# AWS targets AI cost worries with open source agent harness

> Source: <https://www.thestack.technology/aws-targets-ai-cost-worries-with-open-source-agent-harness/>
> Published: 2026-09-22 09:55:06+00:00

As the cost of scaling AI agents gets higher up the CIO priority list, AWS has added an efficiency-focused agent harness to its open source Strands SDK for building agents.

The Strands harness launched on Monday, described by AWS engineers as able to run general-purpose agents at a 28% lower cost when using Claude or GPT models with “nearly equal” benchmark scores.

Principal Engineer Arron Bailiss wrote in a [__blog post__](https://strandsagents.com/blog/introducing-strands-harness/?ref=thestack.technology): “Our default context management largely drove the token-efficiency and accuracy: tool results over ~1500 tokens get truncated, [and] summarization (compaction) triggers when the context window hits above 85%.”

The harness SDK is available [__on GitHub__](https://github.com/strands-agents/harness-sdk?ref=thestack.technology) under an Apache 2.0 license as part of the Strands monorepo for building and running agents in Python and TypeScript.