Show HN: Claude-thermos keeps your Claude session warm for you • Hacker News Board

Re: Show HN: Claude-thermos keeps your Claude session warm for you

#31

Post by foota » Thu, Jul 23, 2026, 9:18 PM UTC

s0ck_r4w wrote: post #14

jonas21 wrote: post #7

Is the 5-minute expiration correct? I thought it was more like ~1 hour.

You can set the retention globally (whole session) to 1 hour which will actually make it more expensive. The default is 5 minutes. *UPD:* actually it appears the default is authentication-dependent. API key gets 5 minutes, subscriptions - 1 hour.

Claiming that it's more expensive isn't true, it's workload dependent. Filling the cache (worst case) 12 times in an hour is much more expensive than caching it for an hour, and the cheapest is to have your 5m cache refilled by a ping like this is doing.

Imo it's their fault for not having pricing that aligns incentives.

Re: Show HN: Claude-thermos keeps your Claude session warm for you

#32

Post by s0ck_r4w » Thu, Jul 23, 2026, 9:22 PM UTC

SwellJoe wrote: post #29

This is just making it more expensive for everyone else, right? How Claude handles its sessions is none of my business. I'm going to let them do the best they can to provide good service for everyone, and if they can't/won't, I'll switch to a provider that can. Using these massive models is already pretty danged extravagant, I'm not going to demand to be at the front of the queue at all times, too.

How do a few extra requests with the same prefix make it more expensive for everyone else?

Re: Show HN: Claude-thermos keeps your Claude session warm for you

#33

Post by boc » Thu, Jul 23, 2026, 9:25 PM UTC

Interested in how the critics of approaches like this defend an agentic session (with Fable, for example) that stops and runs a multi-hour ML training session. It's a script, so the actual LLM convo goes stale, but then when the results get returned to the main thread you get an expensive cache hit without doing anything.

You would have avoided that cache hit if the LLM session was kept "alive" for those few hours. Why not automate the part where you keep the large main thread alive until you're ready to analyze the results?

Re: Show HN: Claude-thermos keeps your Claude session warm for you

#34

Post by sznio » Thu, Jul 23, 2026, 9:28 PM UTC

s0ck_r4w wrote: post #32

SwellJoe wrote: post #29

This is just making it more expensive for everyone else, right? How Claude handles its sessions is none of my business. I'm going to let them do the best they can to provide good service for everyone, and if they can't/won't, I'll switch to a provider that can. Using these massive models is already pretty danged extravagant, I'm not going to demand to be at the front of the queue at all times, too.

How do a few extra requests with the same prefix make it more expensive for everyone else?

you use more memory?

Re: Show HN: Claude-thermos keeps your Claude session warm for you

#35

Post by SwellJoe » Thu, Jul 23, 2026, 9:33 PM UTC

s0ck_r4w wrote: post #32

SwellJoe wrote: post #29

This is just making it more expensive for everyone else, right? How Claude handles its sessions is none of my business. I'm going to let them do the best they can to provide good service for everyone, and if they can't/won't, I'll switch to a provider that can. Using these massive models is already pretty danged extravagant, I'm not going to demand to be at the front of the queue at all times, too.

How do a few extra requests with the same prefix make it more expensive for everyone else?

Keeping a conversation with a very large model active requires hundreds of GB of memory. If my conversation can never be swapped out, like when I go to lunch or take an afternoon walk, that's several hundred GB not available for other users. If everybody does that, Anthropic needs even more infrastructure than the quarter trillion dollars in infra they're already using.

Re: Show HN: Claude-thermos keeps your Claude session warm for you

#36

Post by jaimehrubiks » Thu, Jul 23, 2026, 9:33 PM UTC

They should increase the cache to 10 minutes. 5 is just too low, you can even miss it by taking time to select a response from a question.

Re: Show HN: Claude-thermos keeps your Claude session warm for you

#37

Post by s0ck_r4w » Thu, Jul 23, 2026, 9:41 PM UTC

SwellJoe wrote: post #35

s0ck_r4w wrote: post #32

Earlier quoted context omitted.

How do a few extra requests with the same prefix make it more expensive for everyone else?

Keeping a conversation with a very large model active requires hundreds of GB of memory. If my conversation can never be swapped out, like when I go to lunch or take an afternoon walk, that's several hundred GB not available for other users. If everybody does that, Anthropic needs even more infrastructure than the quarter trillion dollars in infra they're already using.

The idea here is that your conversation is being swapped out for no good reason. The session is still active, as the subagents continue to make progress.

How is this comparable to going to lunch or taking a walk?

Re: Show HN: Claude-thermos keeps your Claude session warm for you

#38

Post by purpleidea » Thu, Jul 23, 2026, 9:42 PM UTC

I assumed (perhaps incorrectly, but it was a guess since I never dug into it) that less used "hot pockets" of previous inference gradually got more stale as time went on, and the conversation went elsewhere and didn't need those bits.

Hearing one byte refreshes the whole thing is huge! 5min is wayy too slow, because sometimes I want to spent more than 5 min looking at a diff before choosing where to go next.

Kind of outrageous, I hope this kind of feature gets built into claude code =D

Re: Show HN: Claude-thermos keeps your Claude session warm for you

#39

Post by SwellJoe » Thu, Jul 23, 2026, 9:48 PM UTC

s0ck_r4w wrote: post #37

SwellJoe wrote: post #35

Earlier quoted context omitted.

Keeping a conversation with a very large model active requires hundreds of GB of memory. If my conversation can never be swapped out, like when I go to lunch or take an afternoon walk, that's several hundred GB not available for other users. If everybody does that, Anthropic needs even more infrastructure than the quarter trillion dollars in infra they're already using.

The idea here is that your conversation is being swapped out for no good reason. The session is still active, as the subagents continue to make progress. How is this comparable to going to lunch or taking a walk?

Is that actually happening, though?

Re: Show HN: Claude-thermos keeps your Claude session warm for you

#40

Post by devnonymous » Thu, Jul 23, 2026, 9:53 PM UTC

SwellJoe wrote: post #29

This is just making it more expensive for everyone else, right? How Claude handles its sessions is none of my business. I'm going to let them do the best they can to provide good service for everyone, and if they can't/won't, I'll switch to a provider that can. Using these massive models is already pretty danged extravagant, I'm not going to demand to be at the front of the queue at all times, too.

From the README:

> Detect the danger window. When the main lineage goes idle and a subagent is actively running, the main prefix is at risk of expiring.

So, this is not demanding to be at the front of the queue, it's just paying someone to take the place you already had in the queue, when you want to take a leak.