Cache LLM responses using semantic similarity matching. Similar questions return cached answers instantly, cutting API costs by 70% or more. Works with OpenAI, Anthropic, and Gemini.

Required Ruby Version

>= 3.0.0

Authors

stokry

Versions

  1. 0.2.0

    1. source

      1. 0.2.0 source January 29, 2026 (15 KB)
  2. 0.1.0

    1. source

      1. 0.1.0 source January 29, 2026 (14 KB)

Pushed by

stokry

SHA 256 checksum

← Previous version