stokry/semantic-cache

Cache LLM responses using semantic similarity matching. Similar questions return cached answers instantly, cutting API costs dramatically.

2 best points · 2 comments · 1 Hacker News post · 5 GitHub stars · View on GitHub

Hacker News discussions

• Show HN: SemanticCache – Save 70%+ on LLM API costs with semantic caching (Ruby) (2 points, 2 comments, by stokry, 2026-01-29)