Building Sulci, the semantic cache for LLM apps and Agentic AI. When a new query means the same thing as a past one, you get the cached answer instead of another model call.Context-aware: pass a session and the same follow-up in two conversations searches with two different vectors.
Open source, Apache 2.0. Patent pending.
https://sulci.io
https://github.com/sulci-io/sulci-oss
pip install "sulci[sqlite]"