The way Claude Code is going is exactly what I want out of a agentic coding tool with this "unix toolish" philosophy. I've been using Claude code since the initial public preview release, and have seen the direction over time.<p>The "golden" end state of coding agents is that you give it a Feature Request (EG Jira ticket), and it gives you a PR to review and give feedback on. Cursor, windsurf, etc, are dead ends in that sense as they are local editors, and can not be in CI.<p>If you are tooling your codebase for optimal AI usage (Rules, MCP, etc), you should target a technology that can bridge the gap to headless usage. The fact Claude Code can trivially be used as part of automation through the tools means it's now the default way I thinking about coding agents (Codex, the npm package, is the same).<p>Disclaimer, I focus on helping companies tool their codebases for optimal agent usage, so I might have a bias here to easily configurable tools.
Claude Code is my favorite way to use LLMs for coding.<p>However I feel what we really need is to have an open source version of it where you can pass any model and also you can compare different models answers.<p>(Aider and other alternatives really doesn't feel as good to use as Claude Code)<p>I know this is not what anthropic would want to do as it removes their moat, but as a consumer I just want the best model and not be tied to an ecosystem. (Which I imagine is the largest fear of LLM model providers)
Aider has had support for Python and shell scripting [0] for a long time.
I made a screencast [1] recently that included ad-hoc bash scripting aider as part of the effort to add support for 130 new programming languages. It may give a flavor for how powerful this approach can be.<p>[0] <a href="https://aider.chat/docs/scripting.html" rel="nofollow">https://aider.chat/docs/scripting.html</a><p>[1] <a href="https://aider.chat/docs/recordings/tree-sitter-language-pack.html" rel="nofollow">https://aider.chat/docs/recordings/tree-sitter-language-pack...</a>
more context from the claude code team: <a href="http://latent.space/p/claude-code" rel="nofollow">http://latent.space/p/claude-code</a><p>you can skim the transcript but some personal highlights:<p>- anthropic employees, with unlimited claude, average to $6/day of usage<p>- headless claude code as a "linux" utility that you use everywhere in CI is pretty compelling<p>- claude code as a user extensible platform<p>- future roadmap of claude code: sandboxing, branching, planning<p>- sonnet 3.7 as a persistent, agentic model
If I was making an AI code assistant, the last thing I would do is to lock it in to a particular foundation model provider.<p>The only possible way for this to be a successful offering is if we have just now reached a plateau of model effectiveness and all foundation models will now trend towards having almost identical performance and capabilities, with integrators choosing based on small niceties, like having a familiar SDK.
Claude Code could already be used in non-interactive mode, and by extension it could be integrated into other apps in the same manner as any other UNIX command line utility.<p>This SDK currently supports only command line usage. Isn't that just what we already had?<p>I don't understand what's actually new here. What am I missing?
You can use this in the cloud through a nice UI in <a href="https://cloudcoding.ai/chat" rel="nofollow">https://cloudcoding.ai/chat</a>
<a href="https://cloudcoding.ai/" rel="nofollow">https://cloudcoding.ai/</a> is a way to use a similar claude code sdk in the cloud!
I would also recommend Codebuff (<a href="https://www.codebuff.com/">https://www.codebuff.com/</a>), a great CLI code assistant comparable to Claude Code, which can save a lot on token costs.<p>(I am not affiliated with this project, just a user.)
> You may not access or use, or help another person to access or use, our Services in the following ways:
> 2. To develop any products or services that compete with our Services, including to develop or train any artificial intelligence or machine learning algorithms or models or resell the Services.<p>Can somebody please tell me what software product or service doesn’t compete with general intelligence?<p>Imagine selling intelligence with a legal term that, under strict interpretation, says you’re not allowed to use it for anything.<p>Is it so vague it’s unenforceable?<p>How do we own the output if we can’t use it to compete with a general intelligence?<p>Is it just a “lol nerd no one cares about the legal terms” thing? If no one cares then why would they have a blanket prohibition on using the service ?<p>We’re supposed to accept liability to lose a lawsuit just to accept their slop? So many questions
When you have model lock in, it’s a big detriment to use because if anyone comes out with SOTA models, and you have already invested infra development on this, you are stuck. Even if you open it up, it’s likely not to work as your model is likely trained specifically on that CLI. Just look at Codex CLI, you can use Gemini 2.5 pro, but it will get randomly stuck or fail a lot vs OpenAI models
The new GitHub action is exactly what I have been looking for <a href="https://docs.anthropic.com/en/docs/claude-code/github-actions" rel="nofollow">https://docs.anthropic.com/en/docs/claude-code/github-action...</a> but there doesn't seem to be a way to use it with the Claude Code's Max plan?<p>As it only accepts an API key as far as I can tell.
This is great! Especially the GitHub Actions issue/PR integration[0] that’s paired with this is exactly what I’ve been wanting!<p>[0]: <a href="https://docs.anthropic.com/en/docs/claude-code/github-actions" rel="nofollow">https://docs.anthropic.com/en/docs/claude-code/github-action...</a>
Hasn't this been invented already in multiple shapes and forms..? I wrote my own version clai[1] over a year ago which does exactly this, only that it has tools support + is multi vendor.<p>[1]: <a href="https://github.com/baalimago/clai">https://github.com/baalimago/clai</a>