Steven Gonsalvez

Software Engineer

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

Why CEREBRO kept it

Claude session management, context-window optimization

The text below is an automated extraction of the article at https://github.com/izeigerman/claude-thermos, stored verbatim in the public cerebro-vault repository. Copyright remains with the original publisher (github.com).

Stop paying to rebuild your Claude Code cache. When your main agent waits on a subagent for more than 5 minutes, its prompt cache silently expires, and the next turn re-encodes your entire conversation at the write rate instead of reading it back cheap. On long sessions with many subagents that's roughly 20% of your bill. claude-thermos keeps the cache warm so you never pay that tax. Run Claude Code exactly as you normally would, but through claude-thermos with uvx: uvx claude-thermos # instead of: claude uvx claude-thermos -p "fix the bug" # any claude args pass straigh

Community take

Cache expiry is 1 hour (not 5 minutes), making the cost of pings to keep it warm exceed session value; won't survive Anthropic policy shifts.

Backlinks

Appeared in 1 briefing

Related

Shares tags: ai/agents · ai/llm-mechanics

Also from github.com