https://hotkv.com/blogEngineering notes, benchmarks and product news from HotKV.en-gbhttps://hotkv.com/blog/ai-agent-memoryhttps://hotkv.com/blog/ai-agent-memoryAI 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.Sun, 18 Oct 2026 04:20:00 GMTGuides https://hotkv.com/blog/mcp-server-for-agent-memoryhttps://hotkv.com/blog/mcp-server-for-agent-memoryAn 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.Sun, 18 Oct 2026 04:20:00 GMTGuides https://hotkv.com/blog/prompt-caching-vs-semantic-cachinghttps://hotkv.com/blog/prompt-caching-vs-semantic-cachingPrompt caching makes a repeated prefix cheaper. Semantic caching removes the model call. How each works, what we measured and which to use when.Sun, 18 Oct 2026 04:20:00 GMTGuides https://hotkv.com/blog/vector-search-benchmarkhttps://hotkv.com/blog/vector-search-benchmarkHotKV and Redis 8.10.2 vector search on 100,000 and 999,000 embeddings from 1 to 100 clients: throughput, latency, recall, loading speed, memory and limits.Wed, 14 Oct 2026 06:00:00 GMTEngineering https://hotkv.com/blog/token-savings-benchmarkhttps://hotkv.com/blog/token-savings-benchmarkFour 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.Fri, 25 Sep 2026 06:00:00 GMTEngineering https://hotkv.com/blog/introducing-hotkvhttps://hotkv.com/blog/introducing-hotkvWhy I built HotKV, a multithreaded, Redis-compatible data store written from scratch in modern C++, what it offers today and how it did in our benchmark.Mon, 06 Apr 2026 06:00:00 GMTAnnouncements