So much negativity in this thread. After seeing the recent demo of gemini cli working in zed, I'm actually pretty excited for standardization in this space.
Helix has been my favorite editor ever since I started using it, but the lack of integrated AI features has been becoming more of a deal-breaker for me lately. Though, I can see why the maintainers are hesitant to build for it, because there hasn't been a standardized protocol. I hope ACP changes that.
I like having a sub agent for "pre-commit fixer" that the main agent uses before committing so it can pass pre-commit checks. I find it useful because it uses less of the main agents context.
In contrast, I find the scope of the ones in this repository a little weird. The claude main agent does great with CLAUDE.md context, so does it really make sense for it to delegate different tasks to a frontend and backend agent and coordinate between the two? Especially when the additional context in the frontend agent definition is a listing of what libraries and patterns are used in the repo?
Helix has been my favorite editor ever since I started using it, but the lack of integrated AI features has been becoming more of a deal-breaker for me lately. Though, I can see why the maintainers are hesitant to build for it, because there hasn't been a standardized protocol. I hope ACP changes that.