Python install
pip install "strands-agents==1.64.0"Strands Agents, the open-source, model-driven agent SDK from AWS, in Python and TypeScript: what it is, how the two SDKs compare, when to choose it, and how it relates to Amazon Bedrock and AgentCore.
Strands Agents is an open-source (Apache 2.0) SDK from AWS for building agents. It is model-driven: you give an agent a model, a system prompt and tools, and the model plans the steps and decides when it is done. The SDK supplies the loop around that: tool execution, conversation management, sessions, hooks and policies, multi-agent orchestration, MCP and A2A, and OpenTelemetry tracing. It uses Amazon Bedrock by default and works with Anthropic, OpenAI, Google and other providers.
Current versions: Python strands-agents 1.64.0 with strands-agents-tools 0.9.0 · TypeScript @strands-agents/sdk 1.24.0 (checked 2026-11-19).
Python install
pip install "strands-agents==1.64.0"TypeScript install
npm install @strands-agents/sdk@1.24.0 zodfrom strands import Agent, tool
@tooldef get_weather(city: str) -> str: """Get today's forecast for a city.
Args: city: City name. """ return f"Light rain in {city}, 14°C"
agent = Agent(model="us.anthropic.claude-sonnet-5-5", tools=[get_weather])agent("Do I need an umbrella in Leeds today?")There is no graph to draw and no prompt template to fill: the model sees the tool’s schema, decides to call it, reads the result and answers. Everything else in the SDK is about controlling that loop: bounding it, observing it, persisting it, pausing it for a human, and combining several agents.
| Python | TypeScript | |
|---|---|---|
| Package | strands-agents (+ strands-agents-tools, strands-agents-evals) | @strands-agents/sdk |
| Runtime | Python 3.10+ | Node.js 22+, ESM only |
| Tools | @tool functions (schema from type hints and docstrings) | tool() with Zod schemas, fully typed |
| Providers | Bedrock, Anthropic, OpenAI, Gemini, LiteLLM, Ollama, Mistral, llama.cpp, Llama API, SageMaker, Writer | Bedrock, Anthropic, OpenAI, Google, Vercel AI SDK |
| Multi-agent | Agents as tools, Swarm, GraphBuilder, model-driven graph tool, A2A | Agents as tools, Swarm, Graph, A2A |
| Extras | Evals package, real-time voice (BidiAgent), the larger tool library | Vended tools only |
Both SDKs share the concepts and most names, so moving between them is mostly syntax. Choose by the language of the service the agent lives in; choose Python if you need evals, the wider tool set or a provider only Python supports.
Good fit:
Consider something else when:
These are three different things that work well together:
| Piece | What it is | Where it is covered |
|---|---|---|
| Strands Agents | An SDK: the agent loop runs in your process | This guide |
| Amazon Bedrock | The model service; Strands’ default provider (BedrockModel), plus Guardrails and Knowledge Bases | Model providers |
| Amazon Bedrock AgentCore | Managed infrastructure for agents written with any framework: Runtime (hosting), Memory, Gateway (tools as MCP), Identity, Code Interpreter, Browser, Observability | The Amazon Bedrock guide |
A typical AWS deployment is a Strands agent inside a BedrockAgentCoreApp on AgentCore Runtime, calling Bedrock models, keeping conversations in AgentCore Memory and reaching internal APIs through AgentCore Gateway. Strands does not require AgentCore, or even AWS: the same agent runs in Lambda, a container, or on your laptop against the Anthropic or OpenAI API. Hosting is covered on the production pages (Python, TypeScript).
| Date | Version | Changes |
|---|---|---|
| 2026-10-24 | Py 1.64.0 / TS 1.24.0 | New standalone guide. Python and TypeScript sections with comprehensive, tools and MCP, hooks and interrupts, multi-agent and A2A, observability and evals (Python), recipes and production pages, plus shared diagrams. Replaces the Strands page in the Amazon Bedrock guide; all examples run against the installed packages with an offline Bedrock stub. |