Agent Client Protocol (ACP) • Hacker News Board

Re: Agent Client Protocol (ACP)

#101

Post by nsonha » Thu, Sep 04, 2025, 4:20 AM UTC

hari-trata wrote: post #26

I 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. O…

I don't know about other protocols but for this one it's because AI vendors decided to ship their agents in the form of TUIs, which are not programmable. They need to be wrapped into something to be build on top of.

I actually prefer something like opencode which is one TUI to rule them all (albeit still lacking in some area), it also provides an an SDK that abstracts away the underlying model.

Re: Agent Client Protocol (ACP)

#102

Post by gtsop » Fri, Sep 05, 2025, 12:20 PM UTC

nsonha wrote: post #100

gtsop wrote: post #93

Earlier quoted context omitted.

Because there is no ai hype in LSP. AI is literally going through the same phase as early javascript libraries did. An explosion of tools, completely ignoring/bypassing previous accumulated knowledge, solving the wrong problems with the wrong tools. And this will pile up the bloat stack, similar to js libraries, because new problems will rise from the wrong solutions, requiring even more wrong solutions to be incorpo…

did you actually think about the question or you just want to shout an opinion? The question doesn't even make sense, there is no overlap between LSP and ACP

Your response is an exact proof of what I said in my comment. Thanks

Edit: Ok elaboration for the well intended. There is a HUGE overlap of LSP and ACP. LSP solves the problem of "oh we have many IDEs and many language integration plugins, we have an NxM problem, let's make it a N+M". ACP goes to do exactly that but for agents (which is an implementation detail), which means they could very well piggy back on top of LSP

Re: Agent Client Protocol (ACP)

#103

Post by nsonha » Fri, Sep 05, 2025, 4:21 PM UTC

gtsop wrote: post #102

nsonha wrote: post #100

Earlier quoted context omitted.

did you actually think about the question or you just want to shout an opinion? The question doesn't even make sense, there is no overlap between LSP and ACP

Your response is an exact proof of what I said in my comment. Thanks Edit: Ok elaboration for the well intended. There is a HUGE overlap of LSP and ACP. LSP solves the problem of "oh we have many IDEs and many language integration plugins, we have an NxM problem, let's make it a N+M". ACP goes to do exactly that but for agents (which is an implementation detail), which means they could very well piggy back on top of…

The overlap being... they are both... protocols?

Re: Agent Client Protocol (ACP)

#104

Post by makeboss » Tue, Sep 09, 2025, 9:39 AM UTC

gtsop wrote: post #102

nsonha wrote: post #100

Earlier quoted context omitted.

did you actually think about the question or you just want to shout an opinion? The question doesn't even make sense, there is no overlap between LSP and ACP

Your response is an exact proof of what I said in my comment. Thanks Edit: Ok elaboration for the well intended. There is a HUGE overlap of LSP and ACP. LSP solves the problem of "oh we have many IDEs and many language integration plugins, we have an NxM problem, let's make it a N+M". ACP goes to do exactly that but for agents (which is an implementation detail), which means they could very well piggy back on top of…

This kind of arguments don't make sense because of scope creep. LSP is for programming languages, why would the maintainers of LSP consider AI agents as a valid language server? And ACP is useful beyond code editors that supporting LSP just for the sake of it makes even less sense.