Strands introduces their state-of-the-art agent harness that delivers frontier-level performance while reducing token costs by 28%.

Presents SoL-Pi, a method for improving coding agents through recursive self-improvement loops that reduces token usage by 44.7-49.0% and API costs by about one third while maintaining performance on code generation tasks.

Guide on creating a custom agent harness for building and deploying intelligent agents with LangChain, covering frameworks and infrastructure options.

Kiro Crew 0.6.0 introduces selectable agent harnesses, remote crew capabilities, and an Apps Launchpad, while requiring Python 3.12 and improving chat interface organization for long-running tasks.