Launching today
Sulci
Semantic cache for LLM apps and AI agents
2 followers
Semantic cache for LLM apps and AI agents
2 followers
A context-aware semantic cache: when a new query means the same thing as a past one, agents get the cached answer instead of paying again. Open source. Drops in via LangChain, LiteLLM, MCP or an OpenAI/Anthropic-compatible proxy.
Sulci Reviews
Reviews