Tag
Using HotKV in language model applications: model calls, token accounting, response reuse and the quality trade-offs of semantic caching.
4 articles in LLMs
AI agent memory is more than a long context window. The four kinds an agent needs, how to store each and what to keep out, with HotKV commands.
An MCP server gives Claude Code or Cursor memory in HotKV through 28 fixed tools. Install it, connect it and limit it with read-only mode and namespaces.
Prompt caching makes a repeated prefix cheaper. Semantic caching removes the model call. How each works, what we measured and which to use when.
Four Claude models, 3,000 support requests each: HotKV caching cut model calls, tokens and API cost by about 70%. Results and answer-quality trade-offs.
Follow your curiosity