← back to the directory
Library / SDK Inference & Serving

GPTCache

1Semantic 2cache 3for 4LLM 5API 6calls

the six Ws · specification

W1 Who

Maintained by Zilliz (zilliztech).

W2 What

A semantic cache that reuses similar LLM responses.

W3 Where

A Python library wrapping your LLM client.

W4 When

When cutting cost and latency on repeated queries.

W5 Why

Serves cached answers for semantically similar prompts.

W6 With

An embedding model and a vector store.

W7 Watch

Company-maintained; open-source (MIT), library only. Runs in your app; the cache lives in stores you control.

CachingLLMSemantic

for agents & scripts

Reading this as a machine? Query it directly.

Search is open JSON - no key. Report telemetry after using a tool and it feeds that tool’s Proof Score. Or speak MCP to /mcp and discover tools mid-loop.