Strands: Agent Frameworks

Founded 2025|Seattle, WA|10000+ people

What is Strands?

Strands Agents is an open-source AI agent SDK developed by AWS that takes a model-driven approach to building and running AI agents in just a few lines of code. Launched as a preview in May 2025, Strands reached version 1.0 in July 2025, bringing production-ready multi-agent orchestration capabilities. The framework uses the reasoning abilities of modern LLMs to handle planning and tool usage autonomously, eliminating the need for hardcoding complex task flows.

Strands is actively used in production by multiple AWS teams, including Kiro, Amazon Q Developer, and AWS Glue. The SDK supports multiple AI providers including Amazon Bedrock, Anthropic, Gemini, LiteLLM, Llama, Ollama, OpenAI, and Writer, making it truly provider-agnostic. Strands 1.0 introduced new primitives for multi-agent architectures, support for the Agent-to-Agent (A2A) protocol, a session manager for retrieving agent state from remote datastores, and improved async support throughout the SDK.

The framework offers comprehensive features including multi-modal support (text, speech, and image processing), rich AWS service integrations, extensibility for custom tools, and robust observability capabilities. With natural language workflow definitions through Agent SOPs and integration with Model Context Protocol (MCP), Strands provides a modern, scalable approach to building production-grade AI agents.

Strengths and tradeoffs

What this tool does well, and the limitations to keep in mind.

Pros

Production-proven by AWS teams (Amazon Q, AWS Glue)
True provider-agnostic support for 8+ LLM providers
Comprehensive multi-agent orchestration with A2A protocol
Rich AWS ecosystem integration
Open-source with active development

Cons

Relatively new framework (launched 2025)
AWS ecosystem bias in design and tooling
Variable costs depending on chosen providers

Plans & pricing

What's included in each plan, and how the tiers compare.

Open Source

Free

Full SDK access
Multi-agent orchestration
Multi-modal support
Provider-agnostic
Community support

AWS Bedrock

Variable

Per request

Pay for model usage
AWS infrastructure
Production scalability
Enterprise support

Custom Providers

Variable

Based on provider

OpenAI pricing
Anthropic pricing
Gemini pricing
Custom model pricing

View official pricing page

Using Strands with Respan

Integrate Strands Agents with Respan to gain comprehensive observability into your multi-agent systems, monitor LLM calls across providers, track agent reasoning chains, and optimize costs across AWS Bedrock and other AI providers.

Monitor agent orchestration and multi-agent communication patterns
Track LLM usage and costs across Amazon Bedrock, Anthropic, OpenAI, and other providers
Evaluate agent reasoning quality and tool usage effectiveness
Debug complex agent workflows with detailed trace analysis
Optimize prompt performance and reduce latency in production

Run Strands in production with Respan

10KFree traces/mo

1,000+Models

5 minSetup

Respan lets you trace LLM and agent calls across any model or framework, A/B test prompts on production traffic, and route requests across 1,000+ models through one gateway.

Try Respan free

Best Strands alternatives & competitors

Top companies in Agent Frameworks you can use instead of Strands.

LangChain

LangChain Expression Language (LCEL)