[novoreorx]

I really wish there were a de facto state-of-the-art coding agent that is LLM-agnostic, so that LLM providers wouldn't bother reinventing their own wheels like Codex and Gemini-CLI. They should be pluggable providers, not independent programs. In this way, the CLI would focus on refining the agentic logic and would grow faster than ever before.

Currently Claude Code is the best, but I don't think Anthropic would pivot it into what I described. Maybe we still need to wait for the next groundbreaking open-source coding agent to come out.

[TeMPOraL]

There is Aider (aider.chat), and it has been there for couple years now. Great tool.

Alas, you don't install Claude Code or Gemini CLI for the actual CLI tool. You install it because the only way agentic coding makes sense is through subscription billing at the vendor - SOTA models burns through tokens too fast for pay-per-use API billing to make sense here; we're talking literally a day of basic use costing more than a monthly subscription to the Max plan at $200 or so.

[therealmarv]

Aider is in a sad state. The maintainer does not "maintain" for quite some time now (look at the open PRs and issues). It's not state of the art definitely but one of the first and best ones in the past. A fork was created, Aider CE, from some members of the Discord community https://github.com/dwash96/aider-ce The fork looks and works promising but there is (sadly) so much more development in the other AI CLI tools nowadays.

[rwestergren]

Agreed. Alternatives seem too "agentic" for me, where Aider strikes the right balance of AI pair programming.

[esafak]

I came to the same conclusion. It's crickets over there: https://github.com/Aider-AI/aider/graphs/contributors

[rwestergren]

With increasingly aggressive usage limits (Claude weekly usage now), "agentic" style of token burning seems much less practical to me. Coming from Aider and trying tools like OpenCode, the "use models to discover the relevant files" etc pattern seems very token heavy and even wasteful - whereas with Aider you include relevant files up front and use your tokens for the real work.

[ssivark]

Opencode (from SST; not the thing that got rebranded as Crush) seems to be just that. I've had a very good experience with it for the last couple of days; having previously used gemini-cli quite a bit. Opencode also has/hosts a couple of "free" models options right now, which are quite decent IMO.

https://github.com/sst/opencode

There are many many similar alternatives, so here's a random sampling: Crush, Aider, Amp Code, Emacs with gptel/acp-shell, Editor Code Assistant (which aims for an editor-agnostic backend that plugs into different editors)

Finally... there is quite a lot of scope for co-designing the affordances / primitives supported by the coding agent and the LLM backing it (especially in LLM post-training). So factorizing these two into completely independent pieces currently seems unlikely to give the most powerful capabilities.

[daigoba66]

> I really wish there were a de facto state-of-the-art coding agent that is LLM-agnostic

Cursor?

It’s really quite good.

Ironically it has its own LLM now, https://cursor.com/blog/composer, so it’s sort of going the other way.

[cesarvarela]

I think Claude Code is the best because it is not agnostic.

[theshrike79]

Vertical integration pretty much, they if they need a feature in CLI the model doesn't support, they can just re-train the next model version.

[bdangubic]

exactly!

[alwillis]

> Currently Claude Code is the best, but I don't think Anthropic would pivot it into what I described.

They don't have to pivot, since it already exists: Claude Code Router [1].

[1]: https://github.com/musistudio/claude-code-router

[theptip]

It’s not gonna happen any time soon. The model is fine-tuned on traces generated by the scaffolding (eg dependent on what tool calls are available), and the scaffolding is co-developed with the strengths/weaknesses of the specific model.

[syspec]

There are actually a lot of those! One of the best things about using them is that you can swap models around at will.

I love to switch models and ask them what they thought of the previous models answer

[therealmarv]

Model agnostic tools I would say:

Roo Code or maybe Kilo (which is a fork of Roo)

[rubenvanwyk]

Goose?