Live data from Hacker News

Claude Code IDE integration for Emacs

github.com

161–170 of 281 posts

Re: Claude Code IDE integration for Emacs

#161

Earlier quoted context omitted.

Neovim and to an extent emacs are where corporate IDE vendors go for ideas. From ergonomics of the UX, performance, portability, design sense (!!) and theming? It's like Sun and GNU in the 90s. Those UI/UX folks getting pissed their perfect HSL wheel and black balance got dicked with by some PM which is why the GitHub theme is great not legendary? They go home and rice Arch or NixOS and just shit on the dayjob stuff.…

>stellarwind That sure is a choice of name for your project!

Ha, it's a working title. The name I want for what this will become is `straylight v4`, but that name belongs to a friend, and it has to be a worthy successor to earn being called that. :)

Re: Claude Code IDE integration for Emacs

#162

Earlier quoted context omitted.

> vim and emacs could potentially have a huge advantage. They always have had. It just depends on what people perceive to be advantageous. For me, VSCode's and IntelliJ's closed model for extensibility is a huge downside. By "closed" I mean - restrictive plugin APIs, sandboxed execution environment, corporate gatekeeping, opaque core, etc. I don't even try to "shop for more features" anymore, learning Emacs allows me…

I went (10 years ago) JetBrains because of emacs. Back then, they were the Kool Kid in town that made emacs-style functionality more accessible. More and more they've become just another IDE with too-much-to-do. Still one of (the?) best, but as soon as your editor becomes impractical to use to edit a text file... (because it really just likes to work on projects...). But yeah, emacs remains functional in a way that J…

Oh boy, I was such a jetbrains kiddo, I can't even tell you. I had posters on my wall with keybinding and commands cheat sheets, I knew people working for JetBrains by their names, I talked to them regularly, it almost felt like we were on the same team. I tried to debug and understand plugins, even wanted to develop one, but somehow never got to do that - the hacking mindset of a habitual programmer just wasn't there yet - I kinda went with the status quo - "if IntelliJ doesn't have this feature, maybe I don't even need to know about it..." I've discovered and reported so many bugs on YouTrack, I still receive updates on them, even today - some of them date to 2009, things that JetBrains never even tried to improve since then.

WebStorm was probably the biggest reason why it took me so long to switch to Emacs. My biggest fear was that if I invested in learning Emacs, and at some point I'd inevitably find that something simply couldn't be done in it, and I'd be forced to go back and my idyllic life would be ruined. God, how wrong I was. Not only have I found _everything_ I needed, I actually discovered radically different ways of solving problems.

In the end, turns out one thing jetbrains did right - they have nailed the marketing - I surrendered without resistance. My biggest regret is not trying out Emacs sooner. I wish someone very persuasive showed me things I did not know were possible. That's why I get very vocal about it - kids have zero idea what they'd be missing.

Re: Claude Code IDE integration for Emacs

#163

Earlier quoted context omitted.

> Should I be learning how to debug elisp better to understand how the commands interact with my environment? Hell yeah, you should. I just don't understand how the heck people would claim to be using Emacs for decades and still not knowing how to use the built-in profiler, edebug, apropos, macro expansion, advising system, indirect buffers, etc. They would complain how "fickle" Emacs is, without even realizing that…

> Hell yeah, you should. I just don't understand how the heck people would claim to be using Emacs for decades and still not knowing how to use the built-in profiler, edebug, apropos, macro expansion, advising system, indirect buffers, etc. Yes I'm familiar with apropos, macros/extensions, advising, indirect buffers, and a lot of stuff. I've just never debugged elisp mostly because I haven't had a hard time just iter…

edebug is great! It was way ahead of its time.

Re: Claude Code IDE integration for Emacs

#164

Earlier quoted context omitted.

Sure. I'm experimenting like everyone else, but I mostly use gptel as the primary interaction surface and Claude Code for a range of refactorings and other "more than mechanical, less than creative" edits. Both of these are very (!!!) well complimented by magit, which is so good at AI supervision it seems designed for it, by a genius. For Claude Code I'm rapidly switching anything I want "vibe coded" into Hadkell for…

Sounds cool. What sort of stuff do you develop, and who's paying for it?

I work for a medium-sized proprietary/discretionary fund. AFAIK the principles trade all kinds of stuff, macro stuff. My current job is tuning up the execution on the cryptocurrency adjacent desk, but not like blockchain stuff, it's somewhere in between OG crypto trading stuff and like Wall St. HFT circa 2006-2010 depending on how you measure, it's in the "kernel bypass matters but FPGAs are still exotic" sort of regime, some of it is legacy REST APIs still but FIX 4.2 SBE and other real finance protocols (and real banks and stuff) are starting to be a part of the ecosystem.

I aspire to be a lot faster than this stuff (I've built faster stuff than this) but this is quite a good library (amazingly good by OSS standards, good stuff in this area is rarely OSS, props to the maintainers): https://github.com/crypto-chassis/ccapi, in particular this library does a really good job of being correct across a lot of surface area, it's serious people doing it, and there are forks of it that use DPDK floating around.

