Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Show HN: I put an AI agent on a $7/month VPS with IRC as its transport layer

georgelarson.me

Post reply on HN
Print view View original

131–137 of 137 posts

Re: Show HN: I put an AI agent on a $7/month VPS with IRC as its transport layer

#131

Post by ekianjo »

selcuka wrote: post #60
ekianjo wrote: post #57

Earlier quoted context omitted.

The LLM is the key element here, not the 7 dollars VPS... The model itself has cost billions of dollars to train and of the service shuts down or is interrupted for some reason your fancy setup breaks like nothing.

> The model itself has cost billions of dollars to train But that has nothing to do with this use case, right? By the same logic, Linux has millions of man-hours went into it but we can use it for free on a $7 VPS. > service shuts down or is interrupted for some reason your fancy setup breaks like nothing No, it doesn't. That's what I meant by commodity. You can switch to another service and it will work just fine (u…

> Linux has millions of man-hours went into it but we can use it for free on a $7 VPS.

Bad analogy. I don't need an API to run Linux.

Re: Show HN: I put an AI agent on a $7/month VPS with IRC as its transport layer

#133

Post by kangraemin »

I did something similar with Slack as the transport layer. Threads work well as conversation context — the bot fetches previous thread messages and rebuilds the full history before each request. The part that got tricky was queueing.

The CLI can only handle one request at a time, so I ended up building a request queue that announces your position ("you're #3 in line").

IRC being single threaded probably has the same constraint. How do you handle concurrent users?

Re: Show HN: I put an AI agent on a $7/month VPS with IRC as its transport layer

#136

Post by farrukh23buttt »

This is a clever split, especially the public/private boundary and the use of IRC as a very lightweight transport. The part I found most interesting is that the transport is intentionally old and simple while the model layer is doing the real work — that seems like a nice way to keep the surface area small.

How are you deciding when to escalate from the public agent to the private one in practice — explicit tool calls, confidence thresholds, or something else?

Post reply on HN