Get the latest tech news

Show HN: Butter – A Behavior Cache for LLMs


For Your LLM Butter is a cache that identifies patterns in LLM responses and saves you money by serving responses directly. It's also deterministic, allowing your AI systems to consistently repeat past behaviors.

None

Get the Android app

Or read this on Hacker News

Read more on:

Photo of LLMs

LLMs

Photo of butter

butter

Photo of behavior cache

behavior cache

Related news:

News photo

Our LLM-controlled office robot can't pass butter

News photo

Poker Tournament for LLMs

News photo

Should LLMs just treat text content as an image?