This product was not featured by Product Hunt yet. It will not be visible on their landing page and won't be ranked (cannot win product of the day regardless of upvotes).
A context-aware semantic cache: when a new query means the same thing as a past one, agents get the cached answer instead of paying again. Open source. Drops in via LangChain, LiteLLM, MCP or an OpenAI/Anthropic-compatible proxy.
Hi Product Hunt, I'm Kathiravan, the maker of Sulci.
Sulci is a semantic cache: when a new question means the same thing as one your app already answered, it returns the cached answer instead of calling the model again. I built it after counting what an agent actually sends to its LLM. In our benchmark the median 200-dispatch agent session sent 2 of them to the model once the cache was warm.
What I'm proudest of is a number most caches don't publish: on a corpus where 39% of questions have no correct cached answer, Sulci correctly says "I don’t have that" 98.9% of the time (98.15–99.38% across four seeded draws).
It's context-aware: give it a session and lookups take the conversation into account. On the hosted tier, an answer that only makes sense inside one conversation is never shared with another.
Adopting it costs a line or less: one line for LangChain/LangGraph, one call for LiteLLM, a base-URL change for any OpenAI or Anthropic client, or an MCP server for agents that can't import Python. It's open source (Apache 2.0), runs on SQLite, Chroma, Qdrant, FAISS, Redis or Milvus, and the hosted tier and its free dashboard went generally available this week.
I'd love feedback, especially if you try it on your own traffic and the numbers disagree with mine.
No comment highlights available yet. Please check back later!
About Sulci on Product Hunt
“Semantic cache for LLM apps and AI agents”
Sulci was submitted on Product Hunt and earned 2 upvotes and 1 comments, placing #148 on the daily leaderboard. A context-aware semantic cache: when a new query means the same thing as a past one, agents get the cached answer instead of paying again. Open source. Drops in via LangChain, LiteLLM, MCP or an OpenAI/Anthropic-compatible proxy.
Sulci was featured in API (98.9k followers), Open Source (69.1k followers), Developer Tools (523.3k followers) and GitHub (41.5k followers) on Product Hunt. Together, these topics include over 160.8k products, making this a competitive space to launch in.
Who hunted Sulci?
Sulci was hunted by Kathiravan Sengodan. A “hunter” on Product Hunt is the community member who submits a product to the platform — uploading the images, the link, and tagging the makers behind it. Hunters typically write the first comment explaining why a product is worth attention, and their followers are notified the moment they post. Around 79% of featured launches on Product Hunt are self-hunted by their makers, but a well-known hunter still acts as a signal of quality to the rest of the community. See the full all-time top hunters leaderboard to discover who is shaping the Product Hunt ecosystem.
Want to see how Sulci stacked up against nearby launches in real time? Check out the live launch dashboard for upvote speed charts, proximity comparisons, and more analytics.
Hi Product Hunt, I'm Kathiravan, the maker of Sulci.
Sulci is a semantic cache: when a new question means the same thing as one your app already answered, it returns the cached answer instead of calling the model again. I built it after counting what an agent actually sends to its LLM. In our benchmark the median 200-dispatch agent session sent 2 of them to the model once the cache was warm.
What I'm proudest of is a number most caches don't publish: on a corpus where 39% of questions have no correct cached answer, Sulci correctly says "I don’t have that" 98.9% of the time (98.15–99.38% across four seeded draws).
It's context-aware: give it a session and lookups take the conversation into account. On the hosted tier, an answer that only makes sense inside one conversation is never shared with another.
Adopting it costs a line or less: one line for LangChain/LangGraph, one call for LiteLLM, a base-URL change for any OpenAI or Anthropic client, or an MCP server for agents that can't import Python. It's open source (Apache 2.0), runs on SQLite, Chroma, Qdrant, FAISS, Redis or Milvus, and the hosted tier and its free dashboard went generally available this week.
I'd love feedback, especially if you try it on your own traffic and the numbers disagree with mine.