claude.vim

I don't think there is something close to Cursor but I'm using `claude.vim` for almost an year and it's pretty good, imo. https://github.com/pasky/claude.vim

Yep! And AWS Bedrock gives you also plenty of other models on the back end, plus better control over rate limits. (But for us the important thing is data residency, the code isn't uploaded anywhere.) Is it ~just about adding another file to https://github.com/codestoryai/sidecar/blob/main/llm_client/... ? I could take a look too - another way for me to test Aide by working with it to implement this. :-) (https://github.com/pasky/claude.vim/blob/main/plugin/claude_... is sample code with basic wrapper emulating Claude streaming API with AWS Bedrock backend.)

Copilot user here, never tried Cursor yet, competition is always good. did a quick check, it's $20/month, and it has a vim plugin: https://github.com/pasky/claude.vim going to give it a spin

I explored how I can use AI when writing software beyond code completion, and I didn't like any of the UX I saw (maybe except Cursor). Well, I do all my work in vim. Claude knows how to use vim! And... you can do anything(!) from vim. Turns out, embedding Claude in vim means you get a fully agentic AI pair programmer in <1000 LoC. (See the GitHub README for examples of what "fully agentic" means.) And if you have some semantic vim tools (jedi.vim, eclim, ...) set up, Claude could use them if instructed. Unlike CLIs, you can review Claude's changes, and keep the chat history. So an editor interface is the killer feature for real work. Sonnet 3.5 won't take your programmer job yet. But it can make you a lot faster, even if you type very fast (especially its one-shot ability is amazing). The trick is not to give up thinking and stay in charg

I was so blown away I just wrote a chat-based integration to vim / neovim (https://github.com/pasky/claude.vim) for it - actually, 95% of the 600 LoC is written by Claude. It is finally on a level where "pair programmer" becomes a way better UX than the "code completion" paradigm. (BTW I think with some further AI-assisted work and using the tools interface, you could mostly match all the web interface features in an integration like this. And using API is less brutally rate limited.)