Butter
AI
llm caching proxy
SHOW HN2025
How HN took it
4 positive, 3 neutral or asking, 0 mixed, 1 critical, out of 8 comments about the project. Thread score +0.39.
Idea: 3 for, 0 againstDocs: 0 for, 1 againstExecution: 1 for, 0 against
The thread, comment by comment
Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.
positive neutral or mixed critical about another commenter or something else the maker
What HN said
What people liked
Simple proxy design makes integration easy via a URL swap
From 2 comments
I've known Erik for a while now — simply incredible founder. Doing this as a simple API proxy makes this practically effortless to integrate into existing systems, just a simple…
MorganGallant on HNExciting to see a product like this launch! There are obviously a host of ‘memory’ solutions out there that try to integrate in fancy ways to cache knowledge / save tokens, but I…
ketan_around on HN
Idea of cache reuse for repetitive LLM inference is promising
From 1 comment
logged back in to HN to comment on this. looks really sick - i've been saying for a while that a surprising amount of LLM inference really comes down to repetition down a known…
samraaj on HN
Objections
Value proposition and what gets cached is unclear
From 2 comments
Still not clear - the tool calls come from the model, so what is being cached by Muscle Memory? Also: ``` After my time building computer-use agents, I’m convinced that the…
bigwheels on HNAre you able to walk through a specific use case or example case in detail? I'm not yet totally grokking what Butter is going to do exactly.
bigwheels on HN
Requests
Concrete walkthrough of a use case
From 1 comment
Are you able to walk through a specific use case or example case in detail? I'm not yet totally grokking what Butter is going to do exactly.
bigwheels on HN
Inject prompt cache tokens to save cost rather than bypass generations
From 1 comment
An interesting alternative product to offer is injecting prompt cache tokens into requests where they could be helpful; not bypassing generations but at least low hanging fruit…
edunteman on HN
Questions
How to integrate with LangChain, AutoGPT and robotics stacks
From 1 comment
looks pretty cool! How would you integrate this into production agent stacks like langchain, autogpt, even closed loop robotics?
tsvoboda on HN
Alternatives named
Prompt caching features offered by LLM providers
From 1 comment
An interesting alternative product to offer is injecting prompt cache tokens into requests where they could be helpful; not bypassing generations but at least low hanging fruit…
edunteman on HN
Memory solutions for LLM knowledge caching
From 1 comment
Exciting to see a product like this launch! There are obviously a host of ‘memory’ solutions out there that try to integrate in fancy ways to cache knowledge / save tokens, but I…
ketan_around on HN