Strands Harness cuts agent costs by 28% while matching frontier accuracy
Strands harness is a general-purpose agent harness that runs on Claude, GPT, and other models. Across six benchmarks, it costs 28% less than Claude Code, Codex, and similar tools while scoring equal or better. With Fable 5, it cost 77% less than Claude Code and scored higher on Terminal Bench 2.1. Built-in prompt caching and context management drive the savings. One line of Python or TypeScript gets you started; Apache 2.0 licensed.
With Fable 5, Strands harness cost 77% less than Claude Code and scored higher on Terminal Bench 2.1.
- johnmlussier
I am increasingly hesitant to use non-native harnesses - model providers are now starting to train their agents for use within the harness. An eval like terminal bench can only capture so much data. I don't want to have to assess each harness every model release to make sure it's working as well as it can.
- max-privatevoid
Including Ollama support is the new token "open option", like a cross-platform application that claims to support Windows, macOS, and Linux, and targets Ubuntu 16.04 only. Just target the OpenAI-compatible API with custom endpoints, it's not that hard. https://schizo.cooking/schizo-takes/9.html
- theturtletalks
Why is Pi not in the benchmarks? Deepseek beats Strands and its built on Pi so that’s all I needed to know.
- seizethecheese
> With Fable 5, Strands harness cost 77% less than Claude Code and scored higher on Terminal Bench 2.1.
Terminal Bench 2.1 is saturated. Many token saving techniques would save money and score basically the same running Fable 5 against Terminal Bench 2.1. (They claim a better score but don’t say how much better. I’d bet my favorite hat that it’s not statistically significant.)
This is at least the fourth time I’ve seen a project hit front page with a “save money with same score on saturated benchmark” claim.
- Oras
I remember reading about strands SDK and it looked great in terms how everything is an event that you can extend, so this harness feels quite about right.
However, for this kind of customisation, Pi is actually quite great. One of the most things I love about Pi is ability to ask it to create an extension and it does it quite well as it’s part of their docs. Also ability to customise the system prompt to avoid the clutter that Claude Code add (around 20k system prompt that mostly had nothing to do with the code).
The demo was showing something I have created for my Pi setup, which is asking me in each new session which skills and MCP I would to enable for the session. This works quite well if you have multiple projects where you don’t need all skills but just a small subset