Butter
a muscle memory cache for LLMs. Today we launch Butter, an OpenAI-compatible API proxy that caches LLM generations and serves them deterministically on revisit.
Reactions (1)
Similar products
by description similarity
Butter
butter.devA Behavior Cache for LLMs
An LLM response cache that's aware of dynamic data
blog.butter.devIn this blog post, we discuss how Butter automatically caches templates corresponding to the messages in LLM interactions.
OpenLake is a high performance storage engine for efficient LLM inference and GPU Training
Local persistent memory store for LLM applications including claude desktop, github copilot, codex, antigravity, etc.
CasCache
github.commulti-generational cache with optimistic concurrency control