Get started

Name: Strands Agents SDK
Author: Strands Agents

The Strands Agents SDK empowers developers to quickly build, manage, evaluate and deploy AI-powered agents. These quick start guides get you set up and running a simple agent in less than 20 minutes.

Python QuickstartCreate your first Python Strands agent with full feature access!

TypeScript QuickstartCreate your first TypeScript Strands agent!

A library, not a platform

Strands runs inside your own process. Creating an agent is constructing an object in Python or Node.js: there is no hosted control plane, scheduler, or database to stand up first. Any model provider works. Amazon Bedrock is the default, and swapping in Anthropic, OpenAI, Gemini, or Ollama is a one-line change, so an AWS account is only required if you keep the default. Adding an agent to an existing FastAPI, Express, or Next.js app is a dependency and a few lines of code, not new infrastructure.

Here is the whole of it: one file that answers HTTP requests with a Strands agent. The route handler constructs an agent and calls it. The only service it reaches is the model provider.

Python
TypeScript

from fastapi import FastAPI
from pydantic import BaseModel
from strands import Agent

app = FastAPI()


class ChatRequest(BaseModel):
    prompt: str


@app.post("/chat")
def chat(request: ChatRequest) -> dict[str, str]:
    # The agent lives in this process: no scheduler or database to reach.
    agent = Agent()
    result = agent(request.prompt)
    return {"reply": str(result)}

Run it with uvicorn main:app.

import { Agent } from '@strands-agents/sdk'
import express, { type Request, type Response } from 'express'

const app = express()
app.use(express.json())

app.post('/chat', async (req: Request, res: Response) => {
  // The agent lives in this process: no scheduler or database to reach.
  const agent = new Agent()
  const result = await agent.invoke(req.body.prompt)
  res.json({ reply: result.lastMessage })
})

app.listen(3000)

Run it with tsx server.ts.

Use any model provider

The model is one object you hand to the agent. Amazon Bedrock is the default, and every other provider is a one-line swap; the rest of your agent code does not change.

Python
TypeScript

from strands import Agent

# Amazon Bedrock is the default, so no model object is required.
agent = Agent()
print(agent("What can you help me build?"))

from strands import Agent
from strands.models.anthropic import AnthropicModel

agent = Agent(model=AnthropicModel(client_args={"api_key": "<KEY>"}, model_id="claude-sonnet-5"))
print(agent("What can you help me build?"))

from strands import Agent
from strands.models.openai import OpenAIModel

agent = Agent(model=OpenAIModel(client_args={"api_key": "<KEY>"}, model_id="gpt-5.4"))
print(agent("What can you help me build?"))

from strands import Agent
from strands.models.gemini import GeminiModel

agent = Agent(model=GeminiModel(client_args={"api_key": "<KEY>"}, model_id="gemini-2.5-flash"))
print(agent("What can you help me build?"))

from strands import Agent
from strands.models.ollama import OllamaModel

agent = Agent(model=OllamaModel(host="http://localhost:11434", model_id="llama3.1"))
print(agent("What can you help me build?"))

import { Agent } from '@strands-agents/sdk'

// Amazon Bedrock is the default, so no model object is required.
const agent = new Agent()
const result = await agent.invoke('What can you help me build?')
console.log(result.lastMessage)

import { Agent } from '@strands-agents/sdk'
import { AnthropicModel } from '@strands-agents/sdk/models/anthropic'

const agent = new Agent({
  model: new AnthropicModel({ apiKey: '<KEY>', modelId: 'claude-sonnet-5' }),
})
const result = await agent.invoke('What can you help me build?')
console.log(result.lastMessage)

import { Agent } from '@strands-agents/sdk'
import { OpenAIModel } from '@strands-agents/sdk/models/openai'

const agent = new Agent({
  model: new OpenAIModel({ apiKey: '<KEY>', modelId: 'gpt-5.4' }),
})
const result = await agent.invoke('What can you help me build?')
console.log(result.lastMessage)

import { Agent } from '@strands-agents/sdk'
import { GoogleModel } from '@strands-agents/sdk/models/google'

const agent = new Agent({
  model: new GoogleModel({ apiKey: '<KEY>', modelId: 'gemini-2.5-flash' }),
})
const result = await agent.invoke('What can you help me build?')
console.log(result.lastMessage)

Ollama runs in the Python SDK only.

See model providers for the full list and per-provider configuration.

Strands harness or the Strands Harness SDK?

Strands gives you two starting points, and you can move between them without a rewrite.

If you want to…	Start with	Why
Get a complete agent harness with tested defaults, in one import	Strands harness	Model, tools, memory, context management, and a production loop are already wired together.
Build the agent yourself and customize every part of the loop	SDK	You define the tools, model, memory, and control flow, and the Strands Harness SDK runs the loop.
Start on Strands harness and drop down for more control later	Compose with the Strands Harness SDK	Strands harness is built on the Strands Harness SDK, so you can change any piece of it without a rewrite.

Weighing Strands against other frameworks or a hand-written loop instead? See choosing an agent foundation.

Language support

Strands Agents SDK is available in both Python and TypeScript.

Feature availability

The table below compares feature availability between the Python and TypeScript SDKs.

Category	Feature	Python	TypeScript
Core	Agent creation and invocation	✅	✅
	Streaming responses	✅	✅
	Structured output	✅	✅
Model providers	Amazon Bedrock	✅	✅
	OpenAI	✅	✅
	OpenAI Responses API	✅	✅
	Anthropic	✅	✅
	Google	✅	✅
	Ollama	✅	❌
	LiteLLM	✅	❌
	Custom providers	✅	✅
	Additional providers	5+	1+
Tools	Custom function tools	✅	✅
	MCP (Model Context Protocol)	✅	✅
	Built-in tools	30+ via community package	4 built-in
Conversation	Null manager	✅	✅
	Sliding window manager	✅	✅
	Summarizing manager	✅	✅
Hooks	Lifecycle hooks	✅	✅
	Custom hook providers	✅	✅
Multi-agent	Swarms	✅	✅
	Graphs	✅	✅
	Workflows	✅	✅
	Agents as tools	✅	✅
	Agent-to-Agent (A2A)	✅	✅
Session management	File, S3, repository managers	✅	✅
Observability	OpenTelemetry integration	✅	✅
Steering	Agent steering	✅	✅
Experimental	Bidirectional streaming	✅	❌