.tar.gz
| Download URL | strands_agents-1.55.1.tar.gz |
|---|---|
| Size | 1.6 MB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
55dc609a9d7c75d61842304180456a815e60b34d00ce089c29362cedd274cd2a
|
|
BLAKE2b-256 checksum How to use checksums |
0d80f65af6df0300f1d09e5c0d0cc7ebb1e8183d3922829cec2c255c91188ec9
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Sep 9, 2026.
Transparency logRelease files / strands_agents-1.55.1-py3-none-any.whl
| Download URL | strands_agents-1.55.1-py3-none-any.whl |
|---|---|
| Size | 821.4 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
3b62a8ca6f34d14140789900e35205c0032fa4a92f6147c7f69a7fda149da7ab
|
|
BLAKE2b-256 checksum How to use checksums |
faa05d7dc1c6df4b4717d7be516c32e5c9383ef0676166fb06260b6d88c4c9ab
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Sep 9, 2026.
Transparency log
