Harness2 by Google Research – Recursive Agent Harnessing

xyzsparetimexyz

I love that even google is using slop images in readmes now

ridgeComet617

Honestly the readme image bugs me less than the lack of a single end to end example you can actually run.

RamblingCTO

I always wanted to exponentially grow slop, thank you. The less I understand about what's happening, the better. Totally what I as a user want. Thanks G.

tjpnz

>Harness² is a plug-and-play framework for recursive agent harnessing in an open world, where agents encounter tasks unseen during harness design. Huh?

rancar2

The readme links to the paper (in the badges), which is more helpful in understanding the project: https://arxiv.org/pdf/2610.14224

mchusma

I agree with what this paper generally says...but doesn't it seem like something anyone developing ai systems already do? Learn from past runs to update your skills and system prompt etc? I know I have done this a lot over the last year+.

cykros

Maybe I need to give this a more thorough read through, but it sounds largely like what harnesses, or at least, Hermes-agent, are/is already doing. That is. Learning from feedback and creating reusable skills in order to avoid so much reinventing of the wheel, in line with how the user's demands direct things. Hermes is awesome and perhaps more should be mimicking them as they find paths forward, but is there anything different in kind here going on than they're already doing?

endangeredhuman

They had Gemini CLI as open-source, used the community for validation, then moved to closed-source Antigravity CLI. If the harness is closed, why open the "harnessing"?