agent-shell

hmm, I haven't tried Carbon yet. But I have been using Argon on and off via agent-shell - https://github.com/xenodium/agent-shell and unofficial ACP client. In my limited usage, it has fixed issues which has not been correctly fixed by sol-6.1 (medium) - https://github.com/auto-gnufied/markdown-modern/commit/a189a... I am also using it via Google pro tier and did not immediately run into quota issues. But as someone else said in previous discussion of this - Google Pro tier already includes lot of stuff (including Youtube premium etc), the AI plans are just a nice addon.

Not who you replied to, but: I use agent-shell and I love the ecosystem that's being created there: https://github.com/xenodium/agent-shell And for claude interacting back with emacs: Some folks like having an MCP package. I agree that gives you a bit more control. But I live dangerously and run emacs in daemon mode and tell claude to just run emacsclient to execute elisp as needed. It works amazingly well. Claude has full visibility into my editor and together we can pretty much do anything. In fact, I increasingly think of emacs as just a live lisp machine. It's a surface that I and the agents can interact against. It acts as a document store, database, control surface, etc.

Emacs makes for excellent Agent harness. With https://github.com/xenodium/agent-shell/ , this is the only UI I use for working with agents. What makes this great is infinite hack-ability of the interface and agents have become pretty good at writing elisp packages, so basically you can have a workflow exactly how you want. I wish I had time to make a screencast about this, but If you are a Emacs user and not using Emacs for agentic stuff, you are missing out IMO.

Support vendor agnostic tools offering agent integrations through the likes of Agent Client Protocol https://agentclientprotocol.com ps. I built Emacs integration through ACP https://github.com/xenodium/agent-shell

Never heard of that one. The most popular ways for agent stuff seems to be https://github.com/xenodium/agent-shell , or just opening a terminal in emacs and using claude code. If you want to run it through an emacs terminal, consider using https://github.com/dakra/ghostel#ghostel (or vterm, or eat)

Agent Shell connected via ACP to local Claude Code. https://github.com/xenodium/agent-shell

You should give https://github.com/xenodium/agent-shell and https://github.com/dakra/ghostel a shot. With ghostel I genuinely mix up which window (frame) is emacs rather than the native Ghostty window.

> I wish more AI harnesses could also have a dumb-terminal mode you don't need that, you can use an acp (agent-client protocol) client like agent-shell - https://github.com/xenodium/agent-shell I've tried it with cursor and it works okay.

I recently read someone [1] make the case for a sweet spot blending the best of CLI agents (fast, keyboard-driven, in a terminal) and desktop agents (rich UI: inline images, diffs). This resonated with me as fairly on point to what agent-shell has been going for, except from inside Emacs, which arguably gets you plenty of goodies at once: it's fast and text/keyboard-driven like a terminal, also renders inline images, markdown and tables like a desktop app, but with first class integration into your text editor (no context switch). Also, since it's all elisp, you can bend any of it to your own workflow. This release pulls more of that desktop-like experience with richer TAB navigation, actionable items (resizable images) and a more chat-like experience. Also worth highlighting, agent-shell is vendor-neutral: it speaks ACP, so you can drive

Also, if a slash command is missing, that's because the model's ACP client doesn't implement it: https://github.com/xenodium/agent-shell#why-doesnt-agent-she...

Not the person you're replying to, and I have no idea what they were referring to, but I use agent-shell.el and it is incredible: https://github.com/xenodium/agent-shell xenodium is doing some amazing work (and not just on agent-shell, either!)

I use it via the gnu emacs integration :P https://github.com/xenodium/agent-shell

> It’s clearly being ran by someone who comes from a social app or sales app growth hacking background. I fixed that by using cursor the agent but not the UI. I'm just running cursor in GNU Emacs via agent-shell (https://github.com/xenodium/agent-shell). Their cli client (aptly named "agent") supports ACP (agent client protocol) so the UI can be skipped altogether. I know this sounds like a meme ("use x in emacs") but at this point at the very least i can keep my workflows and my UI all the same and focus on my work rather than "where did $company put $feature this month".

Absolutely. I do all my LLM-assisted work inside Emacs using Agent Shell and Emacs skills: https://github.com/xenodium/agent-shell https://github.com/xenodium/emacs-skills

It's not just Zed, Emacs has has a thriving ACP implementation in agent-shell[0], and allows for some very cool integrations[1]. There are a fair number of other clients[2] as well. [0]: https://github.com/xenodium/agent-shell [1]: https://www.youtube.com/watch?v=HJQ86HuSIJI [2]: https://agentclientprotocol.com/get-started/clients