If by who's paying for it you mean the big Anthropic bill? My boss's boss is pretty enlightened about the fact that learning how to use AI well is expensive, so when I'm on a tight schedule I get a pretty forgiving budget for the model fees. It's a pretty serious perk in the sense that it's really expensive to master using these things :)

Re: Claude Code IDE integration for Emacs

#165

Earlier quoted context omitted.

Sure. I'm experimenting like everyone else, but I mostly use gptel as the primary interaction surface and Claude Code for a range of refactorings and other "more than mechanical, less than creative" edits. Both of these are very (!!!) well complimented by magit, which is so good at AI supervision it seems designed for it, by a genius. For Claude Code I'm rapidly switching anything I want "vibe coded" into Hadkell for…

I have a couple more! I take it this is all back-end work? Have you tried out one of the Haskell-y front-end languages? Elm? > Both of these are very (!!!) well complimented by magit, which is so good at AI supervision it seems designed for it, by a genius. Can you expand a little on this point?

I very much recommend just watching some of the great `magit` videos on youtube, but later on when I have time I'll do a little `asciinema` of like, a Claude Code interaction and reviewing / piecewise incorporating the bots changes, so if you check back here tonight or tomorrow latest I'll do a little demo.

Re: Claude Code IDE integration for Emacs

#166

Earlier quoted context omitted.

Sure. I'm experimenting like everyone else, but I mostly use gptel as the primary interaction surface and Claude Code for a range of refactorings and other "more than mechanical, less than creative" edits. Both of these are very (!!!) well complimented by magit, which is so good at AI supervision it seems designed for it, by a genius. For Claude Code I'm rapidly switching anything I want "vibe coded" into Hadkell for…

Sounds wild! What have you built this way? Also as another Emacs user I'm wondering what lesser known packages or elisp snippets do you use? gptel, magit, tramp and org-mode are the usually touted killer features, but what else do you use in the Emacs ecosystem?

Sorry, I saw another commenter ask about the dots but for some reason didn't see this one, all the key files are linked as gists here: https://news.ycombinator.com/item?id=44817968

Let me know if you have any questions (or suggestions for that matter, it's rough in places).

Re: Claude Code IDE integration for Emacs

#167
I love(d) Emacs a lot a few years ago. Until my job and obligations didn’t leave me much room for tinkering. There is an inverse relationship between tinkering and getting things done. Although LLMs changed the game: These days I leave the tinkering to Claude Code. And can change every aspect of my tools within seconds. No waste of time, max output. But I still moved away. why? Because I believe the Emacs way is wrong. And here’s why: If I‘d do all my computing in Emacs, I‘d miss out on MailMate as a mail app, on Ghostty as my terminal, on Nvim as an editor, Python as my automation language (instead of Elisp where buffer is the data type used most?) and so much more. I like the Unix way: Do one thing, and do it really good: fzf, ripgrep, yazi, lazygit, absolutely awesome apps for the console. And all can communicate with each other via pipes! So I moved away, and never was happier.

Re: Claude Code IDE integration for Emacs

#168
post #12
post #9

Like LSP and tree-sitter, I think AI coding tools like Claude Code or Aider are very good news for niche editors like Emacs or Vim. Instead of struggling about implementing advanced IDE-like features, they can integrate with these tools relatively easily, and focus on other editing related features that set them apart. In fact, IMO it makes these editors more competitive because they are highly customizable and easie…

Is there a standard for integrating agentic coding tools into an editor similar to how an LSP allows the integration of language-specific features?

I'm sure some other users can give you better answers, but I'm a bit curious what you mean by "standard".

FWIW, Vim (and presumably emacs) can run terminals as well as do things like ssh and ftp. Though I'm pretty sure the easiest thing to do would just be to use the Ctrl-R pattern in vim and have it send curl requests in a different buffer. As far as I'm aware, all the major LLM platforms have APIs that can be accessed through curl (or any other way you want to to GET/PUT requests). Here's something I found with a quick Google search[0].

So I'm not sure there needs to be "a standard" so much as "can it do http requests?" which is yes. I mean with this I think you can also see it wouldn't be too hard to set up and connect to a LLM hosted on the LAN. Could do it all through ssh

[0] https://arjunaravind.in/blog/using-vim-as-a-http-client/

Re: Claude Code IDE integration for Emacs

#169
post #20

Earlier quoted context omitted.

Queue the old adage ... "Emacs is a great operating system, what it needs is a good editor." I'm not sure there is a rigid enough definition of IDE to say whether Emacs qualifies or not. I think it does by virtue of its extensibility, but I could definitely see a legit argument that it's merely an editor because it doesn't have a lot of the tooling of something more modern. I think what you consider to be an IDE (Int…

"Cue"

A pro tip - add a clause in your LLM prompt to randomly misspell words, so people can't blame you for an aislopper. :)

Re: Claude Code IDE integration for Emacs

#170

Earlier quoted context omitted.

I just like having a neovim terminal open with claude code open

I think that’s a decent approach, but doesn’t the performance of a Neovim terminal bother you? It simply does not feel as good as a native terminal pane. It’s not as bad as VSCode’s terminal pane, but it still leaves something to be desired.

I use Neovim + kitty (https://sw.kovidgoyal.net/kitty/conf/) and the performance is phenomenal. Everything is instant. kitty also has a built-in robust layout system so I ended up ditching tmux entirely for it.
Post reply on HN