Claude Agent SDK vs AWS Strands Agents: Which to Build On

Both SDKs do the same basic job: give a language model tools and let it act on its own. The Claude Agent SDK is Anthropic's library for running the same agent loop that powers Claude Code inside your own application, and it only drives Claude models. AWS Strands Agents is an open-source, Apache-2.0 framework that runs any model on any cloud, with Swarm, Graph, and Workflow primitives for coordinating multiple agents plus support for the Agent2Agent (A2A) protocol. Pick the Claude Agent SDK when you want a tight, batteries-included harness built around one model family. Pick Strands when you need model or cloud portability, or when you are already building multi-agent systems that need to talk to agents outside your own stack.

Key takeaways

  • Claude Agent SDK is single-vendor (Claude only) and ships under Anthropic's Commercial Terms of Service; Strands Agents is Apache-2.0 and runs Bedrock, Anthropic, OpenAI, Gemini, and Ollama models interchangeably (Source: Anthropic Agent SDK Overview; AWS Strands Agents 1.0 Announcement).
  • Strands' four multi-agent primitives, Agents-as-Tools, Handoffs, Swarms, and Graphs, plus A2A protocol support, give it a coordination story the Claude Agent SDK does not natively match.
  • The Claude Agent SDK's subagents, one-line MCP server config, and native Bedrock/Vertex/Azure auth make it the faster path if your stack is already Claude-only.
  • Strands now pulls roughly 33 million PyPI downloads a month, so the "which one" question has real production stakes, not just launch-week curiosity (Source: PyPI Download Stats).

The Short Answer: Same Job, Opposite Bets

An AI agent, in the SDK sense, is a loop: a model reads a goal, picks a tool, reads the result, and repeats until it is done. Both SDKs implement that loop for you so you do not have to write the retry and tool-dispatch logic yourself.

Where they split is the bet each vendor made. The Claude Agent SDK bets that most teams standardizing on Claude want the exact agent loop, context management, and tool set that already powers Claude Code, just callable as a library (Source: Anthropic Agent SDK Overview). Strands Agents bets that teams want to swap models and clouds without rewriting their agent logic, so it treats the model as a pluggable dependency behind a common interface (Source: AWS Strands Agents 1.0 Announcement). Neither bet is wrong; they serve different constraints.

What Strands Agents 1.0 Actually Shipped

Strands launched as a preview in May 2025, then reached its 1.0 milestone with a post titled "Introducing Strands Agents 1.0: Production-Ready Multi-Agent Orchestration Made Simple," published by AWS engineers Ryan Coleman and Belle Guttman (Source: AWS Strands Agents 1.0 Announcement). That release added four multi-agent primitives: Agents-as-Tools (specialized agents exposed as callable tools), Handoffs (an agent passing a task to another agent or a human), Swarms, and Graphs (explicit, conditional-routing workflows).

The same release added support for A2A, an open protocol that lets agents built on different frameworks discover and call each other through auto-generated capability cards, and a SessionManager abstraction that persists conversation state to an external store such as Amazon S3 so an agent survives a restart or a scaling event (Source: AWS Strands Agents 1.0 Announcement). Coleman and Guttman framed the release as closing a gap between prototype and production: "Strands 1.0 brings the same level of simplicity to multi-agent applications that Strands has provided for single agents," they wrote, pairing that simplicity with the new A2A support (Source: AWS Strands Agents 1.0 Announcement). Notably, Anthropic is listed as one of the model-provider contributors to Strands, alongside Meta, OpenAI, Cohere, Mistral, Stability, and Writer, meaning Claude can run inside a Strands agent even though Strands is not an Anthropic product.

Why This Comparison Matters Now

A framework decision made in a preview month rarely stays interesting a year later, but Strands kept compounding. The strands-agents Python package is now pulling close to 33 million downloads a month, against 69.6 million total downloads since launch, and the GitHub repo sits at roughly 6,400 stars on the current python/v1.45.0 release (Source: PyPI Download Stats; Source: strands-agents/sdk-python (GitHub)). A May 21, 2026 release, python/v1.41.0, folded Swarm and Graph orchestration into a dedicated MultiAgentPlugin, a sign the multi-agent surface is still actively maintained, not a launch-week feature that stalled.

That scale is why the comparison is no longer academic. Teams choosing an agent SDK in mid-2026 are choosing between a fast-growing, cloud-agnostic default and a narrower, deeply-integrated one, and the wrong call is expensive to unwind once tool integrations and prompts are written against a specific API.

Claude Agent SDK: What You Get

Install it with pip install claude-agent-sdk (Python 3.10 or later required) or npm install @anthropic-ai/claude-agent-sdk, and you get the same agent loop, context management, and 10 built-in tools that ship inside Claude Code: Read, Write, Edit, Bash, Monitor, Glob, Grep, WebSearch, WebFetch, and AskUserQuestion (Source: Claude Agent SDK Overview (Anthropic)).

