I ran this a couple of times against terminal bench with different models. I saw that some models aren't as good with code mode, but overall codemode doesn't slow them down. I was usually at about 70% on tbench 2.1 with Sol.
The issue I have with existing harnesses is that they try to solve all issues for all people. I have workflows I use with fork, and a history tree view is another important thing I needed. One of the issues they don't solve for me is easy visibility and good recap (Claude is okay ish).
Additionally, I loved Amp Codes UI/UX and was incredibly inspired by iy
Why not Pi and build around it?
Pi built the extension system, I think DeepSeek perfected it. I took what I wanted from Pi, and made it more stable (I think)
Love the idea! Have you run this against any benchmarks?
What were your main UX issues with existing harnesses?
Thanks for the question!
I ran this a couple of times against terminal bench with different models. I saw that some models aren't as good with code mode, but overall codemode doesn't slow them down. I was usually at about 70% on tbench 2.1 with Sol.
The issue I have with existing harnesses is that they try to solve all issues for all people. I have workflows I use with fork, and a history tree view is another important thing I needed. One of the issues they don't solve for me is easy visibility and good recap (Claude is okay ish).
Additionally, I loved Amp Codes UI/UX and was incredibly inspired by iy
Lol how much money did you spend