llm_optimizer reduces LLM API costs by up to 80% through semantic caching, intelligent model routing, token pruning, and conversation history summarization. Strictly opt-in and non-invasive.

Required Ruby Version

>= 3.2.0

Authors

arun kumar

Versions

  1. 0.1.7

    1. source

      1. 0.1.7 source May 05, 2026 (25 KB)
  2. 0.1.6

    1. source

      1. 0.1.6 source May 04, 2026 (25 KB)
  3. 0.1.5

    1. source

      1. 0.1.5 source April 22, 2026 (24 KB)
  4. 0.1.4

    1. source

      1. 0.1.4 source April 13, 2026 (22 KB)
  5. 0.1.3

    1. source

      1. 0.1.3 source April 10, 2026 (21 KB)
Show all versions (8 total)

Pushed by

arunsdev

SHA 256 checksum

← Previous version