Subagents are defined in-process with AgentDefinition, letting a main agent delegate a focused task (say, a code review) to a specialized one and read back the result. MCP, the Model Context Protocol that lets an agent call external tools and data sources through a common interface, attaches with a single dict, for example mcp_servers={"playwright": {"command": "npx", "args": ["@playwright/mcp@latest"]}}, and hooks like PreToolUse and PostToolUse let you log, block, or transform tool calls. Cloud auth is a single environment variable: CLAUDE_CODE_USE_BEDROCK=1, CLAUDE_CODE_USE_VERTEX=1, or CLAUDE_CODE_USE_FOUNDRY=1 for Bedrock, Vertex AI, or Azure Foundry respectively. Anthropic's own guidance is blunt about where the SDK fits: interactive development and one-off tasks stay on the Claude Code CLI, while CI/CD pipelines, custom applications, and production automation move to the SDK (Source: Claude Agent SDK Overview (Anthropic)).

Licensing and Vendor Lock-In

This is the part most comparisons skip, and it is the one that determines whether you can change your mind later. Strands ships under Apache-2.0, is free to fork, and already runs Bedrock, Anthropic, OpenAI, Gemini, Ollama, and custom model providers behind one interface (Source: AWS Strands Agents 1.0 Announcement). Swapping the underlying model is a config change, not a rewrite.

The Claude Agent SDK is governed by Anthropic's Commercial Terms of Service and only drives Claude models; there is no supported path to point the same agent loop at a non-Anthropic model (Source: Claude Agent SDK Overview (Anthropic)). That is a deliberate trade, not an oversight: in exchange, you get tooling built and maintained by the same team that ships the model, tested against the exact agent loop Claude Code uses in production every day.

Claude Agent SDK vs Strands Agents at a Glance

The feature and licensing details below come straight from each vendor's own documentation, not a third-party summary (Source: Claude Agent SDK Overview (Anthropic); Source: AWS Strands Agents 1.0 Announcement).

Claude Agent SDKAWS Strands Agents
LicenseAnthropic Commercial TermsApache-2.0
Model supportClaude models onlyBedrock, Anthropic, OpenAI, Gemini, Ollama, custom
Multi-agent patternsSubagents (in-process delegation)Agents-as-Tools, Handoffs, Swarm, Graph
Cross-framework protocolNot built-inA2A (Agent2Agent)
Tool protocolMCP (single dict config)MCP-native
Installpip install claude-agent-sdkpip install strands-agents strands-agents-tools
Cloud authEnv-var flags for Bedrock, Vertex, Azure FoundryAWS-native, IAM-aware
Best forClaude-only stacks wanting Claude Code's exact loopMulti-model, multi-cloud, or cross-framework agent systems

When to Pick Each

If your team already standardized on Claude and wants the shortest path from prototype to production, the Claude Agent SDK wins on integration depth: subagents, hooks, and session resume all come from the same codebase that powers Claude Code, so behavior transfers directly between the CLI and your service (Source: Claude vs Strands Agents (LOW/CODE Agency)).

Pick Strands when any of these apply: you need to run more than one model provider behind the same agent code, your infrastructure is AWS-native and you want IAM-aware tools and Lambda-friendly deployment, or you are building a multi-agent system that needs Swarm or Graph coordination, or needs to hand off work to agents built on a different framework entirely via A2A. Operator note (first-hand): running pip install claude-agent-sdk against pip install strands-agents strands-agents-tools on a clean virtualenv, the Claude SDK reaches a working query() call in one file with a single ANTHROPIC_API_KEY export, while the Strands quickstart needs a model-provider choice and, for Bedrock, an IAM role before the first agent runs. That extra step buys Strands its portability; it is not free.

FAQ

What are the key differences between Strands Agents and the Claude Agent SDK?

Strands Agents is an open-source, Apache-2.0 framework that runs any model provider and adds Swarm, Graph, and A2A multi-agent coordination. The Claude Agent SDK is a commercially licensed library that only drives Claude models but mirrors Claude Code's exact agent loop, tools, and subagent system (Source: AWS Strands Agents 1.0 Announcement; Claude Agent SDK Overview (Anthropic)).

Why use the Claude Agent SDK instead of Strands?

Choose the Claude Agent SDK when your stack is already Claude-only and you want the identical agent loop, built-in tools, hooks, and subagent system that power Claude Code, with no abstraction layer between your code and the model. Teams standardizing on one vendor generally reach a working agent faster this way than building on a multi-provider framework.

Is AWS Strands Agents only for AWS?

No. Strands runs on Amazon Bedrock, but the same interface also supports the direct Anthropic API, OpenAI, Gemini, Ollama for local development, and custom model providers. The framework itself is a Python and TypeScript package that deploys anywhere those runtimes run, including Lambda, Fargate, EKS, Docker, or a plain server outside AWS entirely.

Can Claude models run inside a Strands agent?

Yes. Anthropic is listed as one of the model-provider contributors to Strands Agents, alongside Meta, OpenAI, Cohere, Mistral, Stability, and Writer. That means a Strands-based agent can call Claude models directly today while keeping the option open to swap in a different provider later without rewriting the agent's tool or orchestration logic.

Does the Claude Agent SDK support multi-agent orchestration?

It supports subagents: a main agent delegates a focused task, like a code review, to a specialized in-process agent defined with AgentDefinition, then reads back the result. It does not ship Strands-style Swarm or Graph primitives, and it has no native A2A protocol support for discovering or calling agents built outside its own process.

Related coverage

References