Has it gotten better and good enough? I tried it a few months back and it was pretty crappy. And it's not because of bad models (I used it with the latest Claude at that time) but because of poor harness implementation and UI.
Is it worth trying the latest version to see how it compares with Claude Code? I want OSS, model agnostic implementation to win but I felt the odds are off then. I'd be happy to be proven wrong.
Instead, its strength tends to be a continued improvement over the long term, in a way that commercial software just can't sustain because it needs to show a return on investment.
I use Claude Sonnet 4.5, Gemini 3 Pro Preview, and GPT 5/5-mini with great results on OC. I initially tried it so I could decouple from VS Code extensions while still using my Github Copilot plan like I had been with Roo Code/Kilo Code, but have branched out to also using it with the Claude Code backend and their free models as they come and go.
Definitely worth trying if you haven't picked it up recently.
MIT license and model agnostic
I’d also keep a close eye on Toad which is launching this month:
"Bitcoin is about access, not speculation. It’s designed to be open, fast, low-cost, and free from centralized control. It’s meant to empower people"
This is the most amazing paragraph I think I have ever read, pure gold!
https://blog.identity.foundation/block-contributes-to-dif/
This company seems to be mocking itself.