An LLM response cache that's aware of dynamic data
Raymond here from Butter.dev, an LLM response cache built as a chat-completions proxy. Today we're launching a key feature for the platform: the ability to generalize on dynamic, templated inputs. Caching at the HTTP request level has the obvious problem of generalizability. Nearly no request is identical, due to templated variables (like names) and metadata (like timestamps), so exact-match cache lookups rarely hit. We solve this at Butter by using LLMs to detect dynamic content in requests and derive their inter-relationships, allowing the cache entry to be stored as a template + variables…
An LLM response cache that's aware of dynamic data launched on January 7, 2026 with 17 votes, #754 of 14,584 launches that month and more than 90% of that year's launches.
In plain words
Butter.dev is an LLM response cache that works as a chat-completions proxy. It identifies dynamic content like names and timestamps within requests and stores responses as reusable templates with variables, enabling cache hits on similar but not identical requests. This approach is designed for teams running repetitive tasks like back-office automation, data processing, or agent-based workflows where request patterns are similar but contain varying data.
written from the facts on this page · September 2026
From the sources
In this blog post, we discuss how Butter automatically caches templates corresponding to the messages in LLM interactions.
As of last week, Butter’s proxy now offers automatic template induction for its response cache! We’ve prepared the following blog post to help explain its significance and potential to help you serve more LLM responses from cache. You can also read through our documentation on template-induction . Butter is a cache for LLM responses, sitting as an HTTP proxy between clients and LLM inference endpoints. Our main strategy for doing so is via template-aware response caching , something we discussed in an earlier post . We’ll cover it again here, as well as talk about the challenges involved in automating it. Rather than storing user-agent messages verbatim, a template-aware response cache…from blog.butter.dev
In the maker’s words, at launch
Raymond here from Butter.dev, an LLM response cache built as a chat-completions proxy. Today we're launching a key feature for the platform: the ability to generalize on dynamic, templated inputs. Caching at the HTTP request level has the obvious problem of generalizability. Nearly no request is identical, due to…
Does a similar job
all alternatives →
Butter – A Behavior Cache for LLMsOct 2025 · butter.dev · ▲50Hi HN! I'm Erik. We built Butter, an LLM proxy that makes agent systems deterministic by caching and replaying responses, so automations behave consistently across runs. - It’s a chat completions compatible endpoint, making it easy to drop into existing agents with a custom base_url - The cache is template-aware, meaning lookups can treat dynamic content (names, addresses, etc.) as variables You can see it in action in this demo where it memorizes tic-tac-toe games: https://www.youtube.com/watch?v=PWbyeZwPjuY Why we built this: before Butter, we were Pig.dev (YC W25), where we…
- BAButter, a muscle memory cache for LLMs2025 · docs.butter.dev · ▲23
Hi HN, Erik here. Today we launch Butter, an OpenAI-compatible API proxy that caches LLM generations and serves them deterministically on revisit. Since April, we’ve been working on this concept of “muscle memory,” or deterministic replay, for agent systems performing automations. You may recall our first post in May, launching a python package called Muscle Mem: https://news.ycombinator.com/item?id=43988381 Since then, the product has evolved entirely, now taking the form of an LLM Proxy. For a deep dive into this process, check out:…
Why write code if the LLM can just do the thing? (web app experiment)Nov 2025 · github.com · ▲436I spent a few hours last weekend testing whether AI can replace code by executing directly. Built a contact manager where every HTTP request goes to an LLM with three tools: database (SQLite), webResponse (HTML/JSON/JS), and updateMemory (feedback). No routes, no controllers, no business logic. The AI designs schemas on first request, generates UIs from paths alone, and evolves based on natural language feedback. It works—forms submit, data persists, APIs return JSON—but it's catastrophically slow (30-60s per request), absurdly expensive ($0.05/request), and has zero UI…
Demystifying Advanced RAG Pipelines2023 · github.com · ▲131I've built an advanced RAG (Retrieval-Augmented Generation) pipeline from scratch to demystify the complex mechanics of modern LLM-powered Question Answering systems. This repository features: -- An implementation of a sub-question query engine from scratch to answer complex user questions. -- Illustrative explanations that unveil the inner workings of the system. -- An analysis of the challenges I faced while working with the system, like prompt engineering and cost estimation. -- Qualitative comparison with similar frameworks like LlamaIndex, offering a broader perspective. Key Takeaway:…
More ai this month
the category →
Paintings by AI models: programs run through a simulation of oil paint.
AI · 21d ago · stillwet.art
PixVerse R2▲381A real-time world model you can explore and change
AI · 30d ago · world.pixverse.video
Source: Show HN post ↗ · launch text quoted in part
Launched alongside, January 2026
the whole month →- IN
Hey HN! I wanted to share something I built over the last few weeks: isometric.nyc is a massive isometric pixel art map of NYC, built with nano banana and coding agents. I didn't write a single line of code. Of course no-code doesn't mean no-engineering. This project took a lot more manual labor than I'd hoped! I wrote a deep dive on the workflow and some thoughts about the future of AI coding and creativity: http://cannoneyed.com/projects/isometric-nyc
AI · Jan 2026 · cannoneyed.com
Automatic AI-powered code reviews the moment you open a PR
Dev tools · Jan 2026 · kilo.ai
