The big question is why it can't be just a LSP server or extension to the LSP protocol to provide all that might be needed by the LLM.
Agent Client Protocol (ACP)
21–30 of 104 posts
Re: Agent Client Protocol (ACP)
#22Claude, come up with a protocol for communicating between AI agents and IDEs/editors. Create node, python and rust libraries. Create a website with a landing page
Re: Agent Client Protocol (ACP)
#23Earlier quoted context omitted.
> Nowadays, it is better to write prompts Very big doubt . AI can help for a few very specific tasks, but the hallucinations still happen, and making things up (especially APIs) is unacceptable.
> but the hallucinations still happen, and making things up (especially APIs) is unacceptable. The new models are much better at reading the codebase first, and sticking to "use the APIs / libraries already included". Also, for new libraries there's context7 that brings in up-to-date docs. Again, newer models know how to use it (even gpt5-mini works fine with it).
What size of codebases are we talking here? I've had a lot of issues trying to do pretty much anything across a 1.7 million LOC codebase and generally found it faster to use traditional IDE functionalities.
I've had much more success with things under 20k LOC but that isn't the stuff that I really need any assistance with.
Re: Agent Client Protocol (ACP)
#24MCP also started as JSON-RPC over stdio. With solutions like GitHub Codespaces, devcontainers, or "background agents", I wonder if we'll see the development of JSON over SSE.
Currently, my environment uses Claude Code on bare metal, and my application runs in a container, and the agent can do "docker compose exec backend" without any restrictions (YOLO).
My biggest obstacles to adopting workflows with git worktree are the need to share the database engine (local resource constrains) and the initial migration time. Offloading to cloud might be interesting for that.
Re: Agent Client Protocol (ACP)
#25Earlier quoted context omitted.
> Nowadays, it is better to write prompts Very big doubt . AI can help for a few very specific tasks, but the hallucinations still happen, and making things up (especially APIs) is unacceptable.
Hard disagree. LLMs are now incredibly good for any coding task (with popular languages).
You can't disagree with facts. Every time I try to give a chance to all those LLMs, they always use old APIs, APIs that don't exist, or mix things up. I'll still try that once a month to see how it evolves, but I have never been amazed by the capabilities of those things.
> with popular languages
Don't know, don't care. I write C++ code and that's all I need. JS and React can die a painful death for all I care as they have injected the worst practices across all the CS field. As for Python, I don't need help with that thanks to uv, but that's another story.
Re: Agent Client Protocol (ACP)
#26I don’t see why we need so many protocols. In such a greenfield tech, many are eager to define rules. There’s already a protocol called AG-UI that does the similar thing, but even its purpose isn’t entirely clear to me.
Rather than rushing to create standards, I think the focus should be on building practical implementations, AI-centric UI components that actually help developers design more AI-friendly interfaces. Once the space matures and stabilizes, that’s when standardization will make more sense. Right now, it feels too early.
Re: Agent Client Protocol (ACP)
#27Earlier quoted context omitted.
> Nowadays, it is better to write prompts Very big doubt . AI can help for a few very specific tasks, but the hallucinations still happen, and making things up (especially APIs) is unacceptable.
In languages with strong compile-time checks (like say rust) the obvious problems can mostly be solved by having the agent try to compile the program as a last step, and most agents now do that on their own. In cases where that doesn't work (more permissive languages like python, or http APIs) you can have the AI write tests and execute them. Or ask the AI to prototype and test features separately before adding them…
> the obvious problems can mostly be solved by having the agent try to compile the program
The famous "It compiles on my machine." Is that where engineering is going? Spending $billions to get the same result as the laziest developer ever?
Re: Agent Client Protocol (ACP)
#28I would love it, but please don't add JSON-RPC to the world...
It's too heavy for editor.
Re: Agent Client Protocol (ACP)
#29I see they've also caught the RFC2119 bug. This "MUST", "SHALL", "MAY" thing is a linguistic blight on our standards landscape and should be eradicated. HTML5 is written without this unnecessary level of linguistic pretense and works fine.
If your proposed spec is full of "SHALL", "MUST", and "MAY", I'm going to dock you ten points of credibility from the outset. It's a signal you've set out to imitate the vibes of seminal RFC specs without independently considering the substance.
Re: Agent Client Protocol (ACP)
#30Why don’t they focus on IDE first? I still can’t use their IDE as my daily. They also need to hire someone for UI. It took me 10 minutes to figure out how to bring up their AI chat window.