Claude-thermos - Keeps your Claude session cache warm
Show HN: Claude-thermos – keeps your Claude session warm for you
Claude-thermos is a smart tool designed to prevent costly prompt cache expirations during long Claude Code sessions. When subagents run longer than five minutes, the main agent's cache often times out, forcing expensive re-encoding of conversation history. This utility acts as a local reverse proxy, automatically sending lightweight 'warm' requests to keep the cache active in the background. By simply wrapping your standard CLI commands, it saves developers roughly 20% on their API bills by ensuring conversation history is read cheaply rather than rewritten at full cost.
Stop paying to rebuild your Claude Code cache; this tool ensures you never pay that tax by keeping your session warm.
- SwellJoe
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.
- leemoore
If you're running the subscription, by default you are paying 2x for cache writes and you're getting an hour for expiry. So refreshing based on 5 min is wasteful. You need to detect whether you are in 5 min or 1 hour mode.
- unholiness
I've directly inspected calls for pro/Max plans and as of today they have 1hr cache expiries. This has definitely degraded to 5 min in the past but that's the behavior today.
If you're paying API rates, you can choose 5m or 1hr yourself (and pay different rates).
Keeping a 1hr cache warm could still be useful, sure, but outside that, I don't see much use of this today.
- Wowfunhappy
FYI, on Pro and Max plans caching lasts for one hour, not five minutes, unless you're currently using Extra Usage.
https://code.claude.com/docs/en/prompt-caching#on-a-claude-s...
(Thank you to EliasWatson for giving me this link just a few days ago, as I was previously confused too.)
- skeledrew
Yeah I do this manually by compacting the convo. The TTL is about an hour though, definitely not 5 minutes.