--- title: AWS open-sources an AI agent it says is 45% cheaper than... description: AWS has open-sourced Strands Harness, a general-purpose AI agent built on its Strands Agents SDK, giving developers a preconfigured agent with file, shell and... canonical: https://daily.dev/posts/aws-open-sources-an-ai-agent-it-says-is-45-cheaper-than-claude-code-and-codex-ztsrmcay8 twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: AWS open-sources an AI agent it says is 45% cheaper than Claude Code and Codex | daily.dev og:description: AWS has open-sourced Strands Harness, a general-purpose AI agent built on its Strands Agents SDK, giving developers a preconfigured agent with file, shell and... og:url: https://daily.dev/posts/aws-open-sources-an-ai-agent-it-says-is-45-cheaper-than-claude-code-and-codex-ztsrmcay8 og:image: https://api.daily.dev/og/posts/ztsrmcAy8.png og:image:alt: AWS open-sources an AI agent it says is 45% cheaper than Claude Code and Codex og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # AWS open-sources an AI agent it says is 45% cheaper than Claude Code and Codex **[The New Stack](https://daily.dev/sources/newstack)** · 7 min read · 1 upvotes · 0 comments ## Summary AWS has open-sourced Strands Harness, a general-purpose AI agent built on its Strands Agents SDK, giving developers a preconfigured agent with file, shell and web tools plus built-in context management, memory, persistent sessions, prompt caching and multi-agent delegation. AWS claims it runs 45% cheaper than Claude Code and Codex across six benchmarks with comparable accuracy, though that advantage narrows to 28% once DeepSeek Harness is included, as DeepSeek ran about 14% cheaper than Strands Harness. The only AWS-tied default is routing model calls through Amazon Bedrock, which can be swapped for Anthropic, OpenAI, Google, or a local Ollama model with one line of code. AWS also offers Bedrock AgentCore as an optional managed hosting layer built by the same team, giving it a commercial path even though Strands Harness runs independently of AWS infrastructure. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### What is AWS Strands Harness and how does it differ from the Strands Agents SDK? Strands Harness is an open source, general-purpose AI agent that sits above the existing Strands Agents SDK, giving developers a preconfigured agent rather than just building blocks. It bundles file, shell, and web tools with built-in context management, memory, persistent sessions, prompt caching, and delegation to other agents, so developers don't have to assemble that machinery themselves. _Teams weighing prebuilt agent harnesses against custom SDK setups can track these comparisons on daily.dev._ ### Is AWS Strands Harness cheaper than Claude Code and Codex? AWS reports Strands Harness came out 45% cheaper than Claude Code and Codex on average across six benchmarks (ALFWorld, ContextBench, GAIA, WebShop, tau3-bench, Terminal-Bench 2.1) with broadly comparable accuracy. On Terminal Bench 2.1 specifically, Strands Harness running Fable 5 cost $56.29 versus Claude Code's $248.05 across 89 trials while scoring higher, 69.7 versus 61.8. However, once DeepSeek Harness is included, the cost advantage over the full field drops to 28%, since DeepSeek Harness ran about 14% cheaper than Strands Harness on matched runs. _Developers deciding between agent harnesses on cost and accuracy can follow benchmark comparisons like this on daily.dev._ ### Does AWS Strands Harness require Amazon Bedrock or AWS infrastructure to run? No, Strands Harness does not require AWS infrastructure. The only default tied to AWS is model access routed through Amazon Bedrock, and that can be overridden with one line of code to use Anthropic, OpenAI, Google, or a locally running model through Ollama. Everything else, including the agent loop, tools, context management, session handling, and delegation, runs on the local machine by default and works the same regardless of model provider. _Developers avoiding vendor lock-in when picking an agent framework can compare provider flexibility on daily.dev._ ## Similar posts on daily.dev - [Build and Run Your Own AI Agent in the Cloud](https://daily.dev/posts/build-and-run-your-own-ai-agent-in-the-cloud-aoostzrec) · Towards Data Science · 1 upvotes · 0 comments --- Tags: [#aws](https://daily.dev/tags/aws), [#ai-agents](https://daily.dev/tags/ai-agents), [#claude-code](https://daily.dev/tags/claude-code), [#amazon-bedrock](https://daily.dev/tags/amazon-bedrock) [View this post on daily.dev](https://daily.dev/posts/aws-open-sources-an-ai-agent-it-says-is-45-cheaper-than-claude-code-and-codex-ztsrmcay8) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"AWS open-sources an AI agent it says is 45% cheaper than Claude Code and Codex","url":"https://daily.dev/posts/aws-open-sources-an-ai-agent-it-says-is-45-cheaper-than-claude-code-and-codex-ztsrmcay8","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/aws-open-sources-an-ai-agent-it-says-is-45-cheaper-than-claude-code-and-codex-ztsrmcay8"},"datePublished":"2026-09-21T18:35:28.072Z","dateModified":"2026-09-21T20:23:53.881Z","description":"AWS has open-sourced Strands Harness, a general-purpose AI agent built on its Strands Agents SDK, giving developers a preconfigured agent with file, shell and...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/cde1f20df6ed1e3ff25486a3135bf8ce?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/cde1f20df6ed1e3ff25486a3135bf8ce?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"The New Stack","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"The New Stack","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/newstack","url":"https://daily.dev/sources/newstack"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/aws-open-sources-an-ai-agent-it-says-is-45-cheaper-than-claude-code-and-codex-ztsrmcay8","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":1},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"aws,ai-agents,claude-code,amazon-bedrock","timeRequired":"PT7M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"The New Stack","item":"https://daily.dev/sources/newstack"},{"@type":"ListItem","position":3,"name":"AWS open-sources an AI agent it says is 45% cheaper than Claude Code and Codex"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/aws-open-sources-an-ai-agent-it-says-is-45-cheaper-than-claude-code-and-codex-ztsrmcay8#faq","mainEntity":[{"@type":"Question","name":"What is AWS Strands Harness and how does it differ from the Strands Agents SDK?","acceptedAnswer":{"@type":"Answer","text":"Strands Harness is an open source, general-purpose AI agent that sits above the existing Strands Agents SDK, giving developers a preconfigured agent rather than just building blocks. It bundles file, shell, and web tools with built-in context management, memory, persistent sessions, prompt caching, and delegation to other agents, so developers don't have to assemble that machinery themselves. Teams weighing prebuilt agent harnesses against custom SDK setups can track these comparisons on daily.dev."}},{"@type":"Question","name":"Is AWS Strands Harness cheaper than Claude Code and Codex?","acceptedAnswer":{"@type":"Answer","text":"AWS reports Strands Harness came out 45% cheaper than Claude Code and Codex on average across six benchmarks (ALFWorld, ContextBench, GAIA, WebShop, tau3-bench, Terminal-Bench 2.1) with broadly comparable accuracy. On Terminal Bench 2.1 specifically, Strands Harness running Fable 5 cost $56.29 versus Claude Code's $248.05 across 89 trials while scoring higher, 69.7 versus 61.8. However, once DeepSeek Harness is included, the cost advantage over the full field drops to 28%, since DeepSeek Harness ran about 14% cheaper than Strands Harness on matched runs. Developers deciding between agent harnesses on cost and accuracy can follow benchmark comparisons like this on daily.dev."}},{"@type":"Question","name":"Does AWS Strands Harness require Amazon Bedrock or AWS infrastructure to run?","acceptedAnswer":{"@type":"Answer","text":"No, Strands Harness does not require AWS infrastructure. The only default tied to AWS is model access routed through Amazon Bedrock, and that can be overridden with one line of code to use Anthropic, OpenAI, Google, or a locally running model through Ollama. Everything else, including the agent loop, tools, context management, session handling, and delegation, runs on the local machine by default and works the same regardless of model provider. Developers avoiding vendor lock-in when picking an agent framework can compare provider flexibility on daily.dev."}}]} ```