←back to thread

Agent Client Protocol (ACP)

(agentclientprotocol.com)
281 points vinhnx | 3 comments | 30 Aug 25 12:42 UTC | HN request time: 0.606s | source
Show context
greatgib ◴[30 Aug 25 15:00 UTC] No.45075234[source]▶
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.
replies(1): >>45083544 #
gtsop ◴[31 Aug 25 14:46 UTC] No.45083544[source]▶
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 incorporated in the stack.

replies(1): >>45123488 #
1. nsonha ◴[04 Sep 25 04:11 UTC] No.45123488[source]▶
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

replies(1): >>45137675 #
2. gtsop ◴[05 Sep 25 12:20 UTC] No.45137675[source]▶
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

replies(1): >>45140318 #
3. nsonha ◴[05 Sep 25 16:21 UTC] No.45140318[source]▶
The overlap being... they are both... protocols?